Notice of Pre-AIA or AIA Status
This action is made in response to the amendments/remarks filed on 01/29/2026. This action is made FINAL.
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
The amendment filed 01/29/2026 has been entered. Claims 1, 7-14, 16, and 20 remain pending in the application. Claims 2-6, 15, and 17-19 have been cancelled. Claims 21-29 are newly added.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1, 7-14, 16, and 20-29 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Independent Claims
Step 1 analysis:
Claim 1 is drawn to a method (i.e., process), Claim 14 is drawn to a system, and Claim 20 is drawn to a non-transitory computer readable medium (i.e., manufacture), which are all within the four statutory categories. (Step 1 – Yes, the claims fall into one of the statutory categories).
Step 2A analysis – Prong One:
Claim 1 recites:
A method for configuring imaging parameters, implemented on a computing device having at least one processor and at least one storage device, comprising:
obtaining a user identifier of a user to be examined and one or more device parameters to be set of an imaging device;
determining target values of the one or more device parameters based on the user identifier, by:
obtaining user information relating to the user based on the user identifier;
determining historical values of one or more historical device parameters used in a reference historical scan based on the user information;
determining one or more first device parameters and one or more second device parameters from the one or more device parameters, wherein each first device parameter has a matched historical device parameter among the one or more historical device parameters, and each second device parameter has no matched historical device parameter among the one or more historical device parameters;
for each first device parameter, determining a reference value of the first device parameter based on a historical value of the historical device parameter matching the first device parameter;
determining reference values of the one or more second device parameters based on the reference values of the one or more first device parameters and an association model, wherein the association model is a machine learning model reflecting a correlation between the one or more first device parameters and the one or more second device parameters;
determining the target values of the one or more device parameters based on the reference values of the one or more first device parameters and the reference values of the one or more second device parameters;
performing parameter configuration on the imaging device based on the target values of the one or more device parameters; and
controlling the imaging device, on which the parameter configuration has been completed, to perform a scan on the user to be examined to obtain scan data.
The method as recited above in the underlined portions and the controlling the imaging device to perform a scan on the user, describes managing personal behavior or relationships or interactions between people including following rules or instructions, and therefore falls within the scope of certain methods of organizing human activity. Fundamentally, the method is that of a person gathering user information, including a user identifier, and parameters for imaging a person, using the information to set parameters for imaging, and controlling the imaging device, which encompasses a person interacting with another individual including following rules or instructions. Accordingly, the claim recites an abstract idea of managing interactions between people.
The series of steps as recited above in the underlined limitations also falls within the “mental processes” grouping of abstract ideas, and describes concepts that can be performed in the human mind through observation, evaluation, judgement, and opinion. Determining target values, reference values, and parameters, obtaining a user identifier, and performing parameter configuration based on the target values of the one or more device parameters can all be performed in the human mind, with or without the use of a physical aid. Therefore, the claim recites an abstract idea of a mental process.
Claim 20 recites/describes nearly identical steps as claim 1 (and therefore also recite limitations that fall within this subject matter grouping of abstract ideas), and these claims are therefore determined to recite an abstract idea under the same analysis.
Claim 14 recites:
A system for configuring imaging parameters, comprising:
at least one storage device storing a set of instructions; and
at least one processor configured to communicate with the at least one storage device, wherein when executing the set of instructions, the at least one processor is configured to direct the system to perform operations including:
obtaining a user identifier of a user to be examined and one or more device parameters to be set of an imaging device;
determining target values of the one or more device parameters based on the user identifier, by:
obtaining user information relating to the user based on the user identifier;
obtaining reference values of the one or more device parameters based on the user information, wherein the reference values of the one or more device parameters include a plurality of sets of reference values, the plurality of sets of reference values includes a first set of reference values and a second set of reference values, the first set of reference values is determined based on historical values of one or more historical device parameters used in a reference historical scan, and the second set of reference values is determined by processing the user information using a parameter prediction model, and the parameter prediction model is a machine learning model;
determining a recommendation degree of each set of the plurality of sets of reference values, wherein the recommendation degree of the first set of reference values is determined based on a count of device parameters that match the one or more historical device parameters among the one or more device parameters, and the recommendation degree of the second set of reference values is determined based on a count of usage of the second set of reference values by target reference users in target devices;
determining the target values of the one or more device parameters based on the recommendation degree of each set of the plurality of sets of reference values;
performing parameter configuration on the imaging device based on the target values of the one or more device parameters; and
controlling the imaging device, on which the parameter configuration has been completed, to perform a scan on the user to be examined to obtain scan data.
The system as recited above in the underlined portions and the controlling the imaging device to perform a scan on the user, describes managing personal behavior or relationships or interactions between people including following rules or instructions, and therefore falls within the scope of certain methods of organizing human activity. Fundamentally, the method is that of a person gathering user information, including a user identifier, and parameters for imaging a person, and using the information to set parameters for imaging, which encompasses a person interacting with another individual including following rules or instructions. Accordingly, the claim recites an abstract idea of managing interactions between people.
The series of steps as recited above in the underlined limitations also falls within the “mental processes” grouping of abstract ideas, and describes concepts that can be performed in the human mind through observation, evaluation, judgement, and opinion. Determining target values, reference values, and parameters, obtaining a user identifier, determining a recommendation degree, and performing parameter configuration based on the target values of the one or more device parameters can all be performed in the human mind, with or without the use of a physical aid. Therefore, the claim recites an abstract idea of a mental process.
Step 2A analysis – Prong 2:
This judicial exception is not integrated into a practical application. Specifically, independent claims 1, 14, and 20 recite the following additional elements beyond the abstract idea: the association model is a machine learning model; a computing device, a processor, a storage device; using a parameter prediction model, and the parameter prediction model is a machine learning model; and a non-transitory computer readable medium. These limitations are recited at a high level of generality and amount to no more than mere instructions to apply the exception using generic computer components. Additionally, the use of the models to carry out the abstract idea amounts to using a mathematical algorithm to apply the abstract idea, which amounts to mere instructions to apply the exception, as per MPEP 2106.05(f)(2). The limitations do not impose any meaningful limits on practicing the abstract idea, and therefore do not integrate the abstract idea into a practical application (see MPEP 2106.05(f)).
The additional elements do not show an improvement to the functioning of a computer or to any other technology, rather the additional elements perform general computing functions and do not indicate how the particular combination improves any technology or provides a technical solution to a technical problem. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Therefore, Claims 1, 14, and 20 are directed to an abstract idea without practical application. (Step 2A – Prong 2: No, the additional elements are not integrated into a practical application).
Step 2B analysis:
As discussed above in “Step 2A analysis – Prong 2”, the identified additional elements in Independent Claims 1, 14, and 20 are equivalent to adding the words “apply it” on a generic computer, and/or generally link the use of the judicial exception to a particular technological environment or field of use. Therefore, the claims as a whole do not amount to significantly more than the judicial exception itself.
For the role of a computer in a computer implemented invention to be deemed meaningful in the context of this analysis, it must involve more than performance of “well- understood, routine, [and] conventional activities previously known to the industry.” Further, “the mere recitation of a generic computer cannot transform a patent ineligible abstract idea into a patent-eligible invention.”
The applicant’s specification discloses: the machine learning model for the association model and the parameter prediction model may include a neural network (NN) model, a convolutional neural network (CNN) model, a recurrent neural network (RNN) model, etc. (see Applicant’s specification [0121] and [0138]), which are known algorithms. In addition, the use of the models to carry out the abstract idea amounts to using a mathematical algorithm to apply the abstract idea, which amounts to mere instructions to apply the exception, as per MPEP 2106.05(f)(2). The processing device may be a single server or group of servers and may be implemented on a cloud platform or provided virtually (see Specification par. 27-28). The unimodal medical imaging device may be an ultrasound (US) scanner, an X-ray scanner, a computed tomography (CT) scanner, a magnetic resonance imaging (MRI) scanner, a positron emission computed tomography (PET) scanner), an optical coherence tomography (OCT) scanner, an intravenous ultrasound (IVUS) scanner, a near infrared spectroscopy (NIS) scanner, a far infrared (FIR) scanner, etc., or any combination thereof. The multimodal medical imaging device may include an X-ray-magnetic resonance imaging (X-ray-MRI) scanner, a positron emission computed tomography-X- ray (PET-X-ray) scanner, a single photon emission computed tomography-magnetic resonance imaging (SPECT-MRI) scanner, a positron emission tomography-computed tomography (PET-CT) scanner, a digital subtraction angiography-magnetic resonance imaging (DSA-MRI) scanner, etc. (See specification par. 28).
The use of a computer or processor to merely automate or implement the abstract idea cannot provide significantly more than the abstract idea itself. (See MPEP 2106.05(f) where mere instructions to apply an exception does not render an abstract idea patent eligible). There is no indication that the additional limitations alone or in combination improves the functioning of a computer or any other technology, improves another technology or technical field, or effects a transformation or reduction of a particular article to a different state or thing. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as discussed above with respect to integration of the abstract idea into a practical application, using the additional elements to perform the steps for configuring imaging parameters amounts to no more than using computer related devices to implement the abstract idea. Therefore, the claims are not patent eligible. The Examiner has therefore determined that no additional element, or combination of additional claims elements is/are sufficient to ensure the claims amount to significantly more than the abstract idea identified above (Step 2B: Independent claims - NO).
