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 .
Response to Amendment
The amendment of 02/02/2026 has been entered and fully considered by the examiner. Claims 1, 3, 12, and 16 have been amended. Claims 2 and 10 have been canceled. Claims 1, 3-9 and 11-16 are currently pending in the application with claims 1 and 16 being independent.
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.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 3, 7-9, 11 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Hare et al. (U.S. Publication No. 2023/0326604) hereinafter “Hare” in view of Ellinor, et al. (U.S. 2025/0120676) hereinafter “Ellinor” and Sudhakaran et al. (“Gate-shift networks for video action recognition”, IEEE. 2020) hereinafter “Sudhakaran”.
Regarding claim 1, Hare discloses a method for analysis of echocardiograms for determining health of a human heart, [see abstract of Hare and FIG. 3C] comprising:
receiving a video segment based on an echocardiogram; [see FIG. 3C and [0082] and [0085]; the A4C cardiograms are received by the CNN trained model]
Training, from an ejection fraction training set; [see [0062] of Hare]
comparing [see [0055] comparing the echo to the prior similar-looking hearts] the video segment to a model of echocardiograms, the model trained using labels a likelihood of hypertrophic cardiomyopathy (HCM); and [see [0084] and FIG. 3C; the CNN is the trained model which is trained to detect HCM]
rendering an indication of a presence of HCM and. [see [0088] of Hara]
Hare does not expressly disclose that the model is trained using labels for a sufficiency of an ejection fraction and rendering an indication of an insufficient ejection fraction. Hare further fails to disclose receiving as a result of the comparison, an indication of a deficient ejection fraction depicted by the video segment, wherein the insufficient ejection fraction is computed based on a binary correspondence with model entries labeled for insufficient ejection fraction. Hare further fails to disclose that the model used is a gate shift network (GSN) for binary classification of at least the EF,
In another embodiment, Hare discloses that the model is trained using labels for a sufficiency of an ejection fraction (EF) and rendering an indication of an insufficient ejection fraction. [see [0055] the hearts of patients are compared with similar looking hearts and reduced ejection fraction is classified]
Ellinor, directed toward cardiac diagnosis by deep learning using echocardiogram videos [see abstract of Ellinor] further discloses receiving as a result of the comparison, an indication of a deficient ejection fraction depicted by the video segment, [see [0112]; the left ventricle structure and function including EF is classified suing echocardiogram videos and the trained model] wherein the insufficient ejection fraction is computed based on a binary correspondence with model entries labeled for insufficient ejection fraction. [see [0110], [and [0140]-[0141] disclosing binary classification of various qualities of the heart including classification of the mitral valve and image quality. It would have been obvious to a person of ordinary skill in the art to apply the same binary classification to the ejection fraction classification as well since doing so would have been applying a known technique of binary classification of the heart videos to an area ready for improvement of insufficient ejection fraction (KSR rationale C)]
Sudhakaran, directed towards a GSN network use for video recognition [see abstract of Sudhakaran] further discloses that the model using for classification of videos is a GSN model [see page 1106, left column, section under “datasets” disclosing using the model on videos to classify them]
It would have been obvious to a person of ordinary skill level in the art at the time of the filing of the invention to modify the method of Hare further such that the model is trained using labels for a sufficiency of an ejection fraction and rendering an indication of an insufficient ejection fraction according to the teachings of Hare in order to recognize the possibility of a heart failure as a result of reduced ejection fraction (HFrEF) based on data of the heart. [see [0055] of Hare]
It would have been obvious to a person of ordinary skill level in the art at the time of the filing of the invention to modify the method of Hare further such that receiving as a result of the comparison, an indication of a deficient ejection fraction depicted by the video segment, wherein the insufficient ejection fraction is computed based on a binary correspondence with model entries labeled for insufficient ejection fraction according to the teachings of Elinor in order to present an efficient binary classification tool for heart diagnoses [see [0140] of Ellinor]
It would have been obvious to a person of ordinary skill level in the art at the time of the filing of the invention to modify the method of Hare further such the model used is a gate shift network (GSN) for binary classification of at least the EF according to the teachings of Sudhakaran in order to in order to use a high performing spatio temporal feature extractor with minimal overheard as the classification model. [see page 1104, right column, section under “Gate Shift Networks”.]
