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 .
Acknowledgements
This communication is in response to Remarks made on 2/23/2026.
Claims 1, 3, 5-6, 8-9, 13-15, 22 are amended.
Claims 7, 20, 23-24 are canceled.
Claims 28-29 are new.
Claims 1-6, 8-19, 21-22, 25-29 are currently pending and have been examined and are rejected as follows.
Claim Interpretation
Claim 1 and similarly Claims 8, 9, recite “the processing procedure including macroscopic pathology and microscopic pathology;” and further recites “performing, by the medical system in digital pathology, the processing procedure for the first medical case first among a plurality of medical cases based on the first priority value being highest among priority values of the plurality of medical cases.”
Claim 28 recites “wherein the performing the processing procedure includes performing the macroscopic pathology, the macroscopic pathology including photographic recording of an entirety of the tissue removed from the patient.”
The specification describes a system and method that prioritize and present medical cases to a human pathologist for evaluation. See specification para 119 “The pathologist automatically receives a prioritized list of cases, which they can access manually as required.” See specification para 99 “Pathologists want to prioritize their cases for evaluation because there are often some cases among them where starting therapy is time-critical, and this depends on the pathology results. […] Here, the case can be prioritized both for the macroscopic pathological findings and for the microscopic pathological findings.”
The specification further explains macroscopic pathology. See para 3 “Macroscopy (gross imaging) is the photographic recording of the entirety of the tissue removed (that is, for example, the whole of the tumor that has been removed), whilst in microscopy, sub-regions are viewed in colored form and in high resolution.”
In light of the specification description of pathology activities being carried out by a human pathologist Examiner uses the broadest reasonable interpretation consistent with the specification to interpret “performing, by the medical system in digital pathology, the processing procedure” as encompassing a system and method that prioritizes and facilitates pathology activities performed by a human pathologist.
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 1-6, 8-19, 21-22, 25-29 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Claims 1, 8, 9 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite a method and an apparatus for prioritizing medical cases.
The limitations of (Claim 1 being representative ) determining an estimated resource consumption corresponding to a processing procedure for a first medical case, the processing procedure corresponding to a medical system in […] pathology having limited resources, and the processing procedure including macroscopic pathology and microscopic pathology; determining a first priority value for the first medical case by applying first trained functions to a first data set and the estimated resource consumption, the first priority value being output by the first trained functions in response to input of the first data set and the estimated resource consumption, the first trained functions having been trained based on a difference between a first output priority value and a first training priority value, the first output priority value being output by the first trained functions in response to the first trained functions being applied to a first training data set, the first training priority value corresponding to the first training data set, the first data set being assigned to the first medical case, the first data set including data corresponding to a radiological image of a tissue in a patient, and the first priority value corresponding to a priority of […] pathology imaging of the tissue removed from the patient, and the priority of the […] pathology imaging corresponding to an urgency of an evaluation of the patient or an urgency of a therapy for the patient; and performing, by the medical system in […] pathology, the processing procedure for the first medical case first among a plurality of medical cases based on the first priority value being highest among priority values of the plurality of medical cases, as drafted is a process that, under the broadest reasonable interpretation, covers certain methods of organizing human activity (i.e., managing personal behavior including following rules or instructions) but for the recitation of generic computer components. That is, other that reciting (claim 1, 8) computer or (claim 9) a memory and computation circuitry for executing the abstract idea, the claimed invention amounts to managing personal behavior or interaction between people (i.e., a person following a series of rules or steps). For example, but for the various general-purpose computer elements, the claims encompass a person using collected patient data to calculate an priority, compare the priority to a training priority and then outputting corresponding data in the manner described in the identified abstract idea, supra. The Examiner notes that “method of organizing human activity” includes a person’s interaction with a computer (see October 2019 Update: Subject Matter Eligibility at Pg.5). If a claim limitation, under its broadest reasonable interpretation, covers managing personal behavior or interactions between people but for the recitation of generic computer components, then it falls within the “method of organizing human activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A2
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements of (Claim 1, 8) computer-implemented or (Claim 9) memory and computation circuitry. These additional elements are not exclusively described by the applicant and are recited at a high-level of generality (i.e., a generic general-purpose computer or components thereof, see, e.g., Para. [0040]) such that it amounts no more than mere instructions to apply the exception using a generic computer component. 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 further recites the additional element of using the trained function to output a priority value based on training data. This represents mere instructions to implement the abstract idea on a generic computer. Implementing an abstract idea using a generic computer or components thereof 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 further recites the additional element of (claim 9) an interface. The interface merely generally links the abstract idea to a particular technological environment or field of use. Generally linking an abstract idea to a particular technological environment or field of use is insufficient to provide a practical application. Accordingly, even in combination, this additional element does not integrate the abstract idea into a practical application.
The claim further recites the additional element of (claim 9) an interface. The interface merely generally links the abstract idea to a particular technological environment or field of use. MPEP 2106.04(d)(I) indicates that generally linking an abstract idea to a particular technological environment or field of use cannot provide a practical application. Utilization of the interactive user equates to saying “apply it.” MPEP 2106.04(d)(I) indicates that merely saying “apply it” or equivalent to the abstract idea cannot provide a practical application. Accordingly, even in combination, this additional element does not integrate the abstract idea into a practical application.
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional element of “digital” in regards to pathology imaging that implements the identified abstract idea. The “digital” is not described by the applicant and is recited at a high-level of generality (i.e., a generic computer performing a generic computer functions) such that it amounts no more than mere instructions to apply the exception using a generic computer component. 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.
Step 2B
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 a general-purpose computer (or components thereof) to perform the noted steps amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept (“significantly more”).
As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using the trained function to output a priority value based on training data was found to represent mere instructions to implement the abstract idea on a generic computer. This has been re-evaluated under the “significantly more” analysis and determined to be insufficient to provide significantly more. MPEP 2106.05(I) indicates that mere instructions to implement the abstract idea on a generic computer and/or confining the use of the abstract idea to a particular technological environment or field of use cannot provide significantly more.
Also, as discussed above with respect to integration of the abstract idea into a practical application, the additional element of an interface was considered to generally link the abstract idea to a particular technological environment or field of use. This has been re-evaluated under the “significantly more” analysis and has also been found insufficient to provide significantly more. MPEP 2106.05(A) indicates that generally linking an abstract idea to a particular technological environment or field of use cannot provide significantly more. As such the claim is not patent eligible.
As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a digital in regards to pathology imaging to perform the noted steps amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept (“significantly more”). Accordingly, even in combination, this additional element does not provide significantly more. As such the claim is not patent eligible.