Dependent Claims
Dependent Claims 7-13, 16, 24-25, and 27-29 are directed towards elements used to describe the determination of target values, reference values, and a matching process between historical device parameters and current device parameters. These elements include: (Claim 7) selecting a target reference user from at least two reference users and determining the historical scan of the target reference user as the reference historical scan; (Claim 8) obtaining a historical scan of the user and determining the historical scan of the user as the reference historical scan; (Claim 9) determining sets of reference values including a first set, determining a recommendation degree of each set, and determining the target values of the device parameters based on the recommendation degree; (Claim 10) a second set of reference values is determined based on a parameter prediction model, the recommendation degree of the first set of reference values is determined based on a count of the first device parameters that have matched historical device parameters, and the recommendation degree of the second set is determined based on a count of usage of the second set of reference values by target reference users; (Claim 11) determining sets of reference values, sending the sets to a user terminal, and determining one set as the target values based on a selection instruction received from the user terminal; (Claim 12) the user identifier includes a numeric identifier or a biometric identifier; (Claim 13) the user identifier includes a quick response (QR) code or bar code and the biometric identifier includes a fingerprint, face, voice or iris; (Claim 16) determining the historical values of the historical device parameters and determining the first set of reference values based on a matching relationship between the historical device parameters and device parameters; (Claim 24) determining first device parameters and second device parameters, determining a reference value of the first device parameter based on a historical value matching, and determining reference values of the second device parameters based on the reference values of the first device parameters; (Claim 25) the reference values of the second device parameters are determined based on the reference values of the first device parameters using an association model reflecting a correlation between the first and second device parameters; (Claim 27) the first set of reference values is determined by adjusting the historical values of the historical parameters based on a performance index of the imaging device and performance index of a historical imaging device; (Claim 28) selecting a target reference user from at least two reference users and determining the historical scan of the target reference user as the reference historical scan; (Claim 29) obtaining a historical scan of the user performed by a reference imaging device and determining the historical scan of the user as the reference historical scan. These elements describe managing personal behavior or relationships or interactions between people including following rules or instructions, and therefore fall within the same scope of certain methods of organizing human activity as the independent claims.
The elements as recited above in claims 7-9, 10-12, 16, 24-25, and 27-29 also falls within the “mental processes” grouping of abstract ideas, and describes concepts that can be performed in the human mind through observation, evaluation, judgement, and opinion. Determining historical values of historical device parameters, matching device parameters with historical device parameters, determining reference values, obtaining an association model, selecting a target reference user, determining the historical scan of the reference user, and determining a recommendation degree, are all tasks that can be performed in the human mind. Therefore, the dependent claims recite an abstract idea of a mental process.
Dependent claims 21-23 and 26 are directed to elements used to describe the association model, prediction model, and the determination and selection of target reference users. Claims 21 and 23 recite the training process of the association model and parameter prediction model comprises: inputting the plurality of training samples into the initial model, calculating a value of a loss function based on the labels and an output result of the initial model, and iteratively updating parameters of the initial model based on the value of the loss function until a predetermined condition is satisfied. This represents the creation of mathematical interrelationships between data. The training process involving calculating a value of a loss function and updating the model based on the loss function are mathematical calculations. As such, the training of the machine learning model represents a mathematical concept that is interpreted to be part of the identified abstract idea. Claims 22 and 26 recite the selection/determination of a target reference user by constructing vectors and utilizing the vectors in a vector database to designate a reference user. This also falls within the mathematical calculations grouping of abstract ideas, as constructing a vector is a mathematical concept.
This judicial exception is not integrated into a practical application. Specifically, the dependent
claims recite the following additional elements beyond the abstract idea: the association model being a machine learning model, the parameter prediction model being a machine learning model, sending the plurality of sets of reference values to a user terminal, and a quick response (QR) code or a bar code. These limitations are recited at a high level of generality and amount to no more than mere instructions to apply the exception using generic computer components. The limitations do not impose any meaningful limits on practicing the abstract idea, and therefore do not integrate the abstract idea into a practical application (see MPEP 2106.05(f)).
Specifically, the machine learning model for the association model and the parameter prediction model may include a neural network (NN) model, a convolutional neural network (CNN) model, a recurrent neural network (RNN) model, etc. (see Applicant’s specification [0121] and [0138]), which are known algorithms. In addition, the use of the models to carry out the abstract idea amounts to using a mathematical algorithm to apply the abstract idea, which amounts to mere instructions to apply the exception, as per MPEP 2106.05(f)(2). The reference imaging device refers to another imaging device that has performed the historical scan on the user to be examined and has the same or similar model number as the imaging device used in the current scan (See Specification [0104]. A target device refers to a device of the same type (e.g., the same model number) as the imaging device used by the user to be examined in the current examination scan (See Specification [0086]).
The limitation “sending the plurality of sets of reference values to a user terminal” is mere data gathering and output recited at a high level of generality, and thus is insignificant extra-solution activity. See MPEP 2106.05(g) (“whether the limitation is significant”).
The recitation of “the numeric identifier includes at least one of a quick response (QR) code or a bar code” is recited at a high level of generality and amounts to generally linking the abstract idea to a particular technological environment (See MPEP 2106.04(d)(I)).
The additional elements do not show an improvement to the functioning of a computer or to
any other technology, rather the additional elements perform general computing functions and do not
indicate how the particular combination improves any technology or provides a technical solution to a
technical problem. Accordingly, these additional elements, when considered separately and as an
ordered combination, do not integrate the abstract idea into a practical application because they do not
impose any meaningful limits on practicing the abstract idea. Therefore, the dependent claims are
directed to an abstract idea without practical application.
The use of a computer or processor to merely automate or implement the abstract idea cannot
provide significantly more than the abstract idea itself. (See MPEP 2106.05(f) where mere instructions to apply an exception does not render an abstract idea patent eligible). There is no indication that the
additional limitations alone or in combination improves the functioning of a computer or any other
technology, improves another technology or technical field, or effects a transformation or reduction of a
particular article to a different state or thing. Therefore, the claims are not patent eligible.
The Examiner has therefore determined that no additional element, or combination of
additional claims elements is/are sufficient to ensure the claims amount to significantly more than the
abstract idea identified above.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 7-9, 12-13, and 20-21 are rejected under 35 U.S.C. 103 as being unpatentable over Sun (US 2022/0192619), in view of Srinivasan et al. (CN 109069100 A) (Hereinafter Srinivasan).
Regarding Claim 1, Sun teaches the following:
A method for configuring imaging parameters (Sun [0002] and [0047] discloses methods for determining a value of a procedure parameter related to a procedure of a target subject and causing a medical device to scan a target subject based on a value of an imaging scan parameter), implemented on a computing device having at least one processor and at least one storage device (Sun [0056] and Fig. 2 discloses a computing device (item 200) that may include a processor (item 210) and storage (item 220)), comprising:
obtaining a user identifier of a user to be examined (Sun [0041] and [0076] discloses a processing device that can obtain target prior information of the target subject based on the feature information of the target subject. The feature information of the target subject may include identity information) and one or more device parameters to be set of an imaging device (Sun [0041] discloses the processing device may determine, based on the target prior information of the target subject, a value of a procedure parameter (e.g., a value of an imaging scan parameter) that relates to a procedure (e.g., a CT scan, an MRI scan, a PET scan) of the target subject using a medical device));
determining target values of the one or more device parameters based on the user identifier (Sun [0041] discloses the processing device may determine, based on the target prior information of the target subject, a value of a procedure parameter); and
obtaining user information relating to the user based on the user identifier (Sun [0076] discloses the feature information of the target subject may include identify information (e.g., an identification (ID) number, a name, the gender, the age, a date of birth, an occupation), contact information (e.g., a mobile phone number), medical information (e.g., a medical record number, a registration card number, a health condition, a medical history), shape information (e.g., a width, a thickness, a height, a weight) of the target subject or a portion thereof, or the like, or any combination thereof);
determining historical values of one or more historical device parameters used in a reference historical scan based on the user information (Sun [0019] discloses the prior information database may be established based on at least one of feature information of a candidate subject, a historical scan protocol of the candidate subject, a historical value of an imaging scan parameter of the candidate subject, a historical value of an image reconstruction parameter of the candidate subject, historical scan data of the candidate subject, a historical image of the candidate subject, etc.);
determining one or more first device parameters and one or more second device parameters from the one or more device parameters, wherein each first device parameter has a matched historical device parameter among the one or more historical device parameters (Sun [0042], [0089], and [0128] discloses the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated with one or more historical scans of the target subject. In addition, the processing device may determine whether a historical scan protocol corresponding to the recommended value of the procedure parameter is the same as or similar to a current scan protocol of the target subject. In response to determining that the candidate value of the procedure parameter satisfies the scan condition, the processing device may determine the candidate value of the procedure parameter as the value of the procedure parameter), and each second device parameter has no matched historical device parameter among the one or more historical device parameters (Sun [0088] discloses that a scan condition of the target subject may be different from a historical scan condition of the target subject in the target prior information);
for each first device parameter, determining a reference value of the first device parameter based on a historical value of the historical device parameter matching the first device parameter (Sun [0042] and [0128] discloses the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated with one or more historical scans of the target subject. In addition, the processing device may determine whether a historical scan protocol corresponding to the recommended value of the procedure parameter is the same as or similar to a current scan protocol of the target subject);
determining reference values of the one or more second device parameters based on the reference values of the one or more first device parameters (Sun [0088] discloses examples for when a scan parameter does not have a matching reference value. For example, if a historical scan region is the feet of the target subject, and an actual scan region is the head of the target subject, the processing device may determine a value of the procedure parameter (e.g., a tube voltage, a tube current) corresponding to the head by increasing a historical value of the procedure parameter corresponding to the feet, due to the head have more osseous tissue than the feet.) and an association model, wherein the association model is a machine learning model reflecting a correlation between [device parameters] ([0102], [0111], [0113] the plurality of simulation values of the imaging scan parameter may be determined using the dose simulation model, the candidate scan data corresponding to the candidate value of the imaging scan parameter. The dose simulation model may be generated based on deep learning. The dose simulation model refers to a model (e.g., a machine learning model) or an algorithm for determining a first image corresponding to a first value of the imaging scan parameter based on a second image corresponding to a second value of the imaging scan parameter.);
determining the target values of the one or more device parameters ([0041], [0089] The processing device may determine, based on the target prior information of the target subject, a value of a procedure parameter (e.g., a value of an imaging scan parameter, a value of an image reconstruction parameter) that relates to a procedure (e.g., a CT scan, an MRI scan, a PET scan) of the target subject using a medical device. In some embodiments, the processing device may obtain scan data of the target subject by causing the medical device to scan the target subject based on a value of the imaging scan parameter. The processing device may determine whether the candidate value (e.g., a historical value, a simulation value) of the procedure parameter of the target subject in the target prior information satisfies the scan condition. In response to determining that the candidate value of the procedure parameter satisfies the scan condition, the processing device may determine the candidate value of the procedure parameter as the value of the procedure parameter. In response to determining that the candidate value of the procedure parameter does not satisfy the scan condition, the processing device may adjust (by, e.g., increasing, decreasing) the candidate value of the procedure parameter. The processing device may determine the adjusted candidate value of the procedure parameter as the value of the procedure parameter.) based on the reference values of the one or more first device parameters ([0042] the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated with one or more historical scans of the target subject and/or simulation data (e.g., simulation scan data, a simulated image, a simulation value of the procedure parameter) of the target subject stored in the prior information database) and the reference values of the one or more second device parameters (Sun [0088] discloses examples for when a scan parameter does not have a matching reference value. For example, if a historical scan region is the feet of the target subject, and an actual scan region is the head of the target subject, the processing device may determine a value of the procedure parameter (e.g., a tube voltage, a tube current) corresponding to the head by increasing a historical value of the procedure parameter corresponding to the feet, due to the head have more osseous tissue than the feet.);
performing parameter configuration on the imaging device based on the target values of the one or more device parameters (Sun [0044] and [0047] discloses the medical device may be configured to acquire image data relating to a subject (e.g., a target subject) and that the processing device may cause a medical device to scan the target subject based on a value of an imaging scan parameter); and
controlling the imaging device, on which the parameter configuration has been completed, to perform a scan on the user to be examined ([0070], [0071] The determination module may select a value of the imaging scan parameter from the plurality of target values of the imaging scan parameter. The control module may be configured to control one or more components (e.g., the medical device) of the medical system. For example, the control module may cause a medical device (e.g., the medical device) to scan a target subject based on a value of an imaging scan parameter.).