Regarding claim 3, Hare in view of Ellinor and Sudhakaran discloses all the limitations of claim 1 [see rejection of claim 1 above]
Ellinor further discloses computing a healthy heart using a database split based on the ejection fraction. [see [0112]; the left ventricle structure and function including EF is classified suing echocardiogram videos and the trained model; also see [0110], [and [0140]-[0141] disclosing binary classification of various qualities of the heart including classification of the mitral valve and image quality. It would have been obvious to a person of ordinary skill in the art to apply the same binary classification to the ejection fraction classification as well since doing so would have been applying a known technique of binary classification of the heart videos to an area ready for improvement of insufficient ejection fraction (KSR rationale C)]
It would have been obvious to a person of ordinary skill level in the art at the time of the filing of the invention to modify the method of Hare further such that receiving as a result of the comparison, an indication of a deficient ejection fraction depicted by the video segment, wherein the insufficient ejection fraction is computed based on a binary correspondence with model entries labeled for insufficient ejection fraction according to the teachings of Elinor in order to present an efficient binary classification tool for heart diagnoses [see [0140] of Ellinor]
Regarding claim 7, Hare in view of Ellinor and Sudhakaran discloses all the limitations of claim 1 [see rejection of claim 1 above]
Hare further discloses that the corpus of echocardiograms define, for each video segment, features indicative of a covariate shift, [see FIG. 16A and [0143]; the graph shows the values various parameters and their departure from mean value] a presence of black regions, [see FIGs. 5A-6D; the images are a B-mode ultrasound image and therefore can show any black regions] an opacification, [see FIGs. 5A-6D; the images are a B-mode ultrasound image and therefore can show any opacification] and unclear heart linings. [see FIGs. 5A-6D; the images are a B-mode ultrasound image and therefore can show any unclear heart linings]
Regarding claim 8, Hare in view of Ellinor and Sudhakaran discloses all the limitations of claim 1 [see rejection of claim 1 above]
Hare further discloses that the corpus of echocardiograms define, for each video segment, a degree of clearness of heart linings [see FIGs. 5A-6D; the images are a B-mode ultrasound image and therefore can show the degree of clearness of heart linings using gray-scale in the image], a contrast, [see FIGs. 5A-6D; the images are a B-mode ultrasound image and therefore can show the contrast in the image] and a contraction/relaxation of the heart. [see FIGs. 5A-6D; the images are a B-mode ultrasound image and therefore can show the movement of the heart during contraction and relaxation of the heart]
Regarding claim 9, Hare in view of Ellinor and Sudhakaran discloses all the limitations of claim 1 [see rejection of claim 1 above]
Hare further discloses that the corpus of echocardiograms further include features indicative of a heart wall thickness and a cavity size. [see FIGs. 5A-6D showing the chamber sizes and diameters of the heart including the wall thickness size]
Regarding claim 11, Hare in view of Ellinor and Sudhakaran discloses all the limitations of claim 1 [see rejection of claim 1 above]
Hare further discloses that training, from a hypertrophic cardiomyopathy (HCM) training set, a hypertrophic cardiomyopathy model; [see [0084] and FIG. 3C; the CNN is the trained model which is trained to detect HCM] comparing the video segment to the HCM model; [see [0055] comparing the echo to the prior similar-looking hearts] receiving an indication of a presence of HCM depicted by the video segment; and [see [0084] and FIG. 3C; the CNN is the trained model which is trained to detect HCM] and rendering the received indication for use in diagnosis. [see FIG. 3E and [0089] of Hare]
Regarding claim 16 Hare discloses a computer program embodying program code on a non-transitory computer readable storage medium that,[see [0145] of Hare] when executed by a processor, performs steps for implementing a method for analysis of echocardiograms for determining health of a human heart, [see abstract of Hare and FIG. 3C] the method comprising:
receiving a video segment based on an echocardiogram; [see FIG. 3C and [0082] and [0085]; the A4C cardiograms are received by the CNN trained model]
comparing [see [0055] comparing the echo to the prior similar-looking hearts] the video segment to a model of echocardiograms, the model trained using labels for a likelihood of hypertrophic cardiomyopathy (HCM); [see [0084] and FIG. 3C; the CNN is the trained model which is trained to detect HCM]
and rendering an indication of a presence of HCM. [see [0088] of Hara]
Hare does not expressly disclose that the model is trained using labels for a sufficiency of an ejection fraction and rendering an indication of an insufficient ejection fraction. Hare further fails to disclose receiving as a result of the comparison, an indication of a deficient ejection fraction depicted by the video segment, wherein the insufficient ejection fraction is computed based on a binary correspondence with model entries labeled for insufficient ejection fraction. Hare further fails to disclose that the model used is a gate shift network (GSN) for binary classification of at least the EF,
In another embodiment, Hare discloses that the model is trained using labels for a sufficiency of an ejection fraction (EF) and rendering an indication of an insufficient ejection fraction. [see [0055] the hearts of patients are compared with similar looking hearts and reduced ejection fraction is classified]