Dependent claims
Claims 2-6, 10-19, 21-22, 25-29 are similarly rejected because they either further define/narrow the abstract idea and/or do not further limit the claim to a practical application or provide as inventive concept such that the claims are subject matter eligible even when considered individually or as an ordered combination. Claim 2 merely describes the processing of the medical case using a technical system where the data is from at least a second technical system in a second specialist medical field. Claim 3 merely describes the data set. Claim 4, 12 merely describes the trained functions having been trained on a comparison of a manual change in priority value. Claim 5, 13 merely describes the dataset having one parameter which is an output of another model. Claim 6, 14 merely describes displaying an ordered list for the medical cases ranked by priority. Claim 10 merely describes a medical system comprising an apparatus. Claim 11 merely describes the data set including a parameter and the second training data set including reference information of time of evaluation being relevant to prioritizing a case. Claim 15 merely describes displaying one parameter on which the priority value was determined or a probability parameter predicting probability that the medical case should be prioritized. Claim 16 merely describes the circuitry including a processor. Claim 17 merely describes circuitry having an integrated circuit. Claim 18, 19 merely describes a non-transitory medium. Claim 21 merely describes adjusting a parameter to minimize a difference. Claim 22 merely describes determining a second priority based on a second known training priority and adjusting a parameter based on the second difference to create new trained functions. Claim 25 merely describes the tissue is a tumor. Claim 26 merely describes the priority value corresponding to findings. Claim 27 merely describes output of parameters. Claim 28 merely describes processing procedure. Claim 29 merely describes prioritizing based on radiology image.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-6, 8-22, 25 are rejected under 35 U.S.C. 103 as being unpatentable over Chen (US 20190228524) in view of Godrich (US 20200381122) in view of Gupta (US 20200279173) in view of Bar-Aviv (US 20090028403)
CLAIM 1
Chen teaches:
A computer-implemented method, comprising: (Chen para 6 teaches a computer implemented method. Para 8 teaches a non-transitory computer readable medium having instructions stored thereon. The instructions, when executed by a processor, perform a method. )
determining […] corresponding to a processing procedure for a first medical case, the processing procedure corresponding to a medical system in digital pathology having limited resources; (Chen para 3-6 teaches queuing systems used to help manage high volume of medical images due to time resources being limited. Para 3 teaches pathology reports. )
and the processing procedure including […] pathology and […] pathology (Chen para 3 and 46 teach digital pathology. Para 46 teaches pathology analysis of a specific organ)
determining a first priority value for the first medical case by applying first trained functions to a first data set, and […] (Chen Para 15 teaches using artificial intelligence (i.e., trained function) for determining priority scores for processing medical image data. See also Para 46 which teaches various other embodiments of trained algorithms. )
the first priority value being output by the first trained functions in response to input of the first dataset and the […], the first trained functions having been trained based on a difference between a first output priority value and a first training priority value, (Chen para 48 teaches priority score being calculated directly from images features with a regression algorithm such as a deep convolutional network. Examiner notes that by definition regression algorithms, such as a convolutional networks, are trained functions and is a type of supervised learning that seeks to understand relationships between dependent variables (i.e., image feature data in Chen) and independent variables (i.e., Priority value in Chen). Further by definition a regression algorithm such as a convolutional network is trained based on the differences between the outputs of the model and the labels of the training data. Minimizing this difference over time is the training of the model in order to make it useful. Because a regression algorithm is used in Chen to predict priority values using image feature data then it is necessary to train it based on the output of the model (output training priority) and training value (training priority value).)
the first output priority value being output by the first trained functions in response to the first trained functions being applied to a first training data set, (Chen Para 57 teaches displaying the priority score for medical image data. Para 48 teaches priority scores are determined by regression algorithm such as convolutional network (i.e., a trained function) using image feature data (i.e., training data set))
the first training priority value corresponding to the first training data set, (Chen para 48 teaches priority score being calculated directly from images features with a regression algorithm such as a deep convolutional network. Examiner notes that by definition regression algorithms such as a convolutional networks are trained functions using training data set and a training priority value would correspond to the training data set in order to be trained.)
the first data set being assigned to the first medical case, (Chen para 15 teaches image data (i.e., first data set) is for a patient case (i.e., medical case))
the first data set including data corresponding to a radiological image of a tissue in a patent, and (Chen para 22 teaches imaging including magnetic resonance imaging (MRI) images, 3D MRI, 2D fluidized MRI, 4D volume MRI, computed tomography (CT) images, cone beam CT, positron emission tomography (PET) images, functional MRI images (such as fMRI, DCE-MRI and diffusion MRI), X-ray images, fluorescence images, ultrasound images, radiotherapy shot images, single photon emission computed tomography (SPECT) images, and so on for acquiring medical images of a patient. )
the first priority value corresponding to a priority of digital pathology imaging […]; and (Chen Para 57 teaches displaying the priority score for medical image data. Para 48-49 teach priority score.)
the priority of the digital pathology imaging corresponding to an urgency of an evaluation of the patient or an urgency of a therapy for the patient; and (Chen [0019] The respective priority score may be used for evaluating the level of emergency of the patient case. Para 4 teaches emergency cases. )
performing, by the medical system in digital pathology, the processing procedure for first medical case among a plurality of medical cases based on the first priority value being highest among priority values of the plurality of medical cases. (Chen para 15 teaches obtaining a priority score for medical image data. Para 18 teaches processing of case based on priority. Para 49 teaches priority of cases from 0 to 100 where 100 is highest score and more prioritized of cases. Para 50 teaches the analysis result of the image analysis module 123 may be further analyzed comprehensively, which may be implemented by the comprehensive analysis module 124 where a comprehensive analysis with respect to the diagnosis result of medical image data, the image features of the medial images, and the attribute information of a patient of the medical images may be performed. )
Chen does not teach:
and the processing procedure including […] pathology and microscopic pathology
wherein the priority value corresponding to a priority of digital pathology imaging of the tissue removed from the patient; and
Godrich does teach:
and the processing procedure including macroscopic pathology and microscopic pathology (Godrich para 28 teaches pathology including slides viewed under a microscope)
the priority value corresponding to a priority of digital pathology imaging of the tissue removed from the patient; and (Godrich para 41 teaches prioritizing pathology of tissue specimens from patients in a slide. Examiner notes if the tissue is on a slide then it is tissue removed from the patient)
It would have been obvious to one or ordinary skill in the art, before the effective filing date of the claimed invention, to modify the pathology as taught by Chen with the microscopic pathology and tissue removed from a patient as taught by Godrich. It would be beneficial for pathology images to includes microscopic pathology because there is a desire to streamline processing of pathology slides which include microscopic pathology images to streamline pathology workflow as taught by Godrich para 2-3.
Chen does not teach
determining an estimated resource consumption corresponding to a processing procedure for a first medical case, the processing procedure corresponding to a medical system in digital pathology having limited resources
determining a first priority value for the first medical case by applying first trained functions to a first data set, and the estimated resource consumption
the first priority value being output by the first trained functions in response to input of the first dataset and the estimated resource consumption,
Gupta does teach:
determining an estimated resource consumption corresponding to a processing procedure for a first medical case, the processing procedure corresponding to a medical system in digital pathology having limited resources (Gupta para 44 teaches predicting resource consumption before prioritization.)
determining a first priority value for the first medical case by applying first trained functions to a first data set, and the estimated resource consumption (Gupta para 20 teaches a machine learning algorithm to prioritize data based on consumption data. Para 44 teaches predicting resource consumption before prioritization. Para 21, 35, 103 further teaches assigning priorities based on resources to run the job. )
the first priority value being output by the first trained functions in response to input of the first dataset and the estimated resource consumption, (Gupta para 20 teaches a machine learning algorithm to prioritize data based on consumption data. Para 44 teaches predicting resource consumption before prioritization. Para 21, 35, 103 further teaches assigning priorities based on resources to run the job. )
It would have been prima facie obvious to one of ordinary skill in the art at the time the invention was made to combine the noted features of Gupta with teaching of Chen in view of Godrich since the combination of the two references is merely combining prior art elements according to known methods to yield predictable results (KSR rational A); see MPEP 2143(I)(A)). It can be seen that each element claimed is present in either Gupta or Chen in view of Godrich. Determining an estimated resource consumption corresponding to a processing procedure as taught by Gupta does not change or affect the normal prioritizing of cases. Prioritizing cases would be performed the same way even with the addition of estimating resource consumption. Since the functionalities of the elements in Gupta and Chen in view of Godrich do not interfere with each other, the results of the combination would be predictable.
Chen in view of Godrich in view of Gupta does not teach and the processing procedure including macroscopic pathology and microscopic pathology.
