DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
Claims 1-19 are pending in this application. Claims 10-13 are withdrawn, claims 17-19 are newly added, and Claims 1-9 and 14-19 have been examined on the merits.
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 1-9 and 14-16 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claim 1 recites first ultrasound image data based on a reception signal received by an ultrasound probe.
The limitation of reception signal received by an ultrasound probe, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind i.e., receiving or viewing an ultrasound image. Further, (although it is not required) if these processes are performed by an “inherent” processor, these claimed steps could easily be performed by a generic computer component as the claimed limitations do not require any specialized processor. If a Claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind, then it falls within the “Mental Processes” grouping of abstract ideas. Similarly, a machine learning model trained by using training data, is a process that, under its broadest reasonable interpretation, covers performance of a mental process (i.e. abstract idea) using a generic model that has no specifics to the algorithmic foundation or dimensionality associated with the model used and as such can be considered a vector of minimal dimensions that can be “used” by mental process or a simple pen and paper computations. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites one additional element — using one or more generic processors for execution. The processors are recited at a high-level of generality (i.e., an ultrasound probe) such that it amounts no more than mere instructions to apply the exception using processors. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using processors to perform the identifying and determining steps amounts to no more than mere instructions to apply the exception using generic processors. Mere instructions to apply an exception using generic processors cannot provide an inventive concept. The claim is not patent eligible. The other independent claim 16 also recites similar limitations as claim 8, which is also found to be not patent eligible at least for the reasons noted above.
The dependent claims 2-9, 14 and 15 are also directed to an abstract idea as the depending claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. In particular, claim 14 recites the additional element “an ultrasound probe” which does not result in significantly more than the abstract idea because a generic ultrasound probe is routine, well-understood, and conventional for obtaining ultrasound image data. The elements in those claims do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea. Therefore, the depending claims, are, also not patent eligible.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 2, 4, 6-9, and 14-16 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Masuda (US20230316513A1).
Regarding Claim 1,
Masuda teaches a machine learning model trained by using training data (corresponding disclosure in at least [0051], where the methods are completed using machine learning “the region may be specified using a learned model of the regions of the left atrium or the left ventricle constructed on the basis of training data prepared in advance using a machine learning technique”) that comprises: first ultrasound image data based on a reception signal received by an ultrasound probe (corresponding disclosure in at least [0101], where the image can come from an ultrasound image “the input image may be a 3D ultrasound image (for example, transcutaneous ultrasound, transesophageal ultrasound, or the like), or may be MRI, PET, SPECT, or the like”);
first ground truth data that is first region information associated with a detection target of the first ultrasound image data (corresponding disclosure in at least [0055], where the detection target (the four chambers) are acquired based on the first region (the heart) and the data acquired is ground truth data (the data is taken from the segmented CT image, which is referred to as the ground truth) “the region acquisition function 353 first performs a segmentation process of four chambers of the heart (left ventricle: LV, right ventricle: RV, left atrium: LA, and right atrium: RA)”)
and second ground truth data that is first position information relative to the detection target of the first ultrasound image data or that is second region information based on the first position information (corresponding disclosure in at least [0055], where the first position (the mitral valve based on the feature points) is acquired “region acquisition function 353 performs a precise feature point detection process of detecting coarse feature points around the mitral valve and then detecting the location of Trigone. Thereafter, the region acquisition function 353 specifies the partial region including the mitral valve on the basis of the detected location of the Trigone”).
Regarding Claim 2,
Matsuda teaches wherein the second ground truth data is the second region information (corresponding disclosure in at least [0055], where the second region (the mitral valve) is taught “region acquisition function 353 performs a precise feature point detection process of detecting coarse feature points around the mitral valve and then detecting the location of Trigone. Thereafter, the region acquisition function 353 specifies the partial region including the mitral valve on the basis of the detected location of the Trigone”).
