DETAILED ACTION
Response to Arguments
Applicant's arguments filed with respect to claims 1-10 have been fully considered but are moot in view of the new ground(s) of rejection. The rejections are necessitated due to significant claim amendments.
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 1-10 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. When reviewing independent claim 1, and based upon consideration of all of the relevant factors with respect to the claim as a whole, claims 1-10 are held to claim an abstract idea without reciting elements that amount to significantly more than the abstract idea and is/are therefore rejected as ineligible subject matter under 35 U.S.C. 101.
The Examiner will analyze Claim 1, and similar rationale applies to independent Claims 9 and 10.
The rationale, under MPEP § 2106, for this finding is explained below. The claimed invention (1) must be directed to one of the four statutory categories, and (2) must not be wholly directed to subject matter encompassing a judicially recognized exception, as defined below. The following two step analysis is used to evaluate these criteria.
Step 1: Is the claim directed to one of the four patent-eligible subject matter categories: process, machine, manufacture, or composition of matter?
When examining the claim under 35 U.S.C. 101, the Examiner interprets that the claims is related to a machine since the claim is directed to an apparatus that generate a performance of image analysis model.
Step 2a, Prong 1: Does the claim wholly embrace a judicially recognized exception, which includes laws of nature, physical phenomena, and abstract ideas, or is it a particular practical application of a judicial exception?
The Examiner interprets that the judicial exception applies since Claim 1 limitation of wherein the image analysis model is configured to perform image analysis [observation, evaluation, and judgment] on the plurality of ultrasound images by executing at least one of identifying a tissue cross section, performing a measurement on tissue, or detecting a lesion part [mathematical concept or mental process]; calculate a score indicating performance of the image analysis model using the log [mathematical concept]; generate a log including information indicating execution of a plurality of analysis operations by the image analysis model, and information indicating an adoption or a non- adoption by an examiner with respect to the plurality of analysis results [A mental process. A person (reviewer) could record that an analysis occurred and mark its result accepted/rejected or adoption/non-adoption. Also, it’s nothing more than a computerized collection and recordkeeping associated with the performance evaluation] are directed to an abstract.
If/when the claim recites a judicial exception (i.e., an abstract idea enumerated in MPEP § 2106.04(a), a law of nature, or a natural phenomenon), the claim requires further analysis in Prong Two.
Step 2a, Prong 2: Does the claim recite additional elements that integrate the judicial exception into a practical application?
The additional claim limitations “an ultrasound probe, configured to transmit ultrasound waves and receive reflected waves to acquire a plurality of ultrasound images” and “a processor, configured to: input the plurality of ultrasound images acquired by the ultrasound probe into an image analysis model trained in advance through machine learning and receive a plurality of analysis results [output] outputted by the image analysis model” and “cause different information to be provided [output] to the examiner based on the score, wherein the different information includes at least one of information representing a decrease in the performance of the image analysis model, information for prompting a determination of the adoption or the non-adoption of a current analysis result, or information for prompting a subsequent examination operation of the ultrasound diagnostic apparatus”. Obtaining an image and inputting the image are mere data gathering and presenting an output recited high level of generality and thus are insignificant extra-solution activity.
Therefore, the claim, as a whole, does not integrate the judicial exception into a practical application.
Step 2b: If a judicial exception into a practical application is not recited in the claim, the Examiner must interpret if the claim recites additional elements that amount to significantly more than the judicial exception. No.
The Examiner finds that Claims 2-8 does not state significantly more since the claim only recites additional steps for analyzing model performance using machine learning model.
Thus, claims 1-10 recite the same abstract idea and therefore are not drawn to the eligible subject matter as they are directed to the abstract idea without significantly more.
Therefore, all claims are rejected under 35 U.S.C. 101.
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 1, 4, 9 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Rao et al. (Pub. No. US 2019/0148011) in view of Sorenson et al. (Pub. No. US 2018/0137244).