Bar-Aviv does not teach and the processing procedure including macroscopic pathology and microscopic pathology (Bar-Aviv para 145 teaches prioritizing an image of an organ)
It would have been obvious to one or ordinary skill in the art, before the effective filing date of the claimed invention, to modify the pathology as taught by Chen in view of Godrich with the macroscopic pathology as taught by Bar-Aviv. It would be beneficial for pathology images to include macroscopic pathology because there is a need to improve workflow of medical images which include macroscopic pathology images as taught by Bar-Aviv para 21.
CLAIM 2
Chen teaches wherein the first data set includes data from at least one technical system in a specialist medical field, the specialist medical field including a field of radiology. (Chen para 22 teaches data can include MRI, CT, X-ray, fluorescence images, ultrasound images, radiotherapy shot images, single photon emission computed tomography (SPECT) images.)
CLAIM 3
Chen teaches wherein the first data set comprises at least one of: (Chen para 14 teaches medical data)
a first parameter defining whether a time of evaluation is relevant to a decision for a first diagnosis or a first therapy, (Chen para 24 teaches data acquisition time is recorded. Para 33 teaches the length of time of the case in a waiting queue is a factor to in increasing the priority score so that cases that are there longer will increase in priority over time so all cases are reviewed in a timely manner. Chen para 5 teaches priority value is used to ensure the optimal treatment window is not delayed (i.e., first therapy))
the first parameter being determined by applying second trained functions to the first data set, the second trained functions being trained using a second training data set including reference information as to whether the time of evaluation of a first training case was relevant for a decision on a training diagnosis or a first training therapy; (Chen para 54 teaches using an artificial intelligence based means for processing medical image data (Examiner notes this includes the data acquisition time as taught in para 24). Para 48 a regression algorithm such as a deep convolutional network to determine priority score based on medical image data features (Examiner notes this includes the data acquisition time as taught in para 24). Examiner notes that by definition regression algorithms such as a convolutional networks are trained functions and that by definition are trained based on weighting features that make up the regression algorithm which is based on the difference between the output of the model and the labels of the training data. (i.e., Training requires reference information as to whether a feature, such as acquisition time understood to be analogous to time of evaluation, is relevant for a decision))
[…] (Examiner notes additional claim limitations are interpreted as optional due to claim language “at least one of … or”)
a pre-existing condition; (Chen para 14 teaches medical history which Examiner notes would include pre-existing conditions. )
a pathology image of the pre-existing condition; (Chen para 14 teaches medical history which Examiner notes would include pathology images of pre-existing images.)
or patient data. (Chen para 14 teaches medical image data which is patient data. Para 14 also teaches patient subject's age, height, weight, gender, medical history and the like)
CLAIM 4, 12
Chen teaches wherein the first trained functions have been trained based on a comparison of a previous manual change in a priority value with a priority value determined by computer implementation. (Chen Para 25 teaches an automatic diagnosis result (including a priority score) is compared to a doctor diagnosis result and then sent to more doctors for a more comprehensive diagnosis result. Para 27 teaches using final diagnosis result data as training data to train an artificial intelligence analysis module to improve precision of the artificial intelligence module. See also para 60. )
CLAIM 5, 13
Chen teaches wherein the first data set includes at least one parameter, each of the at least one parameter being an output value from a corresponding trainable model that has been applied to a second data set from a technical system different from a technical system from which the first data set is obtained, the at least one parameter including at least one of: (Para 45 teaches a deep convolution network (i.e., trainable model) for classifying images into different organs and sub regions. Para 22 teaches images may be from different fields and systems such as MRI, CT, X-ray, fluorescence images, ultrasound images, radiotherapy shot images, single photon emission computed tomography (SPECT) images)
an automated image evaluation of available image data relating to the medical case output by a first trainable model; (Para 45 teaches automatically evaluating image data using a deep convolution network (i.e., trainable model) for classifying images into different organs and sub regions)
[…] (Examiner notes additional claim limitations are interpreted as optional due to claim language “at least one of … or”)
CLAIM 6, 14
Chen teaches causing display of an ordered list including the first medical case and further medical cases, a position of the first medical case in the ordered list being based on the first priority value. (Chen para 54-55 teaches a sorted order of the medical image data. Para 33 teaches sorting based on the priority score. See also Fig 3 where cases are sorted by priority. )
CLAIM 8
Chen teaches A computer implemented method for providing first trained functions, the first trained functions being trained for determining a first priority value of a first medical case, and the method comprising: (Chen para 6 teaches a computer implemented method. Chen para 48 teaches priority score being calculated directly from images features (i.e., medical case) with a regression algorithm such as a deep convolutional network. Examiner notes that by definition regression algorithms, such as a convolutional networks, are trained functions)
receiving a first training data set relating to at least one medical training case, (Chen para 48 teaches a regression algorithm such as a deep convolutional network for evaluating image feature data (i.e., data set relating to a medical case) to predict priority scores. Examiner notes that this requires training data which would be the image feature data. Chen para 45 also teaches image data being used as training data. )
the first training data set being associated with a first known training priority for the at least one medical training case; (Chen para 48 teaches priority score being calculated directly from images features with a regression algorithm such as a deep convolutional network. Examiner notes that by definition regression algorithms require a labeled training set. )
the first training data set including data corresponding to a radiological image of a tissue in a patient […] and a training […] for a first medical case, the processing procedure corresponding to a medical system in digital pathology having limited resources (Chen para 48 teaches priority score being calculated directly from images features (i.e., radiological images) with a regression algorithm such as a deep convolutional network which requires training. Examiner notes that by definition regression algorithms require a labeled training set. Para 22 teaches images may be from different fields and systems such as MRI, CT, X-ray, fluorescence images, ultrasound images, radiotherapy shot images, single photon emission computed tomography (SPECT) images) Chen para 3-6 teaches queuing systems used to help manage high volume of medical images due to time resources being limited. Para 3 teaches pathology reports.)
and the processing procedure including […] pathology and […] pathology (Chen para 3 and 46 teach digital pathology. Para 46 teaches pathology analysis of a specific organ)
determining a second priority value for the at least one medical training case by applying trainable functions to the first training data set, (Chen para 46 teaches a random forest and gradient boosting decision tree as an example of an algorithm used to determine priority score. Examiner notes Random forests by definition create multiple decision trees each trained on random subset of data features (Examiner notes this feature subset may be the same feature subset for a number of trees based on the number of features, number of trees and size of training data) and then combine their predictions by taking a majority vote.)
the second priority value corresponding to a priority of digital pathology imaging […], and (Chen Para 57 teaches displaying the priority score for medical image data. Para 48-49 teach priority score.)
the priority of the digital pathology imaging corresponding to an urgency of an evaluation of the patient or an urgency of a therapy for the patient; and (Chen [0019] The respective priority score may be used for evaluating the level of emergency of the patient case. Para 4 teaches emergency cases. )
determining a first difference between the second priority value and the first known training priority; and adjusting at least one first parameter in the trainable functions based on the first difference to obtain the first trained functions. (Chen para 46 teaches a random forest and gradient boosting decision tree as an example of an algorithm used to determine priority score. Examiner notes Random forests by definition create multiple decision trees each trained on random subset of data features (Examiner notes this feature subset may be the same feature subset for a number of trees based on the number of features, number of trees and size of training data) and then combine their predictions by taking a majority vote. Examiner notes that a first random tree would give a first priority value and a second random tree would give a second priority value. The features (parameters) of the random tree are then adjusted based on the difference in the labeled data (known training priority) and the model output (random tree priority value) in order to tune the random forest as a whole. Examiner notes gradient boosting takes weak learners and makes them into stronger learners by taking previous learner results and adding another weak learner based on previous performance in order to create a stronger learner. Examiner notes this too would determine a first priority value and then a second priority value (up to N priority value based on number of trees) until the difference between the labeled data and model output are sufficiently decreased or number of trees has hit designer required maximum. Examiner notes both techniques are trained based on the difference in model output and labeled training data in order to result in the final trained model.)