However, Sun does not explicitly teach the following that is met by Srinivasan:
wherein the association model is a machine learning model reflecting a correlation between the one or more first device parameters and the one or more second device parameters (Pg. 11, para. 3-5 and Pg. 9, para. 6: the processor can determine a desired output including imaging parameters such as saturation, contrast (global or local), sharpness, brightness, dynamic range, one or any combination of spatial filter, etc. The model uses as input imaging parameters such as a spatial gradient, boundary pixel, beam forming, radio frequency (RF), channel data, Doppler data, etc. The model may produce output including imaging parameter ranges such as dynamic range, spatial filter, edge enhancement, contrast enhancement, imaging frequency, linear density, etc. based on the input parameters. Therefore, the examiner interprets this model to produce an output of desired imaging parameters (i.e., second device parameters) based on input of different imaging parameters (i.e., first device parameters), showing a correlation between the first and second parameters. The model may include one or any combination of several of method, algorithm, process, formula, rule or the like, such as a feedforward neural network (FNN), recurrent neural network (RNN), Kohonen self-organizing maps, automatic coder, probabilistic neural network (PNN). Time delay neural network (TDNN), radial basis function network (RBF), learning vector quantization, a convolutional neural network (CNN), one or any combination of several of adaptive linear neuron (ADALINE) model, the associated neural network (ASNN) and so on. An exemplary recurrent neural network (RNN) may include Hopfield network, Boltzmann machine, echo state network, long term memory network, bidirectional recurrent neural network, hierarchical recurrent neural network, one kind or the combination of optional several kinds in random nerve network and the like.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to have combined the method for determining values of imaging parameters, as taught by Sun, with the model that reflects a correlation between first and second device parameters, as taught by Srinivasan, because the model allows the processor to process images in an improved way, and allows for an improved user experience (See Srinivasan Pg. 10, para. 2).
Regarding Claim 7, the combination of Sun and Srinivasan teaches the method of claim 1, and Sun further discloses the following:
The method of claim 1, further comprising:
selecting a target reference user from at least two reference users based on the user information, wherein each of the at least two reference users has received a historical scan performed by a historical imaging device (Sun [0104], [0050], and [0084] discloses that the sample image and the reference image may be historical images reconstructed based on historical scan data of a sample subject during a historical scan. The sample subject may be the same as or different from the target subject. The prior information can include information of a plurality of candidate subjects. The processing device may select a candidate subject with the highest degree of similarity to the target subject among the plurality of candidate subjects, or a portion thereof (e.g., among the plurality of candidate subjects, those who share at least one similar feature with the target subject), in the prior information database.); and
determining the historical scan of the target reference user as the reference historical scan (Sun [0104] discloses the reference image may be obtained based on the sample image, the sample value of the imaging scan parameter, and the reference value of the imaging scan parameter).
Regarding Claim 8, the combination of Sun and Srinivasan teaches the method of claim 1, and Sun further discloses the following:
The method of claim 1, further comprising:
obtaining, based on the user information, a historical scan of the user performed by a reference imaging device ([0019] the prior information database may be established based on at least one of feature information of a candidate subject, a historical scan protocol of the candidate subject); and
determining the historical scan of the user as the reference historical scan (Sun [0042] discloses the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated).
Regarding Claim 9, the combination of Sun and Srinivasan teaches the method of claim 1, and Sun further discloses the following:
The method of claim 1, wherein the determining the target values of the one or more device parameters ([0018] The method may include, in response to determining that the recommended value of the procedure parameter satisfies the scan condition, determining the value of the procedure parameter based on the recommended value of the procedure parameter) includes:
determining a plurality of sets of reference values based on the user information (Sun [0041], [0129] The processing device may obtain target prior information of the target subject based on the feature information of the target subject and a prior information database. The prior information database may include prior information of a plurality of candidate subjects. The processing device may determine values of a plurality of imaging scan parameters (e.g., the tube voltage, the tube current, and the scan time)), wherein the plurality of sets of reference values include a first set of reference values, the first set of reference values includes the reference value of each first device parameter ([0042] the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated with one or more historical scans of the target subject and/or simulation data (e.g., simulation scan data, a simulated image, a simulation value of the procedure parameter) of the target subject stored in the prior information database) and the reference value of each second device parameter (Sun [0088], [0129], Fig. 6 discloses examples for when a scan parameter does not have a matching reference value. For example, if a historical scan region is the feet of the target subject, and an actual scan region is the head of the target subject, the processing device may determine a value of the procedure parameter (e.g., a tube voltage, a tube current) corresponding to the head by increasing a historical value of the procedure parameter corresponding to the feet, due to the head have more osseous tissue than the feet. In response to determining that the prior information database does not include a recommended radiation dose of the target subject, the processing device may determine the value of the procedure parameter of the target subject based on candidate values through process 600.);
determining a recommendation degree of each set of the plurality of sets of reference values (Sun [0083] discloses that in some embodiments, a degree of similarity between the specific candidate subject and the target subject may reach or exceed a threshold (e.g., 80%, 85%, 90%, 95%)); and
determining the target values of the one or more device parameters based on the recommendation degree of each set of the plurality of sets of reference values (Sun [0083]-[0084] discloses the processing device (e.g., the determination module) may determine, based on the target prior information of the target subject which includes a degree of similarity between the target and another subject, a value of a procedure parameter that relates to a procedure of the target subject using a medical device.).
Regarding Claim 12, the combination of Sun and Srinivasan teaches the method of claim 1, and Sun further discloses the following:
The method of claim 1, wherein the user identifier includes at least one of a numeric identifier (Sun [0076] discloses the feature information of the target subject may include identity information (e.g., and identification (ID) number, a medical record number, a registration card number, etc.)) or a biometric identifier (Sun [0077] discloses an image capturing device (e.g., a camera) may capture the image data of the target subject, and the processing device may determine the feature information of the subject based on the image data according to an image analysis algorithm (e.g., an image segmentation algorithm, a feature point extraction algorithm)).
Regarding Claim 13, the combination of Sun and Srinivasan teaches the method of claim 12, and Srinivasan further discloses the following::
The method of claim 12, wherein the numeric identifier includes at least one of a quick response (QR) code or a bar code (See Pg. 8, par. 4: can receive input via a bar code or a quick response (QR) code scanning device receives user and/or patient); or
the biometric identifier includes at least one of a fingerprint, a face, a voice, or an iris (See Pg. 8, par. 4: user identification can be through the biological identification device (e.g., a voice recognition device, a facial recognition device, a fingerprint identification device, an iris identification device, etc.)).
It would have been obvious to one of ordinary skill in the art before the effective filing date to have combined the method of identifying a user, as taught by Sun, with the user identification as described in Srinivasan because the claimed invention is only a combination of these well-known elements which would have performed the same function in combination as each did separately. Sun already discloses using identifiers to identify a user for the method, and based on the teachings of Srinivasan, the use of biometric identifiers and/or numeric identifiers would perform the same functions of identifying a user as Sun does. Therefore, the results would have been predictable to one of ordinary skill in the art (MPEP 2143).