Regarding Claim 4,
Matsuda teaches wherein the first region information and the second region information are image data (corresponding disclosure in at least [0055], where it’s specified the data are image data “Thereafter, the region acquisition function 353 specifies the partial region including the mitral valve on the basis of the detected location of the Trigone, and acquires a VOI image”).
Regarding Claim 6,
Matsuda teaches wherein the training data further includes third ground truth data that is second position information associated with the detection target of the first ultrasound image data or that is third region information based on the second position information (corresponding disclosure in at least [0091], where there is a second position information (the second partial region) that is acquired based on the first partial region (first image data) “wherein the training data further includes third ground truth data that is second position information associated with the detection target of the first ultrasound image data or that is third region information based on the second position information”).
Regarding Claim 7,
Matsuda teaches wherein the machine learning model is composed of a convolutional neural network (corresponding disclosure in at least [0066], where the model uses convolutional neural network (CNN) “a case where the existence probability calculation process is performed using a U-net, which is a type of convolutional neural network (CNN)”).
Regarding Claim 8,
Matsuda teaches a non-transitory computer-readable storage medium storing a program for causing a computer to, by using the machine learning model according to claim 1 (corresponding disclosure in at least [0016], where a medium used for storing methods is implemented “a medical image processing method, and a non-transitory computer readable medium”)
implement an output function of outputting an inference result associated with the detection target from second ultrasound image data based on the reception signal received by the ultrasound probe (corresponding disclosure in at least [0035], where the ML model (learning function) uses an input image and outputs information based on the probability (inference result) “the learning function 356 constructs the learned model that uses, as input, the input image including the region of interest of the subject and outputs the information on the existence probability of the region of interest”).
Regarding Claim 9,
Matsuda teaches an ultrasound diagnostic apparatus, comprising: an ultrasound probe that transmits and receives an ultrasonic wave to and from a subject (corresponding disclosure in at least [0019] and Figure 1, where the medical image diagnostic apparatus that is used includes an ultrasound diagnostic apparatus, which inherently uses a probe to transmit and receive ultrasonic waves, as an ultrasound image is formed “Examples of the medical image diagnostic apparatus 1 include an X-ray computed tomography (CT) apparatus, a magnetic resonance imaging (MRI) apparatus, an X-ray diagnostic apparatus, an ultrasonic diagnostic apparatus”).
PNG
media_image1.png
283
523
media_image1.png
Greyscale
Figure 1 of Matsuda
an inference section that, by using the machine learning model (corresponding disclosure in at least [0062], where machine learning is used for the steps “the method based on the machine learning”) according to claim 1, outputs an inference result associated with the detection target from second ultrasound image data based on the reception signal received by the ultrasound probe (corresponding disclosure in at least [0035], where a learning function is used (inference result) by receiving an input (detection target) based on the image (ultrasound image) to output an inference result (information of the region of interest) “the method based on the machine learning”).
Regarding Claim 14,
Matsuda teaches An ultrasound diagnostic system, comprising: an ultrasound probe that transmits and receives an ultrasonic wave to and from a subject (corresponding disclosure in at least [0019] and Figure 1, where the medical image diagnostic apparatus that is used includes an ultrasound diagnostic apparatus, which uses a probe to transmit and receive ultrasonic waves, as an ultrasound image is formed “ Examples of the medical image diagnostic apparatus 1 include an X-ray computed tomography (CT) apparatus, a magnetic resonance imaging (MRI) apparatus, an X-ray diagnostic apparatus, an ultrasonic diagnostic apparatus”);
and an output that, by using the machine learning model according to claim 1, outputs an inference result associated with the detection target from second ultrasound image data based on the reception signal received by the ultrasound probe (corresponding disclosure in at least [0052], where the output based on the ultrasound image data is outputted “a process can be performed on the input image to detect the location of a trigona fibrosa (Trigone), which is a type of anatomical region between the left atrium and the aorta, and to specify the partial region where the mitral valve exists, on the basis of the detected location”).