Regarding claim 1, Rao et al. (Pub. No. US 2019/0148011) teaches an ultrasound probe (transducer 14), configured to transmit ultrasound waves (transmits acoustic energy) and receive reflected waves (receives echoes) to acquire a plurality of ultrasound images (frames or images) [Para. 87 “For scanning with ultrasound, the transducer 14 transmits acoustic energy and receives echoes.”; para. 22 “The ultrasound scanner generates ultrasound images of the patient. The images are generated by scanning the patient”; and para. 39 “The ultrasound scanner or an image processor applies computer-assisted detection to each, one, a subset, or all the frames or images of the sequence acquired by the scanning. Any now known or later developed computer-assisted detection may be applied”]; and a processor, configured to: input the plurality (sequence) of ultrasound images (frames) acquired by the ultrasound probe (transducer 14) into an image analysis model (machine learnt network) trained in advance through machine learning (machine-learning) [Para. 39 “The ultrasound scanner or an image processor applies computer-assisted detection to each, one, a subset, or all the frames or images of the sequence acquired by the scanning.”; , 46 “The machine-learnt network, with or without deep learning, is trained to associate the categorical labels (output identity and/or segmentation) to the extracted values of one or more features. The machine-learning uses training data with ground truth, such as values for features extracted from frames of data for patients with known objects and/or segmentations, to learn to detect based on the input feature vector. The resulting machine-learnt network is a matrix for inputs, weighting, and combination to output the detection. Using the matrix or matrices, the image processor inputs the extracted values for features and outputs the detection.”; 50 “one detector is trained to both classify and segment.”, and Para. 60 “Where deep learning is used, the segmentor extracts the values for the features.”]; and receive a plurality of analysis results (detection) outputted (outputs) by the image analysis model (machine-learnt network) [Para. 46 “The machine-learnt network, with or without deep learning, is trained to associate the categorical labels (output identity and/or segmentation) to the extracted values of one or more features”; para. 39 “The ultrasound scanner or an image processor applies computer-assisted detection to each, one, a subset, or all the frames or images of the sequence acquired by the scanning. Any now known or later developed computer-assisted detection may be applied”, and 64 “Once anatomy has been successfully identified and/or segmented, the identity or location information is utilized to improve the imaging workflow for the user by avoiding at least one user interaction with the ultrasound scanner”]; wherein the image analysis model (machine-learnt network) is configured to (is trained to) perform image analysis (applies computer-assisted detection) on the plurality (sequence) of ultrasound images (frames) by executing at least one of identifying a tissue cross section, performing a measurement on tissue, or detecting (identifying) a lesion part (session or tumor) [Para. 46, 39 and 74]; information (indication) indicating (indicates) an adoption or a non-adoption (weather the detection is correct) by an examiner (physician/user) with respect to the plurality of analysis results (detection) [Para. 48].
however, Rao doesn’t explicitly teach generate a log including information indicating execution of a plurality of analysis operations by the image analysis model.
Sorenson teaches generate a log including information indicating execution of a plurality of analysis operations by the image analysis model [Para. 93 “Tracking module 211 is configured to keep track of which image processing engines are utilized for which medical studies or by which users, on which image cohorts and clinical content cohorts, which resulted in which indexed user data, then generating tracking data 221 (also referred to as engine data) stored in persistent storage device 202, also called a database or databases”; Para. 95; Para. 32 “The target findings are either held in blind confidence to see if the physician agrees independently, or the findings are presented within the physician interpretation process to evoke responses, and any feedback, adjustments, agreement or disagreement are captured and utilized as performance feedback for the engines which created the suggestions.”].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Rao’s ultrasound detection-feedback processing by incorporating Sorenson’s generation of a log (engine data) containing both executed analysis operations and examiner adoption/non-adoption (agreement or disagreement), recording each detector execution together with its corresponding examiner feedback. This modification improves Rao by preserving the association between executed analyses and reviewed outcomes for subsequent performance evaluation, using detection and review information already available to the system.
Rao doesn’t explicitly teach calculating a score indicating performance of the image analysis model using the log.
However, Sorenson teach calculating (perform an analysis) a score (engine ratings) indicating performance (accuracy) of the image analysis model (engines) using (based on) the log (engine data) [Para. 33 and 96].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Rao’s ultrasound image-analysis processing by incorporating Sorenson’s analysis of the log (engine data) to calculate a score (engine ratings) indicating model performance (accuracy), supplying the stored execution and examiner feedback records to that calculation. This modification improves Rao by converting individual reviewed outcomes into a model-performance assessment suitable for communicating the detector’s observed reliability to its examiner.
Rao teaches cause different information (a list of measurements) to be provided to the examiner [Para. 75].
However, Sorenson teaches cause different information (which COPD e-suites have the best findings detection rates) to be provided (providing) to the examiner (physicians) based on the score (engine ratings) [Para. 91 and 96].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Rao’s examination interface by incorporating Sorenson’s score-dependent presentation of model performance information, displaying the current score (engine ratings) together with Rao’s different information (a list of measurements) for the subsequent examination operation (next act). This medication improves Rao by placing the model’s observed performance at the point where the examiner (user) selects the subsequent examination operation (next act), without requiring consultation of a separate model rating interface.
Rao further teaches wherein the different information (a list of measurements) includes at least one of information representing a decrease in the performance of the image analysis model, or information for prompting (for selection by the user) a subsequent examination operation (next act) of the ultrasound diagnostic apparatus (ultrasound scanner 10) [Para. 68 “The next act may be measurement”; Para. 75 “Parts of steps may be automated, such as showing a list of measurements that could be performed on the user interface for selection by the user”, and para. 82 “The ultrasound scanner 10 is a medical diagnostic ultrasound imaging system”].