Regarding Claim 20, Sun teaches the following:
A non-transitory computer readable medium, comprising a set of instructions (Sun [0021] discloses a non-transitory computer readable medium may include at least one set of instructions),
wherein when executed by at least one processor, the set of instructions direct the at least one processor to effectuate a method (When executed by at least one processor of a computing device, the at least one set of instructions may cause the at least one processor to effectuate a method), the method comprising:
obtaining a user identifier of a user to be examined (Sun [0041] and [0076] discloses a processing device that can obtain target prior information of the target subject based on the feature information of the target subject. The feature information of the target subject may include identity information) and one or more device parameters to be set of an imaging device (Sun [0041] discloses the processing device may determine, based on the target prior information of the target subject, a value of a procedure parameter (e.g., a value of an imaging scan parameter) that relates to a procedure (e.g., a CT scan, an MRI scan, a PET scan) of the target subject using a medical device));
determining target values of the one or more device parameters based on the user identifier (Sun [0041] discloses the processing device may determine, based on the target prior information of the target subject, a value of a procedure parameter), by:
obtaining user information relating to the user based on the user identifier (Sun [0076] discloses the feature information of the target subject may include identify information (e.g., an identification (ID) number, a name, the gender, the age, a date of birth, an occupation), contact information (e.g., a mobile phone number), medical information (e.g., a medical record number, a registration card number, a health condition, a medical history), shape information (e.g., a width, a thickness, a height, a weight) of the target subject or a portion thereof, or the like, or any combination thereof);
determining historical values of one or more historical device parameters used in a reference historical scan based on the user information (Sun [0019] discloses the prior information database may be established based on at least one of feature information of a candidate subject, a historical scan protocol of the candidate subject, a historical value of an imaging scan parameter of the candidate subject, a historical value of an image reconstruction parameter of the candidate subject, historical scan data of the candidate subject, a historical image of the candidate subject, etc.);
determining one or more first device parameters and one or more second device parameters from the one or more device parameters, wherein each first device parameter has a matched historical device parameter among the one or more historical device parameters (Sun [0042], [0089], and [0128] discloses the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated with one or more historical scans of the target subject. In addition, the processing device may determine whether a historical scan protocol corresponding to the recommended value of the procedure parameter is the same as or similar to a current scan protocol of the target subject. In response to determining that the candidate value of the procedure parameter satisfies the scan condition, the processing device may determine the candidate value of the procedure parameter as the value of the procedure parameter), and each second device parameter has no matched historical device parameter among the one or more historical device parameters Sun [0088] discloses that a scan condition of the target subject may be different form a historical scan condition of the target subject in the target prior information);
for each first device parameter, determining a reference value of the first device parameter based on a historical value of the historical device parameter matching the first device parameter (Sun [0042] and [0128] discloses the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated with one or more historical scans of the target subject. In addition, the processing device may determine whether a historical scan protocol corresponding to the recommended value of the procedure parameter is the same as or similar to a current scan protocol of the target subject);
determining reference values of the one or more second device parameters based on the reference values of the one or more first device parameters (Sun [0088] discloses examples for when a scan parameter does not have a matching reference value. For example, if a historical scan region is the feet of the target subject, and an actual scan region is the head of the target subject, the processing device may determine a value of the procedure parameter (e.g., a tube voltage, a tube current) corresponding to the head by increasing a historical value of the procedure parameter corresponding to the feet, due to the head have more osseous tissue than the feet.) and an association model, wherein the association model is a machine learning model reflecting a correlation between [device parameters] ([0102], [0111], [0113] the plurality of simulation values of the imaging scan parameter may be determined using the dose simulation model, the candidate scan data corresponding to the candidate value of the imaging scan parameter. The dose simulation model may be generated based on deep learning. The dose simulation model refers to a model (e.g., a machine learning model) or an algorithm for determining a first image corresponding to a first value of the imaging scan parameter based on a second image corresponding to a second value of the imaging scan parameter.);
determining the target values of the one or more device parameters ([0041], [0089] The processing device may determine, based on the target prior information of the target subject, a value of a procedure parameter (e.g., a value of an imaging scan parameter, a value of an image reconstruction parameter) that relates to a procedure (e.g., a CT scan, an MRI scan, a PET scan) of the target subject using a medical device. In some embodiments, the processing device may obtain scan data of the target subject by causing the medical device to scan the target subject based on a value of the imaging scan parameter. The processing device may determine whether the candidate value (e.g., a historical value, a simulation value) of the procedure parameter of the target subject in the target prior information satisfies the scan condition. In response to determining that the candidate value of the procedure parameter satisfies the scan condition, the processing device may determine the candidate value of the procedure parameter as the value of the procedure parameter. In response to determining that the candidate value of the procedure parameter does not satisfy the scan condition, the processing device may adjust (by, e.g., increasing, decreasing) the candidate value of the procedure parameter. The processing device may determine the adjusted candidate value of the procedure parameter as the value of the procedure parameter.) based on the reference values of the one or more first device parameters ([0042] the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated with one or more historical scans of the target subject and/or simulation data (e.g., simulation scan data, a simulated image, a simulation value of the procedure parameter) of the target subject stored in the prior information database) and the reference values of the one or more second device parameters (Sun [0088] discloses examples for when a scan parameter does not have a matching reference value. For example, if a historical scan region is the feet of the target subject, and an actual scan region is the head of the target subject, the processing device may determine a value of the procedure parameter (e.g., a tube voltage, a tube current) corresponding to the head by increasing a historical value of the procedure parameter corresponding to the feet, due to the head have more osseous tissue than the feet.);
performing parameter configuration on the imaging device based on the target values of the one or more device parameters (Sun [0044] and [0047] discloses the medical device may be configured to acquire image data relating to a subject (e.g., a target subject) and that the processing device may cause a medical device to scan the target subject based on a value of an imaging scan parameter); and
controlling the imaging device, on which the parameter configuration has been completed, to perform a scan on the user to be examined to obtain scan data ([0070], [0071] The determination module may select a value of the imaging scan parameter from the plurality of target values of the imaging scan parameter. The control module may be configured to control one or more components (e.g., the medical device) of the medical system. For example, the control module may cause a medical device (e.g., the medical device) to scan a target subject based on a value of an imaging scan parameter.).
However, Sun does not explicitly teach the following that is met by Srinivasan:
wherein the association model is a machine learning model reflecting a correlation between the one or more first device parameters and the one or more second device parameters (Pg. 11, para. 3-5 and Pg. 9, para. 6: the processor can determine a desired output including imaging parameters such as saturation, contrast (global or local), sharpness, brightness, dynamic range, one or any combination of spatial filter, etc. The model uses as input imaging parameters such as a spatial gradient, boundary pixel, beam forming, radio frequency (RF), channel data, Doppler data, etc. The model may produce output including imaging parameter ranges such as dynamic range, spatial filter, edge enhancement, contrast enhancement, imaging frequency, linear density, etc. based on the input parameters. Therefore, the examiner interprets this model to produce an output of desired imaging parameters (i.e., second device parameters) based on input of different imaging parameters (i.e., first device parameters), showing a correlation between the first and second parameters. The model may include one or any combination of several of method, algorithm, process, formula, rule or the like, such as a feedforward neural network (FNN), recurrent neural network (RNN), Kohonen self-organizing maps, automatic coder, probabilistic neural network (PNN). Time delay neural network (TDNN), radial basis function network (RBF), learning vector quantization, a convolutional neural network (CNN), one or any combination of several of adaptive linear neuron (ADALINE) model, the associated neural network (ASNN) and so on. An exemplary recurrent neural network (RNN) may include Hopfield network, Boltzmann machine, echo state network, long term memory network, bidirectional recurrent neural network, hierarchical recurrent neural network, one kind or the combination of optional several kinds in random nerve network and the like.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to have combined the method for determining values of imaging parameters, as taught by Sun, with the model that reflects a correlation between first and second device parameters, as taught by Srinivasan, because the model allows the processor to process images in an improved way, and allows for an improved user experience (See Srinivasan Pg. 10, para. 2).
Regarding Claim 21, the combination of Sun and Srinivasan teaches the method of claim 1, and Sun further teaches:
The method of claim 1, wherein the association model is obtained by training an initial association model using a plurality of first training samples with labels, each first training sample comprises first sample values of the one or more first device parameters ([0102], [0104], [0111], [0113] the plurality of simulation values of the imaging scan parameter may be determined using the dose simulation model, the candidate scan data corresponding to the candidate value of the imaging scan parameter. The dose simulation model may be generated based on deep learning. The dose simulation model refers to a model (e.g., a machine learning model) or an algorithm for determining a first image corresponding to a first value of the imaging scan parameter based on a second image corresponding to a second value of the imaging scan parameter. To train the dose simulation model, a plurality of training samples may be used. Each training sample may include a sample value of the imaging scan parameter, a sample image corresponding to the sample value of the imaging scan parameter, a reference value of the imaging scan parameter, and a reference image (also referred to as a gold standard image) corresponding to the reference value of the imaging scan parameter. In some embodiments, the reference value of the imaging scan parameter may be different from the sample value of the imaging scan parameter. For example, the reference value of the imaging scan parameter may be lower than the sample value of the imaging scan parameter. In some embodiments, the sample image and the reference image may be historical images reconstructed based on historical scan data of a sample subject during a historical scan. The sample subject may be the same as or different from the target subject. In some embodiments, the sample image may be a historical image reconstructed based on the historical scan data of the sample during the historical scan. The reference image may be obtained based on the sample image, the sample value of the imaging scan parameter, and the reference value of the imaging scan parameter, using one or more existing low dose simulation algorithms.), and a training process of the association model comprises:
inputting the plurality of first training samples into the initial association model ([0106] For each of the plurality of iterations, a specific training sample may first be input into the preliminary model. For example, a sample value of the imaging scan parameter, a sample image corresponding to the sample value of the imaging scan parameter, and a reference value of the imaging scan parameter in the specific training sample may be inputted into an input layer of the preliminary model,);
calculating a value of a loss function based on the labels and an output result of the initial association model ([0106] The predicted output (i.e., the predicted image) may then be compared with the desired output (e.g., the reference image) based on a cost function. As used herein, a cost function of a machine learning model may be configured to assess a difference between a predicted output (e.g., the predicted image) of the machine learning model and a desired output (e.g., the reference image). If the value of the cost function exceeds a threshold in a current iteration, parameter values of the preliminary model may be adjusted and/or updated in order to decrease the value of the cost function (i.e., the difference between the predicted image and the reference image) to smaller than the threshold, and an intermediate model may be generated.);
iteratively updating parameters of the initial association model ([0106] the dose simulation model may be determined by performing a plurality of iterations to iteratively update one or more parameter values of the preliminary model.) based on the value of the loss function until a predetermined condition is satisfied ([0107] The termination condition may relate to the cost function or an iteration count of the iterative process or training process. For example, the termination condition may be satisfied if the value of the cost function associated with the preliminary model ( or the intermediate model) is minimal or smaller than a threshold (e.g., a constant)).