Regarding Claim 15,
Matsuda teaches an image diagnostic apparatus ([0019] and Figure 1), comprising: an inference section that, by using the machine learning model according to claim 1,
outputs an inference result associated with the detection target from second ultrasound image data based on the reception signal received by the ultrasound probe (corresponding disclosure in at least [0052], where the output based on the ultrasound image data is outputted “a process can be performed on the input image to detect the location of a trigona fibrosa (Trigone), which is a type of anatomical region between the left atrium and the aorta, and to specify the partial region where the mitral valve exists, on the basis of the detected location”).
Regarding Claim 16,
Matsuda teaches a training apparatus that performs machine learning by using training data (corresponding disclosure in at least [0063], where machine learning with training data is used “generates a learned model by machine-learning a plurality of sets of data (training data)”) that comprises:
first ultrasound image data based on a reception signal received by an ultrasound probe (corresponding disclosure in at least [0019] and Figure 1, where the medical image diagnostic apparatus that is used includes an ultrasound diagnostic apparatus, which uses a probe to transmit and receive ultrasonic waves, as an ultrasound image is formed “ Examples of the medical image diagnostic apparatus 1 include an X-ray computed tomography (CT) apparatus, a magnetic resonance imaging (MRI) apparatus, an X-ray diagnostic apparatus, an ultrasonic diagnostic apparatus”);
first ground truth data that is first region information associated with a detection target of the first ultrasound image data (corresponding disclosure in at least [0055], where the detection target (the four chambers) are acquired based on the first region (the heart) “the region acquisition function 353 first performs a segmentation process of four chambers of the heart (left ventricle: LV, right ventricle: RV, left atrium: LA, and right atrium: RA)”); and
second ground truth data that is first position information associated with the detection target of the first ultrasound image data or that is second region information based on the first position information (corresponding disclosure in at least [0055], where the first position (the mitral valve based on the feature points).
Regarding Claim 17,
Masuda further teaches the first region information of the first ground truth is a left ventricular region defined by a left ventricular endocardium boundary (corresponding disclosure in at least [0109], where the location of the left ventricular region (the left ventricle) “the existence probability calculation function 354 calculates information on the existence probability of the region of interest also on the basis of structural information of the region of interest. For example, the existence probabilities of the locations or the like of the left ventricle, the left atrium, and the aortic valve close to the mitral valve may also be calculated” and further in [0050], where the boundary of the left ventricle is shown (the region is displayed and known “ since the mitral valve is a structure located between a left atrium and a left ventricle, regions of the left atrium and the left ventricle of the heart of the subject can be acquired from the input image by a segmentation process using known techniques”) and the first position information of the second ground truth is a position of one of a right annulus and a left annulus (corresponding disclosure in at least [0058], where the position of the right and left annulus are also determined (corresponding disclosure in at least [0058], where the right and left annulus are also determined (the entire annulus, which would encompass the left and right annulus “the region acquisition function 353 estimates the annulus of the mitral valve on the basis of the location of the anatomical features around the mitral valve in the input image, and crops the VOI image from the input image so that the centroid of the annulus is located at the center in the VOI image of 64×64×64 pixels and includes the entire annulus”).
Claim Rejections - 35 USC § 103
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 3 and 5 are rejected under 35 U.S.C. 103 as being unpatentable over Masuda (US20230316513A1) in view of Tahara (US20240005600A1).
Regarding Claim 3, Masuda teaches all of the limitations of Claim 2 and the second region information ([0055]) being information including a distance, the distance being a distance form the first position coordinates associated with the detection target (corresponding disclosure in at least [0099], where the location of the detection target (the mitral valve) is determined, and from that, the first position coordinates (the Trigone); the feature points of the detection target are determined, which are then used to get the location of the first position coordinates based on the set distance between the two anatomical features “the region acquisition function 353 performs a precise feature point detection process of detecting coarse feature points around the mitral valve and then detecting the location of Trigone… the region acquisition function 353 specifies the partial region including the mitral valve on the basis of the detected location of the Trigone”).