Chen does not teach:
and the processing procedure including macroscopic pathological findings and microscopic pathological pathology
wherein the priority value corresponding to a priority of digital pathology imaging of the tissue removed from the patient; and
Godrich does teach:
and the processing procedure including macroscopic pathology and microscopic pathology. (Godrich para 28 teaches pathology including slides viewed under a microscope)
the priority value corresponding to a priority of digital pathology imaging of the tissue removed from the patient; and (Godrich para 41 teaches prioritizing pathology of tissue specimens from patients in a slide. Examiner notes if the tissue is on a slide then it is tissue removed from the patient)
It would have been obvious to one or ordinary skill in the art, before the effective filing date of the claimed invention, to modify the pathology as taught by Chen with the microscopic pathology and tissue removed from a patient as taught by Godrich. It would be beneficial for pathology images to includes microscopic pathology because there is a desire to streamline processing of pathology slides which include microscopic pathology images to streamline pathology workflow as taught by Godrich para 2-3.
Chen in view of Godrich do not teach the first training data set including data corresponding to a radiological image of a tissue in a patient and a training estimated resource consumption corresponding to a processing procedure for a first medical case, the processing procedure corresponding to a medical system in digital pathology having limited resources
Gupta does teach the first training data set including data corresponding to a radiological image of a tissue in a patient and a training estimated resource consumption corresponding to a processing procedure for a first medical case, the processing procedure corresponding to a medical system in digital pathology having limited resources (Gupta para 20 teaches a machine learning algorithm to prioritize data based on consumption data. Para 44 teaches predicting resource consumption before prioritization. Para 21, 35, 103 further teaches assigning priorities based on resources to run the job.)
It would have been prima facie obvious to one of ordinary skill in the art at the time the invention was made to combine the noted features of Gupta with teaching of Chen in view of Godrich since the combination of the two references is merely combining prior art elements according to known methods to yield predictable results (KSR rational A); see MPEP 2143(I)(A)). It can be seen that each element claimed is present in either Gupta or Chen in view of Godrich. Determining an estimated resource consumption corresponding to a processing procedure as taught by Gupta does not change or affect the normal prioritizing of cases. Prioritizing cases would be performed the same way even with the addition of estimating resource consumption. Since the functionalities of the elements in Gupta and Chen in view of Godrich do not interfere with each other, the results of the combination would be predictable.
Chen in view of Godrich in view of Gupta does not teach and the processing procedure including macroscopic pathology and microscopic pathology.
Bar-Aviv does not teach and the processing procedure including macroscopic pathology and microscopic pathology (Bar-Aviv para 145 teaches prioritizing an image of an organ)
It would have been obvious to one or ordinary skill in the art, before the effective filing date of the claimed invention, to modify the pathology as taught by Chen in view of Godrich with the macroscopic pathology as taught by Bar-Aviv. It would be beneficial for pathology images to include macroscopic pathology because there is a need to improve workflow of medical images which include macroscopic pathology images as taught by Bar-Aviv para 21.
CLAIM 9
Chen teaches An apparatus, comprising: a memory to store executable commands; computation circuitry that, upon the commands being carried out in the computation circuitry, is configured (Chen para 60 teaches a processor and computer-readable storage medium may store computer executable instructions thereon, wherein when executed by a processor, the processor may perform any one of the above methods.
determine […] corresponding to a processing procedure for a first medical case, the processing procedure corresponding to a medical system in digital pathology having limited resources; (Chen para 3-6 teaches queuing systems used to help manage high volume of medical images due to time resources being limited. Para 3 teaches pathology reports. )
and the processing procedure including […] pathology and […] pathology (Chen para 3 and 46 teach digital pathology. Para 46 teaches pathology analysis of a specific organ (macroscopic).)
determine a first priority value for a medical case by applying trained functions to a data set and the estimated resource consumption, the first priority value being output by the trained functions in response to input of the first data set and […], the trained functions having been trained based on a difference between an output priority value and a known training priority value, (Chen para 46 teaches a random forest and gradient boosting decision tree as an example of an algorithm used to determine priority score. Examiner notes Random forests by definition create multiple decision trees each trained on random subset of data features (Examiner notes this feature subset may be the same feature subset for a number of trees based on the number of features, number of trees and size of training data) and then combine their predictions by taking a majority vote. Examiner notes that a first random tree would give a first priority value and a second random tree would give a second priority value. The features (parameters) of the random tree are then adjusted based on the difference in the labeled data (known training priority) and the model output (random tree priority value) in order to tune the random forest as a whole. Examiner notes gradient boosting takes weak learners and makes them into stronger learners by taking previous learner results and adding another weak learner based on previous performance in order to create a stronger learner. Examiner notes this too would determine a first priority value and then a second priority value (up to N priority value based on number of trees) until the difference between the labeled data and model output are sufficiently decreased or number of trees has hit designer required maximum. Examiner notes both techniques are trained based on the difference in model output and labeled training data in order to result in the final trained model.)
the output priority value being output by the trained functions in response to the trained functions being applied to a training data set, the known training priority value corresponding to the training data set, (Chen para 48 teaches priority score being calculated directly from images features with a regression algorithm such as a deep convolutional network. Examiner notes that by definition regression algorithms require a labeled training set. )
and the data set being assigned to the medical case, (Chen para 48 teaches priority score being calculated directly from images features (i.e., medical case) with a regression algorithm such as a deep convolutional network. Examiner notes that by definition regression algorithms, such as a convolutional networks, are trained functions)
the data set including data corresponding to a radiological image of a tissue in a patient, (Chen para 48 teaches priority score being calculated directly from images features (i.e., radiological images) with a regression algorithm such as a deep convolutional network which requires training. Examiner notes that by definition regression algorithms require a labeled training set. Para 22 teaches images may be from different fields and systems such as MRI, CT, X-ray, fluorescence images, ultrasound images, radiotherapy shot images, single photon emission computed tomography (SPECT) images))
the priority value corresponding to a priority of digital pathology imaging […], and (Chen Para 57 teaches displaying the priority score for medical image data. Para 48-49 teach priority score.)
the priority of the digital pathology imaging corresponding to an urgency of an evaluation of the patient or an urgency of a therapy for the patient; and (Chen [0019] The respective priority score may be used for evaluating the level of emergency of the patient case. Para 4 teaches emergency cases. Para 4 teaches time sensitive treatment and evaluation required)
an interface to provide the first priority value for processing of the first medical case, (Chen para 7 teaches an interface providing a queue of medical cases based on priority for display)
the medical system in digital pathology being configured to perform the processing procedure for the first medical case among a plurality of medical cases based on the first priority value being highest among priority values of the plurality of medical cases. (Chen para 15 teaches obtaining a priority score for medical image data. Para 18 teaches processing of case based on priority. Para 49 teaches priority of cases from o to 100 where 100 is highest score and more prioritized of cases)
Chen does not teach:
and the processing procedure including macroscopic pathological findings and microscopic pathological pathology
wherein the priority value corresponding to a priority of digital pathology imaging of the tissue removed from the patient; and
Godrich does teach:
and the processing procedure including macroscopic pathology and microscopic pathology. (Godrich para 28 teaches pathology including slides viewed under a microscope)
the priority value corresponding to a priority of digital pathology imaging of the tissue removed from the patient; and (Godrich para 41 teaches prioritizing pathology of tissue specimens from patients in a slide. Examiner notes if the tissue is on a slide then it is tissue removed from the patient)
It would have been obvious to one or ordinary skill in the art, before the effective filing date of the claimed invention, to modify the pathology as taught by Chen with the microscopic pathology and tissue removed from a patient as taught by Godrich. It would be beneficial for pathology images to includes microscopic pathology because there is a desire to streamline processing of pathology slides which include microscopic pathology images to streamline pathology workflow as taught by Godrich para 2-3.