However, Sun does not explicitly disclose the following that is met by Srinivasan:
and the label corresponding to each first training sample comprises second sample values of the one or more second device parameters (Pg. 2, Abstract, Pg. 11, para. 3-5: building an initial model by determining an expected output based on the input and the desired output to obtain. The desired output may include one or any combination of several of the desired imaging parameter range (e.g., dynamic range, spatial filter, edge enhancement, contrast enhancement, imaging frequency, the linear density and so on). An input for the model includes imaging parameters such as a spatial gradient, boundary pixel, beam forming, radio frequency (RF), channel data, Doppler data, etc. Therefore, the first training sample labels comprise parameter ranges for second device parameters.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to have combined the method for training the association model, as taught by Sun, with the label corresponding to each first training sample comprising second sample values of the second device parameters, showing a correlation between first and second device parameters, as taught by Srinivasan, because the model allows the processor to process images in an improved way, and allows for an improved user experience (See Srinivasan Pg. 10, para. 2).
Claims 10, 14, 16, 22, and 24-29 are rejected under 35 U.S.C. 103 as being unpatentable over Sun (US 2022/0192619), in view of Srinivasan et al. (CN 109069100 A) (Hereinafter Srinivasan), in further view of Lyman et al. (US 2022/0005566) (Hereinafter Lyman).
Regarding Claim 10, the combination of Sun and Srinivasan teaches the method of claim 9, and Sun further discloses the following:
The method of claim 9, wherein:
the plurality of sets of reference values further include a second set of reference values, (Sun [0042] and [0128] discloses the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated with one or more historical scans of the target subject. In addition, the processing device may determine whether a historical scan protocol corresponding to the recommended value of the procedure parameter is the same as or similar to a current scan protocol of the target subject.), and the second set of reference values is determined based on a parameter prediction model, the parameter prediction model being a machine learning model (Sun [0102] discloses the dose simulation model refers to a model (e.g., a machine learning model) or an algorithm for determining a first image corresponding to a first value of the imaging scan parameter based on a second image corresponding to a second value of the imaging scan parameter);
However, Sun and Srinivasan does not disclose the following that is met by Lyman:
the recommendation degree of the first set of reference values is determined based on a count of the one or more first device parameters that have matched historical device parameters ([0083]-[0084] The similar scan data can include its own similar scan display parameter data, which can be determined based on some or all of the display parameter data of the identified similar medical scan. The similar scan display parameter data can be the same as the display parameter data mapped to the identified similar medical scan and/or can be the same as the display parameter data of the medical scan itself. A ranking of all identified similar scans is created, and the subset can be selected and/or some or all identified similar scans can be ranked based on each similarity score, and/or based on other factors such as based on a longitudinal quality score of each identified similar medical scan.)
the recommendation degree of the second set of reference values is determined based on a count of usage of the second set of reference values by target reference users in target devices ([0144] The ranking can be based on a longitudinal quality score, such as the longitudinal quality score, which can be calculated for an identified medical scan based on a number of subsequent and/or previous scans for the patient. a longitudinal threshold must be reached, and only scans that compare favorably to the longitudinal threshold will be selected. For example, only scans with at least three scans on file for the patient and final biopsy data will be included);
It would have been obvious to one of ordinary skill in the art before the effective filing date to have combined the system for configuring imaging parameters including having a recommendation degree for the reference sets, as taught by Sun and Srinivasan, with the recommendation based on count of matched parameters and count of usage, as taught by Lyman, because by having these set boundaries, the system can filter similar scans so that only scans with reliable data and scans that compare favorably to the criteria are selected (See Lyman [0144]).
Regarding Claim 14, Sun teaches the following:
A system for configuring imaging parameters (Sun [0002] and [0047] discloses a medical system for determining a value of a procedure parameter related to a procedure of a target subject and causing a medical device to scan a target subject based on a value of an imaging scan parameter), comprising:
at least one storage device storing a set of instructions ([0020] a system may include at least one storage device storing a set of instructions); and
at least one processor configured to communicate with the at least one storage device, wherein when executing the set of instructions, the at least one processor is configured to direct the system to perform operations (Sun [0020] discloses at least one processor in communication with the at least one storage device. When executing the stored set of instructions, the at least one processor may cause the system to perform a method) including:
obtaining a user identifier of a user to be examined (Sun [0041] and [0076] discloses a processing device that can obtain target prior information of the target subject based on the feature information of the target subject. The feature information of the target subject may include identity information) and one or more device parameters to be set of an imaging device (Sun [0041] discloses the processing device may determine, based on the target prior information of the target subject, a value of a procedure parameter (e.g., a value of an imaging scan parameter) that relates to a procedure (e.g., a CT scan, an MRI scan, a PET scan) of the target subject using a medical device));
determining target values of the one or more device parameters based on the user identifier (Sun [0041] discloses the processing device may determine, based on the target prior information of the target subject, a value of a procedure parameter), by:
obtaining user information relating to the user based on the user identifier (Sun [0076] discloses the feature information of the target subject may include identify information (e.g., an identification (ID) number, a name, the gender, the age, a date of birth, an occupation), contact information (e.g., a mobile phone number), medical information (e.g., a medical record number, a registration card number, a health condition, a medical history), shape information (e.g., a width, a thickness, a height, a weight) of the target subject or a portion thereof, or the like, or any combination thereof);
obtaining reference values of the one or more device parameters based on the user information (Sun [0018] discloses the target prior information may include a recommended value of the procedure parameter), wherein the reference values of the one or more device parameters include a plurality of sets of reference values (Sun [0041], [0129] The processing device may obtain target prior information of the target subject based on the feature information of the target subject and a prior information database. The prior information database may include prior information of a plurality of candidate subjects. The processing device may determine values of a plurality of imaging scan parameters (e.g., the tube voltage, the tube current, and the scan time)), the plurality of sets of reference values includes a first sets of reference values and a second set of reference values, the first set of reference values is determined based on historical values of one or more historical device parameters used in a reference historical scan (Sun [0042] and [0128] discloses the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated with one or more historical scans of the target subject. In addition, the processing device may determine whether a historical scan protocol corresponding to the recommended value of the procedure parameter is the same as or similar to a current scan protocol of the target subject.), and the second set of reference values is determined by processing the user information using a parameter prediction model, and the parameter prediction model is a machine learning model (Sun [0102], [0105], [0106] discloses the dose simulation model refers to a model (e.g., a machine learning model) or an algorithm for determining a first image corresponding to a first value of the imaging scan parameter based on a second image corresponding to a second value of the imaging scan parameter. The preliminary model may add simulation noises on the sample image based on the sample value of the imaging scan parameter and the reference value of the imaging scan parameter, to determine a predicted output (i.e., a predicted image corresponding to the reference value of the imaging scan parameter) of the specific training sample. If the value of the cost function exceeds a threshold in a current iteration, parameter values of the preliminary model may be adjusted and/or updated in order to decrease the value of the cost function (i.e., the difference between the predicted image and the reference image) to smaller than the threshold. the preliminary model may be of any type of machine learning model);
determining a recommendation degree of each set of the plurality of sets of reference values (Sun [0083] discloses that in some embodiments, a degree of similarity between the specific candidate subject and the target subject may reach or exceed a threshold (e.g., 80%, 85%, 90%, 95%))
determining the target values of the one or more device parameters based on the recommendation degree of each set of the plurality of sets of reference values ([0083] the processing device may select a candidate subject with the highest degree of similarity to the target subject among the plurality of candidate subjects, or a portion thereof (e.g., among the plurality of candidate subjects, those who share at least one similar feature with the target subject), in the prior information database. The processing device may further designate prior information of the selected candidate subject as the target prior information of the target subject);
performing parameter configuration on the imaging device based on the target values of the one or more device parameters (Sun [0044] and [0047] discloses the medical device may be configured to acquire image data relating to a subject (e.g., a target subject) and that the processing device may cause a medical device to scan the target subject based on a value of an imaging scan parameter), and
controlling the imaging device, on which the parameter configuration has been completed, to perform a scan on the user to be examined to obtain scan data ([0070], [0071] The determination module may select a value of the imaging scan parameter from the plurality of target values of the imaging scan parameter. The control module may be configured to control one or more components (e.g., the medical device) of the medical system. For example, the control module may cause a medical device (e.g., the medical device) to scan a target subject based on a value of an imaging scan parameter.).