Masuda does not teach the certainty factor.
Tahara, in a similar field of endeavor, teaches a similar concept (distance between known anatomical features), of the certainty factor (corresponding disclosure in at least [0139], where a certainty factor is calculated based on the accuracy of the estimation “The color or size of the heat map can be changed according to a certainty factor of an estimation result”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to have incorporated the certainty factor as taught by Tahara into the system of Masuda. One of the ordinary skill in the art would have been motivated to incorporate this because the feature is used to provide feedback in whether the predicted results are accurate in a numerical measure.
Regarding Claim 5, the combined references of Masuda and Tahara teach the limitations of Claim 3, and wherein the second region information is first heat map information (corresponding disclosure in at least [0139] of Tahara, where a heat map based on the certainty factor is taught “The color or size of the heat map can be changed according to a certainty factor of an estimation result”).
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Masuda (US20230316513A1) in view of Murthi (US20170202536A1)
Regarding Claim 18, Masuda teaches the limitations of Claim 1 and further teaches the first region information of the first ground truth and the first position information of the second ground truth (corresponding disclosure in at least [0055], where the detection target (the four chambers) are acquired based on the first region (the heart) and the data acquired is ground truth data (the data is taken from the segmented CT image, which is referred to as the ground truth) “the region acquisition function 353 first performs a segmentation process of four chambers of the heart (left ventricle: LV, right ventricle: RV, left atrium: LA, and right atrium: RA)” and further in [0055], where the first position (the mitral valve based on the feature points) is acquired “region acquisition function 353 performs a precise feature point detection process of detecting coarse feature points around the mitral valve and then detecting the location of Trigone. Thereafter, the region acquisition function 353 specifies the partial region including the mitral valve on the basis of the detected location of the Trigone”), but does not teach an inferior vena cava region and hepatic vein.
Murthi, in a similar field of endeavor, teaches a similar concept (diagnostics in the heart) of an inferior vena cava region (corresponding disclosure in at least [0030], where the region of the inferior vena cava region is determined “The IVC was located in long axis passing into the right atrium”)
and of a hepatic vein (corresponding disclosure in at least [0030], where the position of the hepatic veins are determined (the cursor is played proximally to the hepatic veins, indicating that the position of the veins are known) “A cursor was placed just proximal to the insertion of the hepatic veins, approximately 2 cm into the liver”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to have located the inferior vena cava region and hepatic vein as taught by Murthi. One of the ordinary skill in the art would have been motivated to incorporate this because the two areas are essential in assessing cardiac function in the heart for signs, such as stroke.
Claim 19 is rejected under 35 U.S.C. 103 as being unpatentable over Masuda (US20230316513A1) in view of Fessler (US20230236271A1).
Regarding Claim 19, Masuda teaches the limitations of Claim 1 and further teaches comprising the steps of: inputting, to the machine learning model, first ultrasound image data based on a reception signal received by an ultrasound probe (corresponding disclosure in at least [0101], where the input image is an ultrasound image “the input image may be a 3D ultrasound image (for example, transcutaneous ultrasound, transesophageal ultrasound, or the like)”);
acquiring detection results from the machine learning model including first region information associated with a detection target of the first ultrasound image data and coordinates of first position information relative to the detection target of the first ultrasound image data or second region information based on the first position information (corresponding disclosure in at least [0085], where there are detection results obtained from the machine learning model, which includes the region and the coordinates associated, which are relative to the image data, as the output is based on the inputted image “ the DenseNet includes layers illustrated in FIG. 8 , and outputs a plurality of three-dimensional coordinates indicating the shape of the anterior leaflet and three-dimensional coordinates indicating the shape of the posterior leaflet in response to input of the 64×64×64 pixel VOI image and the probability map of three channels of the anterior leaflet, the posterior leaflet, and the background of the mitral valve. For example, the DenseNet in FIG. 8 outputs mesh information including 19×9 coordinates as the plurality of three-dimensional coordinates indicating the shape of the anterior leaflet”);
and first ground truth data indicating the first region information and second ground truth data indicating coordinates of the first position information or the second region information (corresponding disclosure in at least [0055], where the detection target (the four chambers) are acquired based on the first region (the heart) and the data acquired is ground truth data (the data is taken from the segmented CT image, which is referred to as the ground truth) “the region acquisition function 353 first performs a segmentation process of four chambers of the heart (left ventricle: LV, right ventricle: RV, left atrium: LA, and right atrium: RA)” and further in [0055], where the first position (the mitral valve based on the feature points) is acquired “region acquisition function 353 performs a precise feature point detection process of detecting coarse feature points around the mitral valve and then detecting the location of Trigone. Thereafter, the region acquisition function 353 specifies the partial region including the mitral valve on the basis of the detected location of the Trigone”), but does not teach comparing the detection results with ground truth data including first ground truth and second ground truth data and updating parameters of the machine learning model based on an error between the detection results and the ground truth data.