Chen in view of Godrich do not teach
determining an estimated resource consumption corresponding to a processing procedure for a first medical case, the processing procedure corresponding to a medical system in digital pathology having limited resources
determining a first priority value for the first medical case by applying first trained functions to a first data set, and the estimated resource consumption
the first priority value being output by the first trained functions in response to input of the first dataset and the estimated resource consumption,
Gupta does teach:
determining an estimated resource consumption corresponding to a processing procedure for a first medical case, the processing procedure corresponding to a medical system in digital pathology having limited resources (Gupta para 44 teaches predicting resource consumption before prioritization.)
determining a first priority value for the first medical case by applying first trained functions to a first data set, and the estimated resource consumption (Gupta para 20 teaches a machine learning algorithm to prioritize data based on consumption data. Para 44 teaches predicting resource consumption before prioritization. Para 21, 35, 103 further teaches assigning priorities based on resources to run the job. )
the first priority value being output by the first trained functions in response to input of the first dataset and the estimated resource consumption, (Gupta para 20 teaches a machine learning algorithm to prioritize data based on consumption data. Para 44 teaches predicting resource consumption before prioritization. Para 21, 35, 103 further teaches assigning priorities based on resources to run the job. )
It would have been prima facie obvious to one of ordinary skill in the art at the time the invention was made to combine the noted features of Gupta with teaching of Chen in view of Godrich since the combination of the two references is merely combining prior art elements according to known methods to yield predictable results (KSR rational A); see MPEP 2143(I)(A)). It can be seen that each element claimed is present in either Gupta or Chen in view of Godrich. Determining an estimated resource consumption corresponding to a processing procedure as taught by Gupta does not change or affect the normal prioritizing of cases. Prioritizing cases would be performed the same way even with the addition of estimating resource consumption. Since the functionalities of the elements in Gupta and Chen in view of Godrich do not interfere with each other, the results of the combination would be predictable.
Chen in view of Godrich in view of Gupta does not teach and the processing procedure including macroscopic pathology and microscopic pathology.
Bar-Aviv does not teach and the processing procedure including macroscopic pathology and microscopic pathology (Bar-Aviv para 145 teaches prioritizing an image of an organ)
It would have been obvious to one or ordinary skill in the art, before the effective filing date of the claimed invention, to modify the pathology as taught by Chen in view of Godrich with the macroscopic pathology as taught by Bar-Aviv. It would be beneficial for pathology images to include macroscopic pathology because there is a need to improve workflow of medical images which include macroscopic pathology images as taught by Bar-Aviv para 21.
CLAIM 10
Chen teaches A medical system, comprising at least one apparatus of claim 9. (Chen para 20 teach a medical image management system. )
CLAIM 11
Chen teaches wherein the first data set includes the first parameter; and (Chen Para 14 teaches medical image data which includes, but is not limited to, medical image data, attribute information (such as acquisition time, upload time, data source and the like) of the medial images, for example, the examination type to which the medical images belong, and the subject attribute information (such as the subject's age, height, weight, gender, medical history and the like)) and
the second training data set includes reference information as to whether the time of evaluation of the first training case was relevant for the decision on the training diagnosis or the first training therapy (Chen para 48 teaches a regression algorithm based on image data. Para 24 teaches image feature data includes acquisition time understood to be analogous to time of evaluation. Examiner notes that a regression algorithm works using training data of labeled cases therefore the training data used by Chen would include acquisition time and a label and therefore be by definition reference information as to whether the acquisition time, understood to be analogous to time of evaluation, was relevant for the decision on the training diagnosis. Examiner notes that weighting the contribution of features value impact on results using training data is how regression algorithms work. Minimizing the error by adjusting weights on feature values contribution is the training process of a regression algorithm. )
based on a manual note indicating whether the first training case should have been prioritized. (Chen para 54 teaches a diagnosis result including a priority score can be corrected by a doctor (i.e., manual note on whether the case should have been prioritized))
CLAIM 15
Chen teaches causing display of at least one of at least one parameter based on which the priority value was determined, or […] (Chen Para 57 teaches displaying the image on which the priority score was based on. Examiner notes additional limitation interpreted as optional due to claim language “… or …”)
CLAIM 16
Chen teaches wherein the computation circuitry includes at least one processor. (Chen para 17 teaches at least one processor)
CLAIM 17
Chen teaches wherein the computation circuitry includes at least one integrated circuit. (Chen para circuity that includes at least one integrated circuit. )
CLAIM 18
Chen teaches A non-transitory electronically readable data carrier storing commands which, when carried out by a computer, cause the computer to carry out the computer-implemented method of claim 1. (Chen para 60 teaches a processor and computer-readable storage medium may store computer executable instructions thereon, wherein when executed by a processor, the processor may perform any one of the above methods. The following claim limitations are analogous to claim 1 and therefore similarly analyzed and rejected in the same manner.
CLAIM 19
Chen teaches A non-transitory electronically readable data carrier storing commands which, when carried out by a computer, cause the computer to carry out the computer-implemented method of claim 8. (Chen para 60 teaches a processor and computer-readable storage medium may store computer executable instructions thereon, wherein when executed by a processor, the processor may perform any one of the above methods. The following claim limitations are analogous to claim 1 and therefore similarly analyzed and rejected in the same manner.
CLAIM 21
Chen teaches wherein the adjusting adjusts the at least one first parameter to minimize the first difference. (Chen para 48 teaches a regression algorithm to determine priority scores. Examiner notes by definition regression algorithms work by adjusting parameters in order to minimize a difference in a prediction and training data. )
CLAIM 22
Chen teaches wherein the method further comprises: determining a third priority value for the first medical case by applying the first trained functions to a data set assigned to the first medical case; determining a second difference between the third priority value and a second known training priority, the second known training priority being based on the first priority value or a change to the first priority value; and adjusting at least one second parameter in the first trained functions based on the second difference to obtain second trained functions. (Chen para 46 teaches a random forest and gradient boosting decision tree as an example of an algorithm used to determine priority score. Examiner notes Random forests by definition create multiple decision trees each trained on random subset of data features (Examiner notes this feature subset may be the same feature subset for a number of trees based on the number of features, number of trees and size of training data) and then combine their predictions by taking a majority vote. Examiner notes that a first random tree would give a first priority value and a second random tree would give a second priority value. The features (parameters) of the random tree are then adjusted based on the difference in the labeled data (known training priority) and the model output (aggregate average random tree priority value) in order to tune the random forest as a whole. Therefore the adjusting of a parameter would be based on the difference in the second priority value (and N priority values of N random trees). Examiner notes gradient boosting takes weak learners and makes them into stronger learners by taking previous learner results and adding another weak learner based on previous performance in order to create a stronger learner. Examiner notes this too would determine a first priority value and then a second priority value (up to N priority value based on number of decision trees) until the difference between the labeled data and model output are sufficiently decreased or number of trees has hit designer required maximum. Examiner notes both techniques are trained based on the difference in model output and labeled training data in order to result in the final trained model.)
CLAIM 25
Chen teaches wherein the tissue is a tumor. (Chen para 50 teaches the imaged site may be a tumor)
CLAIM 26
Chen teaches wherein the first priority value corresponds to a priority for […] pathological findings and […] pathological findings. (Chen Para 15 teaches using artificial intelligence (i.e., trained function) for determining priority scores for processing medical image data. )
Chen does not teach wherein the first priority value corresponds to a priority for […] pathological findings and microscopic pathological findings.