Ellinor, directed toward cardiac diagnosis by deep learning using echocardiogram videos [see abstract of Ellinor] further discloses receiving as a result of the comparison, an indication of a deficient ejection fraction depicted by the video segment, [see [0112]; the left ventricle structure and function including EF is classified suing echocardiogram videos and the trained model] wherein the insufficient ejection fraction is computed based on a binary correspondence with model entries labeled for insufficient ejection fraction. [see [0110], [and [0140]-[0141] disclosing binary classification of various qualities of the heart including classification of the mitral valve and image quality. It would have been obvious to a person of ordinary skill in the art to apply the same binary classification to the ejection fraction classification as well since doing so would have been applying a known technique of binary classification of the heart videos to an area ready for improvement of insufficient ejection fraction (KSR rationale C)]
Sudhakaran, directed towards a GSN network use for video recognition [see abstract of Sudhakaran] further discloses that the model using for classification of videos is a GSN model [see page 1106, left column, section under “datasets” disclosing using the model on videos to classify them]
It would have been obvious to a person of ordinary skill level in the art at the time of the filing of the invention to modify the method of Hare further such that the model is trained using labels for a sufficiency of an ejection fraction and rendering an indication of an insufficient ejection fraction according to the teachings of Hare in order to recognize the possibility of a heart failure as a result of reduced ejection fraction (HFrEF) based on data of the heart. [see [0055] of Hare]
It would have been obvious to a person of ordinary skill level in the art at the time of the filing of the invention to modify the method of Hare further such that receiving as a result of the comparison, an indication of a deficient ejection fraction depicted by the video segment, wherein the insufficient ejection fraction is computed based on a binary correspondence with model entries labeled for insufficient ejection fraction according to the teachings of Elinor in order to present an efficient binary classification tool for heart diagnoses [see [0140] of Ellinor]
It would have been obvious to a person of ordinary skill level in the art at the time of the filing of the invention to modify the method of Hare further such the model used is a gate shift network (GSN) for binary classification of at least the EF according to the teachings of Sudhakaran in order to in order to use a high performing spatio temporal feature extractor with minimal overheard as the classification model. [see page 1104, right column, section under “Gate Shift Networks”.]
Claims 5, 6, 12, 13, and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Hare et al. (U.S. Publication No. 2023/0326604) hereinafter “Hare” in view of Ellinor, et al. (U.S. 2025/0120676) hereinafter “Ellinor” and Sudhakaran et al. (“Gate-shift networks for video action recognition”, IEEE. 2020) hereinafter “Sudhakaran” as applied to claim 1 above and further in view of Ouyang et al. (U.S. Publication No. 2021/0304410) hereinafter “Ouyang”.
Regarding claim 5, Hare in view of Ellinor and Sudhakaran discloses all the limitations of claim 1 [see rejection of claim 1 above]
Hare in view of Ellinor and Sudhakaran does not expressly disclose training the model of echocardiograms, training further comprising a corpus of echocardiograms video clips, each clip at least three seconds in duration and capturing at least 5 heartbeats at between 10-50 frames per second.
Ouyang, directed towards using AI to diagnose cardiovascular issues [see abstract of Ouyang] further discloses that training the model of echocardiograms, training further comprising a corpus of echocardiograms video clips, each clip at least three seconds in duration and [see [0058]; 5 or 10 beats are included in each video which is at least 3 seconds based on average of 60 beats/min indicating at least 3 beats in each 5 second long video] capturing at least 5 heartbeats [see [0058] disclosing 5 or 10 beats long videos] at between 10-50 frames per second. [see [0042] of Ouyang disclosing 30 frames per second]
It would have been obvious to a person of ordinary skill level in the art at the time of the filing of the invention to modify the method of Hare in view of Ellinor and Sudhakaran further such that training the model of echocardiograms, training further comprising a corpus of echocardiograms video clips, each clip at least three seconds in duration and capturing at least 5 heartbeats at between 10-50 frames per second according to the teachings of Ouyang in order to have a longer window for analysis of the functioning of the heart [see [0070] of Ouyang]
Regarding claim 6, Hare in view of Ellinor and Sudhakaran and Ouyang further discloses all the limitations of claim 5 [see rejection of claim 5 above]
Ouyang further discloses that the corpus of echocardiograms further includes labels indicative of the actual ejection fraction,[see [0041] of Ouyang and Table 4] end systolic volume (ESV), [see table 4] end diastolic volume (EDV) values [see table 4] , frame height and width,[see FIG. 2D] frames Per Second (FPS) [see [0042] of Ouyang disclosing 30 frames per second] and number of frames.[see [0051] of Ouyang]
It would have been obvious to a person of ordinary skill level in the art at the time of the filing of the invention to modify the method of Hare in view of Ellinor and Sudhakaran and Ouyang further such that the corpus of echocardiograms further include labels indicative of the actual ejection fraction, end systolic volume (ESV), end diastolic volume (EDV) values, frame height and width, frames Per Second (FPS) and number of frames according to the teachings of Ouyang in order to provide detailed information regarding the videos to the operator.