Fessler, in a similar field of endeavor, teaches a similar concept (machine learning and data processing) of comparing the detection results with ground truth data including first ground truth and second ground truth data and updating parameters of the machine learning model based on an error between the detection results and the ground truth data (corresponding disclosure in at [0066], where the results and ground truth are compared to then update the machine learning model based on the errors “The reconstruction errors compared with the ground truth are used as the training loss to update learnable parameters (the trajectory ω and the network's parameters θ) (e.g., at 240 of FIG. 2A)”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to have incorporated comparing results to ground truth data to update parameters of the machine learning model based on an error as taught by Fessler. One of the ordinary skill in the art would have been motivated to incorporate this because the model is then improved and further ensured for accurate results.
Response to Arguments
Applicant's arguments filed 01/05/2026 regarding the claim and drawing objections have been fully considered and are withdrawn in light of the amendments.
Applicant's arguments filed 01/05/2026 regarding the 35 U.S.C. 112b rejections have been fully considered and are withdrawn in light of the amendments.
Applicant's arguments filed 01/05/26 regarding the 35 U.S.C. 101 rejections have been fully
considered but are not persuasive. Claim 1 recites the use of an ultrasound probe to obtain ultrasound image data, which is not integrating the judicial exception into a practical application. The ultrasound probe is considered as an additional element, which does not further integrate the abstract idea into practical application (see rejection above). Thus the 35 U.S.C. 101 is maintained.
Applicant’s arguments with respect to claim 1 regarding the 35 U.S.C. 102 (a)(1) and 35 U.S.C. 103 rejections have been considered but are not persuasive.
Regarding Claim 1, Applicant argues that the prior art Masuda does not teach image, the first ground truth, and a second ground truth. However, Masuda teaches in [0055] a ground truth, which is the segmented CT image (see rejection above). Further, Masuda teaches the use of inputting an ultrasound image as well as the CT image into a machine learning model ([0124], where the existence probability calculation function is based on machine learning “the existence probability calculation function 354 can calculate the existence probability based on the blood flow information on the image by aligning the image (CT image) and the ultrasound image”). Further, Masuda teaches the region information as well as the position information relative to the first ultrasound image ([0055], and [0081], where the coordinates or the position of the various regions of interest are calculated in relation to the CT (ground truth) and ultrasound image “the shape estimation function 355 calculates, as the estimated value of the shape, coordinate values of a plurality of locations corresponding to the region of interest”). All other claims are rejected due to their dependency to the independent claim 1.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 KAITLYN KIM whose telephone number is (571)272-1821. The examiner can normally be reached Monday-Friday 6-2 PST.
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, Anne Kozak can be reached at (571) 270-0552. 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.
/K.E.K./Examiner, Art Unit 3797
/SERKAN AKAR/Primary Examiner, Art Unit 3797
Prosecution Insights