However, Sun does not explicitly disclose the following that is met by Lyman:
wherein the recommendation degree of the first set of reference values is determined based on a count of device parameters that match the one or more historical device parameters among the one or more device parameters ([0083] The similar scan data can include its own similar scan display parameter data, which can be determined based on some or all of the display parameter data of the identified similar medical scan. The similar scan display parameter data can be the same as the display parameter data mapped to the identified similar medical scan and/or can be the same as the display parameter data of the medical scan itself. A ranking of all identified similar scans is created, and the subset can be selected and/or some or all identified similar scans can be ranked based on each similarity score, and/or based on other factors such as based on a longitudinal quality score of each identified similar medical scan.), and the recommendation degree of the second set of reference values is determined based on a count of usage of the second set of reference values by target reference users in target devices ([0144] The ranking can be based on a longitudinal quality score, such as the longitudinal quality score, which can be calculated for an identified medical scan based on a number of subsequent and/or previous scans for the patient. a longitudinal threshold must be reached, and only scans that compare favorably to the longitudinal threshold will be selected. For example, only scans with at least three scans on file for the patient and final biopsy data will be included);
It would have been obvious to one of ordinary skill in the art before the effective filing date to have combined the system for configuring imaging parameters including having a recommendation degree for the reference sets, as taught by Sun, with the recommendation based on count of matched parameters and count of usage, as taught by Lyman, because by having these set boundaries, the system can filter similar scans so that only scans with reliable data and scans that compare favorably to the criteria are selected (See Lyman [0144]).
Regarding Claim 16, the combination of Sun and Lyman teaches the system of claim 14, and further discloses the following:
The system of claim 14, wherein the first set of reference values is determined by:
determining the historical values of the one or more historical device parameters used in the reference historical scan based on the user information (Sun [0019] discloses the prior information database may be established based on at least one of feature information of a candidate subject, a historical scan protocol of the candidate subject, a historical value of an imaging scan parameter of the candidate subject, a historical value of an image reconstruction parameter of the candidate subject, historical scan data of the candidate subject, a historical image of the candidate subject, etc.); and
determining the first set of reference values of the one or more device parameters based on a matching relationship between the one or more historical device parameters and the one or more device parameters (Sun [0042] and [0128] discloses the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated with one or more historical scans of the target subject. In addition, the processing device may determine whether a historical scan protocol corresponding to the recommended value of the procedure parameter is the same as or similar to a current scan protocol of the target subject.).
Regarding Claim 22, the combination of Sun and Srinivasan teaches the method of claim 7, and Sun further teaches:
The method of claim 7, wherein selecting a target reference user from at least two reference users based on the user information (Sun [0104], [0050], and [0084] discloses that the sample image and the reference image may be historical images reconstructed based on historical scan data of a sample subject during a historical scan. The sample subject may be the same as or different from the target subject. The prior information can include information of a plurality of candidate subjects. The processing device may select a candidate subject with the highest degree of similarity to the target subject among the plurality of candidate subjects, or a portion thereof (e.g., among the plurality of candidate subjects, those who share at least one similar feature with the target subject), in the prior information database.) includes:
designating a reference user ([0083] the processing device may select a candidate subject with the highest degree of similarity to the target subject among the plurality of candidate subjects, or a portion thereof (e.g., among the plurality of candidate subjects, those who share at least one similar feature with the target subject), in the prior information database. Exemplary features may include age, gender, medical history, or the like, or any combination thereof)
However, the combination of Sun and Srinivasan does not explicitly disclose the following that is met by Lyman:
constructing a basic feature vector corresponding to the user to be examined based on the user information and device information relating to the imaging device ([0132] The feature vectors can include features as additional input features or desired output features, such as known abnormality data such as location and/or classification data, patient history data such as risk factor data or previous medical scans, diagnosis data, responsible medical entity data, scan machinery model or calibration data, contrast agent data, medical code data, annotation data that can include raw or processed natural language text data, scan type and/or anatomical region data, or other data associated with the image, such as some or all data of a medical scan entry. The input feature vector can include data that will be available in subsequent medical scan input, which can include for example, the three-dimensional sub region pixel data and/or patient history data.);
obtaining a target feature vector in a vector database based on the basic feature vector, wherein the vector database includes reference feature vectors of the at least two reference users ([0144] A medical scan similarity analysis function can be applied to the feature vector of the given medical scan and one or more feature vectors of medical scans in the set.), each reference feature vector includes feature values included in user information of the corresponding reference user and device information of a historical imaging device that has performed a historical scan on the corresponding reference user ([0144] The similar scans identification step can include performing a scan similarity algorithm, which can include generating a feature vector for the given medical scan and for medical scans in the set of medical scans, where the feature vector can be generated based on quantitative and/or category based visual features, inferred features, abnormality location and/or characteristics such as the predetermined size and/or volume, patient history and/or risk factor features, or other known or inferred features.); and
designating a reference [user] corresponding to the target feature vector as the target reference user ([0144] The medical scan similarity analysis function can include computing a similarity distance such as the Euclidian distance between the feature vectors, and assigning the similarity distance to the corresponding medical scan in the set. Similar medical scans can be identified based on determining one or more medical scans in the set with a smallest computed similarity distance, based on ranking medical scans in the set based on the computed similarity distances and identifying a designated number of top ranked medical scans, and/or based on determining if a similarity distance between the given medical scan and a medical scan in the set is smaller than a similarity threshold.).
It would have been obvious to one of ordinary skill in the art before the effective filing date to have combined the process of selecting a reference user, as taught by Sun, with the function of designating a reference user based on feature vectors, as taught by Lyman, because it allows the system to filter similar scans so that only historical scans with reliable data and scans that compare favorably to the criteria are selected (See Lyman [0144]).
Regarding Claim 23, the combination of Sun, Srinivasan, and Lyman teaches the system of claim 14, and Sun further teaches:
The system of claim 14, wherein the parameter prediction model is obtained by training an initial parameter prediction model using a plurality of second training samples with labels, each second training sample comprises sample user information of a sample user in a historical scan, and the label corresponding to each second training sample comprises parameter values of historical device parameters corresponding to the sample user information ([0104] To train the dose simulation model, a plurality of training samples may be used. Each training sample may include a sample value of the imaging scan parameter, a sample image corresponding to the sample value of the imaging scan parameter, a reference value of the imaging scan parameter, and a reference image (also referred to as a gold standard image) corresponding to the reference value of the imaging scan parameter. The sample image and the reference image may be historical images reconstructed based on historical scan data of a sample subject during a historical scan. The sample subject may be the same as or different from the target subject.), and a training process of the parameter prediction model comprises:
inputting the plurality of second training samples into the initial parameter prediction model ([0106] For each of the plurality of iterations, a specific training sample may first be input into the preliminary model. a sample value of the imaging scan parameter, a sample image corresponding to the sample value of the imaging scan parameter, and a reference value of the imaging scan parameter in the specific training sample may be inputted into an input layer of the preliminary model,);
calculating a value of a loss function based on the labels and an output result of the initial parameter prediction model ([0106] The predicted output (i.e., the predicted image) may then be compared with the desired output (e.g., the reference image) based on a cost function. As used herein, a cost function of a machine learning model may be configured to assess a difference between a predicted output (e.g., the predicted image) of the machine learning model and a desired output (e.g., the reference image). If the value of the cost function exceeds a threshold in a current iteration, parameter values of the preliminary model may be adjusted and/or updated in order to decrease the value of the cost function (i.e., the difference between the predicted image and the reference image) to smaller than the threshold, and an intermediate model may be generated);
iteratively updating parameters of the initial parameter prediction model based on the value of the loss function until a predetermined condition is satisfied ([0106] If the value of the cost function exceeds a threshold in a current iteration, parameter values of the preliminary model may be adjusted and/or updated in order to decrease the value of the cost function (i.e., the difference between the predicted image and the reference image) to smaller than the threshold, and an intermediate model may be generated.
Regarding Claim 24, the combination of Sun and Lyman teaches the system of claim 16, and Sun further teaches:
The system of claim 16, wherein the determining the first set of reference values of the one or more device parameters based on a matching relationship between the one or more historical device parameters and the one or more device parameters (Sun [0042] and [0128] discloses the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated with one or more historical scans of the target subject. In addition, the processing device may determine whether a historical scan protocol corresponding to the recommended value of the procedure parameter is the same as or similar to a current scan protocol of the target subject.) includes:
determining one or more first device parameters and one or more second device parameters from the one or more device parameters, wherein each first device parameter has a matched historical device parameter among the one or more historical device parameters (Sun [0042], [0089], and [0128] discloses the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated with one or more historical scans of the target subject. In addition, the processing device may determine whether a historical scan protocol corresponding to the recommended value of the procedure parameter is the same as or similar to a current scan protocol of the target subject. In response to determining that the candidate value of the procedure parameter satisfies the scan condition, the processing device may determine the candidate value of the procedure parameter as the value of the procedure parameter), and each second device parameter has no matched historical device parameter among the one or more historical device parameters (Sun [0088] discloses that a scan condition of the target subject may be different form a historical scan condition of the target subject in the target prior information);
for each first device parameter, determining a reference value of the first device parameter based on a historical value of the historical device parameter matching the first device parameter (Sun [0042] and [0128] discloses the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated with one or more historical scans of the target subject. In addition, the processing device may determine whether a historical scan protocol corresponding to the recommended value of the procedure parameter is the same as or similar to a current scan protocol of the target subject); and
determining reference values of the one or more second device parameters based on the reference values of the one or more first device parameters (Sun [0088] discloses examples for when a scan parameter does not have a matching reference value. For example, if a historical scan region is the feet of the target subject, and an actual scan region is the head of the target subject, the processing device may determine a value of the procedure parameter (e.g., a tube voltage, a tube current) corresponding to the head by increasing a historical value of the procedure parameter corresponding to the feet, due to the head have more osseous tissue than the feet.), wherein the first set of reference values includes the reference value of each first device parameter ([0042] the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated with one or more historical scans of the target subject and/or simulation data (e.g., simulation scan data, a simulated image, a simulation value of the procedure parameter) of the target subject stored in the prior information database) and the reference value of each second devices (Sun [0088], [0129], Fig. 6 discloses examples for when a scan parameter does not have a matching reference value. For example, if a historical scan region is the feet of the target subject, and an actual scan region is the head of the target subject, the processing device may determine a value of the procedure parameter (e.g., a tube voltage, a tube current) corresponding to the head by increasing a historical value of the procedure parameter corresponding to the feet, due to the head have more osseous tissue than the feet. In response to determining that the prior information database does not include a recommended radiation dose of the target subject, the processing device may determine the value of the procedure parameter of the target subject based on candidate values through process 600.)