Godrich does teach wherein the first priority value corresponds to a priority for […] pathological findings and microscopic pathological findings. (Godrich para 28 teaches pathology including slides viewed under a microscope)
It would have been obvious to one or ordinary skill in the art, before the effective filing date of the claimed invention, to modify the pathology as taught by Chen with the microscopic pathology as taught by Godrich. It would be beneficial for pathology images to includes microscopic pathology because there is a desire to streamline processing of pathology slides which include microscopic pathology images as taught by Godrich para 3.
Chen in view of Godrich does not teach wherein the first priority value corresponds to a priority for macroscopic pathological findings and microscopic pathological findings.
Bar-Aviv does not teach wherein the first priority value corresponds to a priority for macroscopic pathological findings and microscopic pathological findings. (Bar-Aviv para 145 teaches prioritizing an image of an organ)
It would have been obvious to one or ordinary skill in the art, before the effective filing date of the claimed invention, to modify the pathology as taught by Chen in view of Godrich with the macroscopic pathology as taught by Bar-Aviv. It would be beneficial for pathology images to include macroscopic pathology because there is a need to improve workflow of medical images which include macroscopic pathology images as taught by Bar-Aviv para 21.
CLAIM 27
Chen teaches wherein the determining the first priority value includes determining at least one parameter by applying the first trained functions to the first data set […], the at least one parameter being a subset of parameters included in the first data set, and the at least one parameter being output by the first trained functions in response to input of the first data set […] based on the at least one parameter being relevant in determining the first priority value. (Chen para 47-48 teaches identifying lesion using a deep convolution network to estimate an area that plays a positive influence on a certain decision which may be the priority score of the image because it is a diagnosis condition. Para 57 teaches selecting or highlighting the display region according to the calculation )
Chen does not teach wherein the determining the first priority value includes determining at least one parameter by applying the first trained functions to the first data set and the estimated resource consumption, the at least one parameter being a subset of parameters included in the first data set, and the at least one parameter being output by the first trained functions in response to input of the first data set and the estimated resource consumption based on the at least one parameter being relevant in determining the first priority value.
Gupta does teach wherein the determining the first priority value includes determining at least one parameter by applying the first trained functions to the first data set and the estimated resource consumption, the at least one parameter being a subset of parameters included in the first data set, and the at least one parameter being output by the first trained functions in response to input of the first data set and the estimated resource consumption based on the at least one parameter being relevant in determining the first priority value. (Gupta para 44 teaches predicting resource consumption before prioritization)
It would have been prima facie obvious to one of ordinary skill in the art at the time the invention was made to combine the noted features of Gupta with teaching of Chen in view of Godrich since the combination of the two references is merely combining prior art elements according to known methods to yield predictable results (KSR rational A); see MPEP 2143(I)(A)). It can be seen that each element claimed is present in either Gupta or Chen in view of Godrich. Determining an estimated resource consumption corresponding to a processing procedure as taught by Gupta does not change or affect the normal prioritizing of cases. Prioritizing cases would be performed the same way even with the addition of estimating resource consumption. Since the functionalities of the elements in Gupta and Chen in view of Godrich do not interfere with each other, the results of the combination would be predictable.
CLAIM 28
Chen teaches wherein the performing the processing procedure includes performing the […] pathology, the […] pathology including photographic recording […]. (Chen para 50 teaches the imaged site may be a tumor. Chen para 22 teaches imaging including magnetic resonance imaging (MRI) images, 3D MRI, 2D fluidized MRI, 4D volume MRI, computed tomography (CT) images, cone beam CT, positron emission tomography (PET) images, functional MRI images (such as fMRI, DCE-MRI and diffusion MRI), X-ray images, fluorescence images, ultrasound images, radiotherapy shot images, single photon emission computed tomography (SPECT) images, and so on for acquiring medical images of a patient. )
Chen does not teach wherein the performing the processing procedure includes performing the […] pathology, the […] pathology including photographic recording of an entirety of the tissue removed from the patient.
Godrich does teach wherein the performing the processing procedure includes performing the […] pathology, the […] pathology including photographic recording of an entirety of the tissue removed from the patient. (Godrich para 41 teaches prioritizing pathology of tissue specimens from patients in a slide. Examiner notes if the tissue is on a slide then it is tissue removed from the patient)
It would have been obvious to one or ordinary skill in the art, before the effective filing date of the claimed invention, to modify the pathology as taught by Chen with the tissue removed from a patient as taught by Godrich. It would be beneficial for pathology images to includes tissue removed from a patient because there is a desire to streamline processing of pathology slides which include tissue removed from a patient to streamline pathology workflow as taught by Godrich para 2-3.
Chen does not teach wherein the performing the processing procedure includes performing the macroscopic pathology, the macroscopic pathology including photographic recording of an entirety of the tissue removed from the patient.
Bar-Aviv does not teach wherein the performing the processing procedure includes performing the macroscopic pathology, the macroscopic pathology including photographic recording of an entirety of the tissue removed from the patient. (Bar-Aviv para 145 teaches prioritizing an image of an organ)
It would have been obvious to one or ordinary skill in the art, before the effective filing date of the claimed invention, to modify the pathology as taught by Chen in view of Godrich with the macroscopic pathology as taught by Bar-Aviv. It would be beneficial for pathology images to include macroscopic pathology because there is a need to improve workflow of medical images which include macroscopic pathology images as taught by Bar-Aviv para 21.
CLAIM 29
Chen teaches wherein the first trained functions are trained to output the priority of digital pathology imaging of the tissue removed from the patient based on input of the radiological image of the tissue in the patient. (Chen para 22 teaches data can include MRI, CT, X-ray, fluorescence images, ultrasound images, radiotherapy shot images, single photon emission computed tomography (SPECT) images. Chen para 48 teaches priority score being calculated directly from images features (i.e., radiological images) with a regression algorithm such as a deep convolutional network which requires training. Examiner notes that by definition regression algorithms require a labeled training set. Para 22 teaches images may be from different fields and systems such as MRI, CT, X-ray, fluorescence images, ultrasound images, radiotherapy shot images, single photon emission computed tomography (SPECT) images) Chen para 3-6 teaches queuing systems used to help manage high volume of medical images due to time resources being limited. Para 3 teaches pathology reports.)
Prior Art Made of Record and Not Relied Upon
43. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20180165805 Eusemann
Abstract teaches A system includes acquisition of an image of a patient volume, automatic determination of medical findings based on the image of the patient volume, automatic determination to assign the medical findings to a priority review queue
US 20130071002 Otsuka
Abstract teaches A system and method supporting medical diagnosis made based on evaluation of images of a histopathology sample.
Stallard, Researchers Report Milestone in Use of Artificial Intelligence in Pathology, July 15, 2019 (Year: 2019)
Summary teaches machine learning for pathology.
Response to Arguments Regarding 35 U.S.C. 101 Rejection
Applicant argue pg. 13-14:
On pages 3-4 of the Office Action, the Examiner asserts that all of the below- bolded features of claim 1 as previously recited are directed to the alleged abstract idea of "a person using collected patient data to calculate an [sic] priority, compare the priority to a trained priority and then outputting corresponding data in the manner described in the identified abstract idea." Specifically, the Examiner asserts that the alleged abstract idea falls within the sub-grouping of "managing personal behavior and interactions between people ... [including] rules or instructions" of the abstract idea grouping "certain methods of organizing human activity." Accordingly, the non-bolded features represent additional elements relative to this alleged abstract idea. […] Applicants respectfully disagree for at least the reasons contained in the Amendments filed on October 16, 2024 and April 14, 2025, and incorporated herein by reference.