Regarding claim 4, Rao teaches Once a physician review detected objects and indicates whether the detection is correct, the indication and sample may be later used as training data. However, Rao doesn’t explicitly teach a log whose adoption/non-adoption records are all correction or rejection records.
However, Sorenson teaches wherein each adoption or non-adoption record is a non-adoption record (manipulated finding) representing correction (adjust) or rejection of the analysis result (initial findings) by the examiner (user 81) [Para. 157, 159, and 163].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Rao’s examination interface by incorporating Sorenson’s score-dependent presentation of model performance information, displaying the current score (engine ratings) together with Rao’s different information (a list of measurements) for the subsequent examination operation (next act). This medication improves Rao by placing the model’s observed performance at the point where the examiner (user) selects the subsequent examination operation (next act), without requiring consultation of a separate model rating interface.
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Rao et al. (Pub. No. US 2019/0148011) in view of Sorenson et al. (Pub. No. US 2018/0137244) further in view of Wenchel et al. (Pub. No. US 2021/0174258).
Regarding claim 2, Rao teaches wherein the processor is configured to generate the different information (a list of measurements) to be provided (showing) to the examiner (user) [Para. 75].
However, Rao in view of Sorenson doesn’t explicitly teach about the threshold.
Wenchel teaches wherein the processor is configured to generate the different information (alert) to be provided (email) to the examiner (user) in a case where (if) the score (accuracy) falls below a set threshold value (90%) [Para. 70 “IF accuracy falls below 90% for T periods THEN ACT take model offline AND email user with high priority (e.g., for a straightforward threshold case, with a true/gold standard label)”].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Rao’s examiner information function, using the performance assessment supplied by Sorenson, by incorporating Wenchel’s generation of an alert when model accuracy falls below a set threshold (90%). This medication improves Rao by providing an explicit warning when the detector’s observed performance becomes inadequate, using a direct numerical comparison and an existing examiner-output interface.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Rao et al. (Pub. No. US 2019/0148011) in view of Sorenson et al. (Pub. No. US 2018/0137244) further in view of Sorenson et al. (Pub No. US 2022/0238232 hereinafter “Sore”).
Regarding claim 3, Rao in view of Sorenson doesn’t explicitly teach the claim limitation.
However, Sore teaches wherein the log includes a first record column consisting of a plurality of analysis operation (operations of the first engine) records and a second record column consisting of a plurality of adoption or non-adoption (validated or invalidated) records [Para. 110, and 117-123]; wherein the processor is configured to calculate an adoption rate as the score based on the number of analysis operations (operations of first engine) within a certain period specified from the first record column and the number of adoptions (validated) within the certain period specified from the second record column [Para. 25, 30, 120, 126 and 140].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Rao diagnostic image analysis performance monitoring system, modified by Sorenson, by incorporating Sore tracking-table arrangement so that analysis-operation records (operations of the first engine) are maintained in a first record column, corresponding acceptable/unacceptable records (validated or invalidated) are maintained in a second record column, and an acceptance rate score is calculated for selected period from the number of validated results relative to the number of analysis operations. This medication improves Rao by directly correlating each analysis operation with its examiner disposition and converting the correlated records into an objective.
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Rao et al. (Pub. No. US 2019/0148011) in view of Sorenson et al. (Pub. No. US 2018/0137244) further in view of Itou et al. (Pub. No. US 2013/0011298).
Regarding claim 5, Rao in view of Sorenson doesn’t explicitly teach the claim limitation.
However, Itou teaches wherein each analysis operation (sample analysis) record includes information representing a time (the measurement date and the measurement time) at which the analysis operation is executed (at which a sample analysis ends) [Para. 36, 55, fig. 2, 3 and related description]; and each adoption (approval) or non-adoption record (record of the approved analysis result) includes information representing a time at which the adoption or the non-adoption of the analysis result is input (the icon C405) [para. 103].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Rao’s diagnostic apparatus by incorporating Itou’s teaching of storing the execution time (date and time) for each analysis operation, specifically by configuring Rao’s record generation logic to include the analysis-completion date and time in each corresponding analysis-operation record (Itou para. 55). This medication improves Rao’s apparatus by preserving the temporal association between each analysis operation, thereby supporting chronological review and time-based retrieval of the analysis history-the proposed benefit of applying Itou’s timestamp-based record retrieval to Rao’s records.
Allowable Subject Matter
Claims 6-8 are objected to as being dependent upon a rejected base claim, but would be allowable if 101 rejection is overcome and if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
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 extension fee 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 date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SOLOMON G BEZUAYEHU whose telephone number is (571)270-7452. The examiner can normally be reached on Monday-Friday 10 AM-8 PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Oneal Mistry can be reached on 313-446-4912. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 888-786-0101 (IN USA OR CANADA) or 571-272-4000.
/SOLOMON G BEZUAYEHU/
Primary Examiner, Art Unit 2666
Prosecution Insights