Regarding Claim 25, the combination of Sun and Lyman teaches the system of claim 24, and Sun further teaches:
The system of claim 24, wherein the reference values of the one or more second device parameters are determined based on the reference values of the one or more first device parameters (Sun [0088] discloses examples for when a scan parameter does not have a matching reference value. For example, if a historical scan region is the feet of the target subject, and an actual scan region is the head of the target subject, the processing device may determine a value of the procedure parameter (e.g., a tube voltage, a tube current) corresponding to the head by increasing a historical value of the procedure parameter corresponding to the feet, due to the head have more osseous tissue than the feet.) using an association model, the association model being a machine learning model reflecting a correlation between [device parameters] ([0102], [0111], [0113] the plurality of simulation values of the imaging scan parameter may be determined using the dose simulation model, the candidate scan data corresponding to the candidate value of the imaging scan parameter. The dose simulation model may be generated based on deep learning. The dose simulation model refers to a model (e.g., a machine learning model) or an algorithm for determining a first image corresponding to a first value of the imaging scan parameter based on a second image corresponding to a second value of the imaging scan parameter.).
However, Sun does not explicitly teach the following that is met by Srinivasan:
the association model being a machine learning model reflecting a correlation between the one or more first device parameters and the one or more second device parameters (Pg. 11, para. 3-5 and Pg. 9, para. 6: the processor can determine a desired output including imaging parameters such as saturation, contrast (global or local), sharpness, brightness, dynamic range, one or any combination of spatial filter, etc. The model uses as input imaging parameters such as a spatial gradient, boundary pixel, beam forming, radio frequency (RF), channel data, Doppler data, etc. The model may produce output including imaging parameter ranges such as dynamic range, spatial filter, edge enhancement, contrast enhancement, imaging frequency, linear density, etc. based on the input parameters. Therefore, the examiner interprets this model to produce an output of desired imaging parameters (i.e., second device parameters) based on input of different imaging parameters (i.e., first device parameters), showing a correlation between the first and second parameters. The model may include one or any combination of several of method, algorithm, process, formula, rule or the like, such as a feedforward neural network (FNN), recurrent neural network (RNN), Kohonen self-organizing maps, automatic coder, probabilistic neural network (PNN). Time delay neural network (TDNN), radial basis function network (RBF), learning vector quantization, a convolutional neural network (CNN), one or any combination of several of adaptive linear neuron (ADALINE) model, the associated neural network (ASNN) and so on. An exemplary recurrent neural network (RNN) may include Hopfield network, Boltzmann machine, echo state network, long term memory network, bidirectional recurrent neural network, hierarchical recurrent neural network, one kind or the combination of optional several kinds in random nerve network and the like.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to have combined the method for determining values of imaging parameters, as taught by Sun, with the model that reflects a correlation between first and second device parameters, as taught by Srinivasan, because the model allows the processor to process images in an improved way, and allows for an improved user experience (See Srinivasan Pg. 10, para. 2).
Regarding Claim 26, the combination of Sun and Lyman teaches the system of claim 14, and Lyman further teaches:
The system of claim 14, wherein the target reference users are determined by:
designating reference users ([0083] the processing device may select a candidate subject with the highest degree of similarity to the target subject among the plurality of candidate subjects, or a portion thereof (e.g., among the plurality of candidate subjects, those who share at least one similar feature with the target subject), in the prior information database. Exemplary features may include age, gender, medical history, or the like, or any combination thereof)
However, the combination of Sun and Srinivasan does not explicitly disclose the following that is met by Lyman:
constructing a basic feature vector corresponding to the user to be examined based on the user information and device information relating to the imaging device that is to perform a scan on the user to be examined ([0132] The feature vectors can include features as additional input features or desired output features, such as known abnormality data such as location and/or classification data, patient history data such as risk factor data or previous medical scans, diagnosis data, responsible medical entity data, scan machinery model or calibration data, contrast agent data, medical code data, annotation data that can include raw or processed natural language text data, scan type and/or anatomical region data, or other data associated with the image, such as some or all data of a medical scan entry. The input feature vector can include data that will be available in subsequent medical scan input, which can include for example, the three-dimensional sub region pixel data and/or patient history data.);
obtaining target feature vectors in a vector database based on the basic feature vector ([0144] A medical scan similarity analysis function can be applied to the feature vector of the given medical scan and one or more feature vectors of medical scans in the set.), wherein the vector database includes reference feature vectors of reference users, each reference feature vector includes feature values included in user information of the corresponding reference user and device information of a historical imaging device that has performed a historical scan on the corresponding reference user ([0144] The similar scans identification step can include performing a scan similarity algorithm, which can include generating a feature vector for the given medical scan and for medical scans in the set of medical scans, where the feature vector can be generated based on quantitative and/or category based visual features, inferred features, abnormality location and/or characteristics such as the predetermined size and/or volume, patient history and/or risk factor features, or other known or inferred features.); and
designating reference [users] ([0083] the processing device may select a candidate subject with the highest degree of similarity to the target subject among the plurality of candidate subjects, or a portion thereof (e.g., among the plurality of candidate subjects, those who share at least one similar feature with the target subject), in the prior information database. Exemplary features may include age, gender, medical history, or the like, or any combination thereof) corresponding to the target feature vectors as the target reference users ([0144] The medical scan similarity analysis function can include computing a similarity distance such as the Euclidian distance between the feature vectors, and assigning the similarity distance to the corresponding medical scan in the set. Similar medical scans can be identified based on determining one or more medical scans in the set with a smallest computed similarity distance, based on ranking medical scans in the set based on the computed similarity distances and identifying a designated number of top ranked medical scans, and/or based on determining if a similarity distance between the given medical scan and a medical scan in the set is smaller than a similarity threshold.).
It would have been obvious to one of ordinary skill in the art before the effective filing date to have combined the process of selecting a reference user, as taught by Sun, with the function of designating a reference user based on feature vectors, as taught by Lyman, because it allows the system to filter similar scans so that only historical scans with reliable data and scans that compare favorably to the criteria are selected (See Lyman [0144]).
Regarding Claim 28, the combination of Sun and Lyman teaches the system of claim 14, and Sun further teaches:
The system of claim 14, wherein the operations further include:
selecting a target reference user from at least two reference users based on the user information, wherein each of the at least two reference users has received a historical scan performed by a historical imaging device (Sun [0104], [0050], and [0084] discloses that the sample image and the reference image may be historical images reconstructed based on historical scan data of a sample subject during a historical scan. The sample subject may be the same as or different from the target subject. The prior information can include information of a plurality of candidate subjects. The processing device may select a candidate subject with the highest degree of similarity to the target subject among the plurality of candidate subjects, or a portion thereof (e.g., among the plurality of candidate subjects, those who share at least one similar feature with the target subject), in the prior information database.); and
determining the historical scan of the target reference user as the reference historical scan (Sun [0104] discloses the reference image may be obtained based on the sample image, the sample value of the imaging scan parameter, and the reference value of the imaging scan parameter).
Regarding Claim 29, the combination of Sun and Lyman teaches the system of claim 14, and Sun further teaches:
The system of claim 14, wherein operations further include:
obtaining, based on the user information, a historical scan of the user performed by a reference imaging device ([0019] the prior information database may be established based on at least one of feature information of a candidate subject, a historical scan protocol of the candidate subject); and
determining the historical scan of the user as the reference historical scan (Sun [0042] discloses the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated).
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Sun (US 2022/0192619), in view Srinivasan et al. (CN 109069100 A) (Hereinafter Srinivasan), in further view of Lyman et al. (US 2022/0005566) (Hereinafter Lyman), in further view of Amthor et al. (CN 112292732 A) (Hereinafter Amthor).
Regarding Claim 11, Sun teaches the method of claim 1, and further discloses the following:
The method of claim 1, wherein the determining the target values of the one or more device parameters ([0018] The method may include, in response to determining that the recommended value of the procedure parameter satisfies the scan condition, determining the value of the procedure parameter based on the recommended value of the procedure parameter) includes:
determining a plurality of sets of reference values based on the user information (Sun [0041], [0129] The processing device may obtain target prior information of the target subject based on the feature information of the target subject and a prior information database. The prior information database may include prior information of a plurality of candidate subjects. The processing device may determine values of a plurality of imaging scan parameters (e.g., the tube voltage, the tube current, and the scan time)), wherein the plurality of sets of reference values include a first set of reference values, the first set of reference values includes the reference value of each first device parameter ([0042] the value of the procedure parameter (e.g., the value of the imaging scan parameter, the value of the image reconstruction parameter) of the target subject may be determined based on historical data (e.g., historical scan data, a historical image, a historical value of the procedure parameter) associated with one or more historical scans of the target subject and/or simulation data (e.g., simulation scan data, a simulated image, a simulation value of the procedure parameter) of the target subject stored in the prior information database) and the reference value of each second device parameter (Sun [0088], [0129], Fig. 6 discloses examples for when a scan parameter does not have a matching reference value. For example, if a historical scan region is the feet of the target subject, and an actual scan region is the head of the target subject, the processing device may determine a value of the procedure parameter (e.g., a tube voltage, a tube current) corresponding to the head by increasing a historical value of the procedure parameter corresponding to the feet, due to the head have more osseous tissue than the feet. In response to determining that the prior information database does not include a recommended radiation dose of the target subject, the processing device may determine the value of the procedure parameter of the target subject based on candidate values through process 600.);
sending the plurality of sets of reference values to a user terminal (Sun [0046] discloses the medical device may transmit the image data via the network to the processing device, the storage device, and/or the terminal device); and
However, Sun and Lyman do not teach the following that is met by Amthor:
determining one set of the plurality of sets of reference values as the target values based on a selection instruction received from the user terminal (Amthor Pg. 4, par. 4 and Pg. 10, par. 4 discloses a technical system or a user interface may be used to present the suggested imaging protocol or protocols to the operator. The feedback system may be configured to collect information (e.g. image quality) about the reason for the operator's selection. The operator is also required to accept a proposed protocol or reject it on a console screen.).