Examiner responds:
The Examiner respectfully disagrees for at least the reasons expressed in Final Rejection 6/23/25 pg. 29.
Applicant argue pg. 14-15:
An additional element reflecting an improvement to the functioning of a computer, or an improvement to another technology or technical field, integrates the alleged exception into a practical application. […] Applicants respectfully submit that amended claim 1 as a whole recites such an improvement to the functioning of a computer, or to another technology or technical field, and thus, integrates any alleged exception into a practical application, for at least the reasons contained on pages 13-14 of the October 16, 2024 Amendment and incorporated herein by reference. Nonetheless, Applicants have amended claim 1. Applicants respectfully disagree for at least the reasons contained on page 15 of the Amendment filed on April 14, 2025. […] Applicants submit that amended claim 1 is directed to improved devices and methods for at least the reasons contained in the October 16, 2024 Amendment, especially in view of claim 1 as amended.
Examiner responds:
Examiner respectfully disagrees for at least the reasons expressed in Final Rejection 6/23/25 pg. 29-31.
Applicant argue pg. 15:
For example, on page 32 of the Office Action, the Examiner asserts that there is no nexus between the argued problem and the argued solution because there is no indication that the claimed invention actually solves this problem. The Applicant has identified that there is a technical problem relating to resource consumption and bottlenecks of computer systems; however, there is no indication that the claim actually solves this problem.
The claim does not define how many resources must or must not be used and in what timeframe and how efficiently and thus the claimed invention may actually use more resources and create more of a bottleneck. Because the claim does not explicitly solve this technical problem, a practical application is not present. Applicants disagree, especially in view of claim 1 as amended.
Amended claim 1 requires "performing, by the medical system in digital
pathology, the processing procedure for the first medical case first among a plurality of
medical cases based on the first priority value being highest among priority values of
the plurality of medical cases" where the "first priority value" corresponds to "an urgency
of an evaluation of the patient or an urgency of a therapy for the patient" and the
"medical system in digital pathology" has "limited resources."
Accordingly, claim 1 requires using the limited resources of the medical system to perform the processing procedures for more urgent medical cases ahead of those of less urgent medical cases, thereby reducing the bottleneck at the medical system and enabling medical systems to be used with fewer resources. Accordingly, Applicants respectfully submit that claim 1 is subject matter eligible as argued in the October 16, 2024 Amendment.
Examiner responds:
Examiner respectfully disagrees for at least the reasons expressed in Final Rejection 6/23/25 pg. 31. MPEP 2106.04(d)(1) and MPEP 2106.05(a) indicates that a practical application may be present where the claimed invention provides a technical solution to a technical problem. See, e.g., DDR Holdings, LLC. v. Hotels.com, L.P., 773 F.3d 1245, 1259 (Fed. Cir. 2014) (finding that claiming a website that retained the “look and feel” of a host webpage provided a technological solution to the problem of retention of website visitors by utilizing a website descriptor that emulated the “look and feel” of the host webpage, where the problem arose out of the internet and was thus a technical problem). Here, while Applicant’s argued problem is a technical problem, there is no nexus between the argued problem and the argued solution because there is no indication that the claimed invention actually solves this problem. The Applicant has identified that there is a technical problem relating to resource consumption and bottlenecks of computer systems; however, there is no indication that the claim actually solves this problem.
Further, Examiner cannot find that that a technical computer system bottleneck or technical resource consumption problem exists. Examiner notes Applicant specification para 4, 85, 121, 124, 155 describes bottlenecks as a time problem of urgent cases being blocked by non-urgent cases where a human pathologist evaluates cases. There is no indication of a computer bottleneck problem. The bottleneck problem is directed to organizing cases for human Pathologist evaluation and not a problem of a computer bottleneck. The technical computer system in processing power, time, and memory is not changed by Applicant’s invention. The computer is merely a tool to perform the abstract idea of prioritizing cases to solve the management problem of evaluating urgent cases first. Further, Applicant specification para 4, 70, 85, 86, 100, 124, describe resources as time. There is no indication of a computer resource consumption problem. The resource consumption problem is directed to organizing cases for Pathology to reduce time for urgent cases to be evaluated and is not a problem of technical computer resources being used. The technical computer system resources such as processing power, time, and memory is not changed by Applicant’s invention. The computer is merely a tool to perform the abstract idea of prioritizing cases to solve the management problem of spending less time before evaluating urgent cases.
Examiner notes a technical system of a computer having a bottleneck or resource consumption problem would be a technical problem, however, it is not apparent that problem exists as indicated by Applicant’s specification and further that problem is not solved by the claimed invention. Because the claim does not solve a technical problem, a practical application is not present.
Response to Arguments Regarding 35 U.S.C. 103 Rejection
Applicant argue pg. 16-20:
In order to establish a prima facie case of obviousness under 35 U.S.C. § 103, all of the claim limitations of the rejected claims must be described or suggested by the cited documents. Applicants respectfully submit that the cited documents do not meet this criterion because none of Chen, Godrich or Gupta describes or suggests at least, "the processing procedure corresponding to a medical system in digital pathology having limited resources, and the processing procedure including macroscopic pathology and microscopic pathology ... and performing, by the medical system in digital pathology, the processing procedure for the first medical case first among a plurality of medical cases based on the first priority value being highest among priority values of the plurality of medical cases," as recited by amended claim 1.
On pages 9-10 of the Office Action, the Examiner cites paragraphs 0003-0006, 0015, 0018 and 0049 of Chen to teach "the processing procedure corresponding to a medical system in digital pathology having limited resources ... and processing, by the medical system in digital pathology, the first medical case first among a plurality of medical cases based on the first priority value being highest among priority values of the plurality of medical cases," as previously recited by claim 1. Applicants disagree, especially in view of claim 1 as amended.
Chen describes a radiologist examining medical images and then providing a pathological report to physicians (para. 0003-0006 and 0022). Separately, Chen describes analyzing medical image data to obtain a priority score of the medical image data and sorting the medical image data based on the priority score (para. 0015-0016 and 0049).
Chen does not describe or suggest at least, "the processing procedure corresponding to a medical system in digital pathology having limited resources, and the processing procedure including macroscopic pathology and microscopic pathology ... and performing, by the medical system in digital pathology, the processing procedure for the first medical case first among a plurality of medical cases based on the first priority value being highest among priority values of the plurality of medical cases." For example, Chen is silent regarding "the processing procedure corresponding to a medical system in digital pathology ... and the processing procedure including macroscopic pathology and microscopic pathology"[emphasis added], as recited by amended claim 1. Instead, Chen refers to a radiologist that provides a pathological report by analyzing radiological images (see, for example, paragraph 0022 of Chen). Chen does not describe "macroscopic pathology" or "microscopic pathology" which cannot be performed through Chen's analysis of radiological images.
Also, Chen is silent regarding "performing, by the medical system in digital pathology, the processing procedure [including macroscopic pathology and microscopic pathology]for the first medical case first among a plurality of medical cases based on the first priority value being highest among priority values of the plurality of medical cases"[emphasis added], as recited by amended claim 1. Instead, Chen merely describes sorting medical image data based on the priority score. […]
Examiner responds:
Chen para 3-6 teaches queuing systems used to help manage high volume of medical images due to time resources being limited. Para 3 teaches pathology reports. Chen para 46 explicitly teaches “In some embodiments, the image analysis module 123 may include a plurality of image analyzers. Each image analyzer is designed to perform calculation with respect to a specific modality and a specific organ. The image analyzer may be a deep learning (e.g., neural network) based algorithm, or other artificial intelligence algorithms. For example, the image analyzer may implement one or more algorithms of deep neural network, Random Forest, and Gradient boosting decision tree. The processing result of the image analyzer on the medical image data includes a diagnosis result, a related region and a priority score of the medical image. The diagnosis result refers to a related pathological analysis and the measurement of physiological index obtained based on the image. For example, the diagnosis result may be the probability of a certain disease feature represented by the image features, and may also be the size, volume, morphological analysis and tissue structure analysis of a specific organ.”
Chen does not teach microscopic pathology, however Godrich does teach microscopic pathology and it would have been obvious to one or ordinary skill in the art, before the effective filing date of the claimed invention, to modify the pathology as taught by Chen with the microscopic pathology of tissue removed from a patient as taught by Godrich. It would be beneficial for pathology images to includes microscopic pathology because there is a desire to streamline processing of pathology slides which include microscopic pathology images to streamline pathology workflow as taught by Godrich para 2-3.
Chen does not teach macroscopic pathology, however Bar-Aviv does teach macroscopic pathology, It would have been obvious to one or ordinary skill in the art, before the effective filing date of the claimed invention, to modify the pathology as taught by Chen in view of Godrich with the macroscopic pathology as taught by Bar-Aviv. It would be beneficial for pathology images to include macroscopic pathology because there is a need to improve workflow of medical images which include macroscopic pathology images as taught by Bar-Aviv para 21.
Applicant argue pg. 20-21:
"Obviousness can be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so." In re Kahn, 441 F.3d 977, 986 (Fed. Cir. 2006); MPEP 9 2143.01. "If a proposed modification would render the prior art invention being modified unsatisfactory for its intended purpose, then there is no suggestion or motivation to make the proposed modification." In re Gordon, 733 F.2d 900 (Fed. Cir. 1984); MPEP @26 2143.01. Applicants submit that the Office Action fails to establish a prima facie case of obviousness with respect to the asserted combination of Chen and Gupta at least because the Examiner's proposed modification would render Chen unsatisfactory for its intended purpose.
On page 11 of the Office Action, the Examiner asserts that it would have been obvious to one of ordinary skill in the art by the effective filing date of the present application to "modify the priority as taught by Chen with the priority corresponding to a priority of digital pathology imaging of the tissue removed from the patient as taught by Godrich" because "[i]t would be beneficial to prioritize pathology imaging to streamline pathology workflow." Applicants disagree. For example, Applicants submit that the Examiner's proposed modification would render Chen unsatisfactory for its intended purpose.
Chen describes prioritizing images for examination by a radiologist to increase the speed of diagnosis by a doctor in emergency cases (para. 0003-0005). Chen notes that such priorities are typically derived from a priority of disease conditions of patient cases as manually decided by a physician, and thus, are vulnerable to diagnosis errors (para. 0005). To address these issues, Chen describes a neural network that processes medical image data to provide a priority score reflecting a temporal emergency of a disease condition of a subject (para. 0046). As may be seen from the above, the intended purpose of Chen is to determine a more accurate priority score reflecting a temporal emergency of a disease condition of a subject.
In contrast, Godrich describes prioritizing digital pathology slides. Accordingly, the Examiner proposes to modify the neural network of Chen to provide Godrich's priority of a digital pathology slide. Applicants submit that this proposed modification would render Chen unsuitable for its intended purpose at least because Godrich's priority of a digital pathology slide is not relevant to the determination of a temporal emergency of a disease condition of a subject for the purposes of radiological diagnosis. Thus, modifying Chen's neural network to provide Godrich's priority of a digital pathology slide would result in a priority score that less accurately reflects the temporal emergency of the disease condition of the subject for the purposes of radiological diagnosis.
Examiner responds:
Examiner proposes to modify the pathology with the microscopic pathology of tissue removed from a patient. It would have been obvious to one or ordinary skill in the art, before the effective filing date of the claimed invention, to modify the pathology as taught by Chen with the microscopic pathology of tissue removed from a patient as taught by Godrich. It would be beneficial for pathology images to includes microscopic pathology because there is a desire to streamline processing of pathology slides which include microscopic pathology images to streamline pathology workflow as taught by Godrich para 2-3.
Applicant argues pg. 22
Additionally, Applicants submit that the Office Action fails to establish a prima facie case of obviousness with respect to the asserted combination of Chen and Gupta at least because the Examiner's proposed modification would render Chen unsatisfactory for its intended purpose for at least the reasons contained on pages 26- 28 of the Amendment filed on September 23, 2025 and incorporated herein by reference. On page 45 of the Office Action, in response to these reasons, the Examiner asserts that
The functionalities in Chen and in view of Godrich and Gupta do not interfere with each other. Chen's neural network would operate the same even with the modification of adding resource consumption data. Examiner notes Applicant's assertion regarding "Gupta's number of executing servers required to execute a series of instructions is not relevant to the determination of a temporal emergency of a disease condition of a subject" would result in the weight of this new data in the network as being minimized during the training of the neural network if the assertion were true. Applicants disagree. […]
A person having ordinary skill in the art by the effective filing date of the present application would have no reason to modify the neural network of Chen to provide the priority score by inputting Gupta's number of executing servers required to execute a series of instructions (the Examiner's proposed modification) given that this input data would be ignored by Chen's neural network and would not influence the priority score provided by Chen's neural network. There is no teaching, suggestion or motivation to combine Chen with Gupta as asserted by the Examiner.
Therefore, the Office Action fails to establish a prima facie case of obviousness with respect to the Examiner's asserted combination of Chen and Godrich.
Examiner responds:
Chen teaches prioritization of cases using trained functions. Gupta teaches using resource estimation as a parameter of machine learning in prioritization. It would have been prima facie obvious to one of ordinary skill in the art at the time the invention was made to combine the noted features of Gupta with teaching of Chen in view of Godrich since the combination of the two references is merely combining prior art elements according to known methods to yield predictable results (KSR rational A); see MPEP 2143(I)(A)). It can be seen that each element claimed is present in either Gupta or Chen in view of Godrich. Determining an estimated resource consumption corresponding to a processing procedure as taught by Gupta does not change or affect the normal prioritizing of cases. Prioritizing cases would be performed the same way even with the addition of estimating resource consumption. Since the functionalities of the elements in Gupta and Chen in view of Godrich do not interfere with each other, the results of the combination would be predictable.
Examiner notes prioritizing cases as taught by Chen uses data to train on and then output a priority value and adding data would not change the functionality of the model. The model would still train and output a priority value. Incorporating additional data relating to prioritization, such as resource consumption in Gupta, would not change the way the model functions. Further, the motivation of additional data is to increase predictiveness and the supervised neural network of Chen would operate in the same way where weights would be attributed in the model according to predictive quality where consumption of resources and its relation to the target feature of priority would be determined based on the training data relationship of resource consumption to priority. Examiner notes Applicant does not claim what the relationship of resource consumption on priority value is. Gupta para 26-27 teaches that resources may be limited and analysis and reporting may require a time bound result and a machine learning model may be used to reconcile factors that influence a data pipeline prioritization scheme. A person would be motivated based on limited resources to take into account resource consumption in prioritization and the combination of additional data would not change or affect the normal prioritizing of cases. Prioritizing cases would be performed the same way, wherein a neural network takes in data and outputs priority, even with the addition of estimating resource consumption. Since the functionalities of the elements in Gupta and Chen in view of Godrich do not interfere with each other, the results of the combination would be predictable.
Conclusion
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 ANDREW KYLE TAPIA whose telephone number is (703)756-1662. The examiner can normally be reached 830 - 530.
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, Mamon Obeid can be reached at (571) 270-1813. 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.T./Examiner, Art Unit 3687
/MAMON OBEID/Supervisory Patent Examiner, Art Unit 3687