It would have been obvious to one of ordinary skill in the art before the effective filing date to have combined the method of determining reference values and sending the reference values to a user terminal, as taught by Sun, with the selection step as taught by Amthor because it will increase the accuracy of the models used in the system (See Amthor Pg. 4, par. 4).
Claim 27 is rejected under 35 U.S.C. 103 as being unpatentable over Sun (US 2022/0192619), in view Srinivasan et al. (CN 109069100 A) (Hereinafter Srinivasan), in further view of Lyman et al. (US 2022/0005566) (Hereinafter Lyman), in further view of Amthor et al. (CN 112292732 A) (Hereinafter Amthor), in further view of Gu et al. (CN 109659010 A) (Hereinafter Gu).
Regarding Claim 27, the combination of Sun and Lyman teaches the system of claim 14, and Sun further teaches:
The system of claim 14, wherein the first set of reference values is determined by adjusting the historical values of the one or more historical device parameters based on a performance index of the imaging device ([0089], [0096], [0110] after the scan is performed on the target subject, the feature information of the target subject, the scan data of the target subject, the value of the procedure parameter of the target subject may be stored in the prior information database to update the prior information database. The processing device may determine whether the candidate value (e.g., a historical value, a simulation value) of the procedure parameter of the target subject in the target prior information satisfies the scan condition. The processing device may determine at least one of the plurality of simulation values of the imaging scan parameter based on the initial image and the initial value of the imaging scan parameter, and may determine whether the quality of the initial image satisfies an image quality evaluation requirement. For example, the processing device may determine whether the quality (e.g., a density resolution, a spatial resolution, a signal-to-noise ratio) of the initial image is higher than a quality threshold (e.g., a density resolution threshold, a spatial resolution threshold, a signal-to-noise ratio threshold). In response to determining that the quality of the initial image does not satisfy the image quality evaluation requirement, the processing device may adjust (e.g., increase) the initial value of the imaging scan parameter, and determine the adjusted initial value of the imaging scan parameter as the simulation value of the imaging scan parameter. The examiner interprets the quality threshold and whether the quality of the processing device meets a certain expectation to be a performance index of the imaging device.)
However, Sun, Srinivasan, Lyman, and Amthor does not explicitly disclose the following that is met by Gu:
adjusting the values of the one or more historical device parameters based on a performance index of a historical imaging device corresponding to the reference historical scan (Pg. 3, para. 9, Pg. 9, para. 4, Pg. 12, para. 5: the second characteristic adjustment history record according to the protocol, the first characteristic value and the second characteristic value, so as to make the first characteristic adjusted value satisfies the corresponding target index, and the adjusted value for the protocol adjusting the closest value in the history record corresponding to the target index.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to have combined the system including adjusting historical values, as taught by Sun and Lyman, with the adjusting values based on a performance index of a historical device, as taught by Gu, because it can effectively improve adjusting efficiency and provide high adjusting accuracy (See Gu Abstract).
Response to Arguments
Applicant's arguments filed 01/29/2026 have been fully considered but they are not persuasive. Regarding the previous rejection under 35 U.S.C. 101, applicant argues the claimed invention is not directed to an abstract idea of a mental process nor certain methods of organizing human activity. Examiner respectfully disagrees. The process of obtaining a user identifier and device parameters, determining target values by obtaining user information, determining historical values used in a reference, determining device parameters that have a matched history and no matched history, determining a reference value based on a historical value matching the first device, determining reference values of the second device parameters based on the reference values of the first device parameters, determining target values based on the reference values is all able to be practically performed in the human mind, with or without the use of a physical aid. These functions are all performed using observation, evaluation, judgement, and opinion. Additionally, Applicant argues that including the step of controlling the physically-configured imaging device to perform a scan on a user and obtain scan data is inherently tied to and must be executed by specific medical imaging hardware, and therefore cannot be performed in the human mind or through purely mental processes. The examiner agrees this step is not a mental process, however, the step for controlling the imaging device is directed to methods of organizing human activity because it is recited at a high level as just controlling the imaging device. The “to perform a scan…” is merely the intended use and this is something performed by humans when interacting with users. The claim incorporates an association model, however, the use of the models to carry out the abstract idea amounts to using a mathematical algorithm to apply the abstract idea, which amounts to mere instructions to apply the exception, as per MPEP 2106.05(f)(2). Applicant argues the claimed invention advances beyond a mere abstract idea by integrating its recited elements into a concrete, real-world application within medical imaging. However, the examiner respectfully disagrees. The use of the trained machine learning models is recited at a high level of generality, and the use of the models to carry out the abstract idea amounts to using a mathematical algorithm to apply the abstract idea, which amounts to mere instructions to apply the exception, as per MPEP 2106.05(f)(2). Therefore, the use of machine learning models does not integrate the abstract idea into a practical application. Regarding Step 2B, applicant argues the claimed invention provides significantly more than the judicial exception, however, the examiner disagrees. As previously stated, the use of the machine learning models in the independent claims amounts to mere instructions to apply the exception using known mathematical algorithms (see Applicant’s specification [0121] and [0138]), and therefore does not provide significantly more than the judicial exception. Furthermore, the applicant argues “the claimed system divides multiple device parameters into the first device parameter with matched historical device parameters and the second device parameter without matched historical device parameters. For a first device parameter, the reference value of the first device parameter is determined directly based on the matched historical device parameter. For a second device parameter, the trained machine learning model is innovatively used to infer the reference value of the second device parameter based on the reference value of the first device parameter” provides an improvement to the technology, however, these limitations amount to steps that can be performed in the human mind. A person can practically determine first and second device parameters, whether or not they match a historical device parameter, and can use the reference values to infer a reference value of a second parameter based on the first. The use of a machine learning model to perform the inference is merely use of the models to carry out the abstract idea amounts to using a mathematical algorithm to apply the abstract idea, and therefore, does not provide significantly more.
Applicant argues that the previous Office Action fails to provide evidence to show why the claims are “well-understood, routine, and conventional”, however, the examiner respectfully disagrees. Referring to the Step 2B analysis, examiner provides citations from the Applicant’s specification to show the additional elements in the claims are well-understood, routine, and conventional. The applicant states the machine learning model for the association model and the parameter prediction model may include a neural network (NN) model, a convolutional neural network (CNN) model, a recurrent neural network (RNN) model, etc. (see Applicant’s specification [0121] and [0138]), which are known algorithms. Furthermore, the processing device may be a single server or group of servers and may be implemented on a cloud platform or provided virtually (see Specification par. 27-28). The unimodal medical imaging device may be an ultrasound (US) scanner, an X-ray scanner, a computed tomography (CT) scanner, a magnetic resonance imaging (MRI) scanner, a positron emission computed tomography (PET) scanner), an optical coherence tomography (OCT) scanner, an intravenous ultrasound (IVUS) scanner, a near infrared spectroscopy (NIS) scanner, a far infrared (FIR) scanner, etc., or any combination thereof. The multimodal medical imaging device may include an X-ray-magnetic resonance imaging (X-ray-MRI) scanner, a positron emission computed tomography-X- ray (PET-X-ray) scanner, a single photon emission computed tomography-magnetic resonance imaging (SPECT-MRI) scanner, a positron emission tomography-computed tomography (PET-CT) scanner, a digital subtraction angiography-magnetic resonance imaging (DSA-MRI) scanner, etc. (See specification par. 28). Therefore, the Office Action does point to why the claims are “well-understood, routine, and conventional”. Thus, the rejection under 35 U.S.C. 101 is maintained.
Applicant’s arguments, with respect to the rejection of claims 1, 7-9, 12, and 20 under 35 U.S.C. 102(a)(2) have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of the previously cited reference Srinivasan. Applicant argues that Sun does not teach the association model that reflects a correlation between first device parameters and second device parameters, the examiner agrees. Referring to the dose simulation model described in Sun, the dose simulation model refers to a model (e.g., a machine learning model) or an algorithm for determining a first image corresponding to a first value of the imaging scan parameter based on a second image corresponding to a second value of the imaging scan parameter (See Sun [0102]). The examiner agrees that this does not explicitly teach a correlation between first device parameters and second device parameters, however, in view of Srinivasan, a correlation between first device parameters, such as a spatial gradient, boundary pixel, beam forming, radio frequency (RF), channel data, Doppler data, etc., and second device parameters, such as saturation, contrast (global or local), sharpness, brightness, dynamic range, one or any combination of spatial filter, etc., is present through a machine learning model (See Srinivasan Pg. 11, para. 3-5).
Applicant’s arguments, see Remarks Pg. 25-27, filed 01/29/2026, with respect to the rejection of claims 14 and 16 under 35 U.S.C. 102(a)(2) and with respect to the rejection of claim 10 under 35 U.S.C. 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Srinivasan et al., in further view of Lyman et al. Arguments with respect to claims 11 and 13 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Conclusion
The relevant art made of record and not relied upon is considered pertinent to applicant’s disclosure.
Salisbury et al. (US 2011/0314401) discloses a user-profile system and method that allows the users of imaging devices to create, store and retrieve user profiles that allow users to readily set operating parameters of the imaging devices.
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALEXIS K VAN DUZER whose telephone number is (571)270-5832. The examiner can normally be reached Monday thru Thursday 8-5 CT.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Fonya Long can be reached at (571) 270-5096. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/A.K.V./Examiner, Art Unit 3682
/EVANGELINE BARR/Primary Examiner, Art Unit 3682
Prosecution Insights