Regarding claim 12, Hare in view of Ellinor and Sudhakaran and Ouyang discloses all the limitations of claim 1 [see rejection of claim 1 above]
Ouyang further discloses that the ejection fraction model implements a video action recognition (VAR) neural network. [see [0039] and [0041] of Ouyang]
It would have been obvious to a person of ordinary skill level in the art at the time of the filing of the invention to modify the method of Hare in view of Ellinor and Sudhakaran and Ouyang further such that the ejection fraction model implements a video action recognition (VAR) neural network according to the teachings of Ouyang in order to provide the state-of-art assessment of cardiac function using the highly efficient VAR method [see [0039] of Ouyang]
Regarding claim 13, Hare in view of Ellinor and Sudhakaran discloses all the limitations of claim 11 [see rejection of claim 11 above]
Ouyang further discloses that the ejection fraction model implements a video action recognition (VAR) neural network. [see [0039] and [0041] of Ouyang]
It would have been obvious to a person of ordinary skill level in the art at the time of the filing of the invention to modify the method of Hare in view of Ellinor and Sudhakaran as modified by Ouyang further such that the ejection fraction model implements a video action recognition (VAR) neural network according to the teachings of Ouyang in order to provide the state-of-art assessment of cardiac function using the highly efficient VAR method [see [0039] of Ouyang]
Regarding claim 15, Hare in view of Ellinor and Sudhakaran discloses all the limitations of claim 14 [see rejection of claim 14 above]
Hare further discloses that the HCM model further analyzes spatiotemporal classifiers for a majority averaging for predicting a presence of HCM. [see [0039] of Ouyang]
It would have been obvious to a person of ordinary skill level in the art at the time of the filing of the invention to modify the method of Hare in view of Ellinor and Sudhakaran and Ouyang further such that the HCM model further analyzes spatiotemporal classifiers for a majority averaging for predicting a presence of HCM according to the teachings of Ouyang in order to provide the state-of-art assessment of cardiac function using the highly efficient VAR method [see [0039] of Ouyang]
Claims 4 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Hare et al. (U.S. Publication No. 2023/0326604) hereinafter “Hare” in view of Ellinor, et al. (U.S. 2025/0120676) hereinafter “Ellinor” and Sudhakaran et al. (“Gate-shift networks for video action recognition”, IEEE. 2020) hereinafter “Sudhakaran” and Ouyang et al. (U.S. Publication No. 2021/0304410) hereinafter “Ouyang” as applied to claim 13 above and further in view of Na et al. (U.S. Publication No. 2021/0357647) hereinafter “Na”.
Regarding claims 4 and 14, Hare in view of Ellinor , Sudhakaran and Ouyang discloses all the limitations of claim 1 and 13 [see rejection of claims 1 and 13 above]
Hare in view of Ellinor and Sudhakaran and Ouyang does not disclose that the HCM model performs analysis using a first slow arm directed at spatial characteristics of the video segment, and a second fast arm directed at temporal characteristics.
Na, directed towards video-based classification methods [see abstract of Na] further discloses that the model performs analysis using a first slow arm directed at spatial characteristics of the video segment, and a second fast arm directed at temporal characteristics. [see abstract and [0029] of Na]
It would have been obvious to a person of ordinary skill level in the art at the time of the filing of the invention to modify the method of Hare in view of Ellinor and Sudhakaran and Ouyang further such that HCM model performs analysis using a first slow arm directed at spatial characteristics of the video segment, and a second fast arm directed at temporal characteristics according to the teachings of Na in order to reduce the training time and consumption of computation resources under this mixed 2D-3D network architecture. [see [0002] of Na]
Response to Arguments
Applicant’s arguments, see remarks filed 02/02/2026 with respect to the rejection(s) of claim(s) 1 and 16 under U.S.C. 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of
Ellinor, et al. (U.S. 2025/0120676) hereinafter “Ellinor”
Sudhakaran et al. (“Gate-shift networks for video action recognition”, IEEE. 2020) hereinafter “Sudhakaran”
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MARJAN - SABOKTAKIN whose telephone number is (303)297-4278. The examiner can normally be reached M-F 9 am-5pm CT.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Michael Carey can be reached at (571) 270-7235. 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.
/MARJAN SABOKTAKIN/Examiner, Art Unit 3797
/MICHAEL J CAREY/Supervisory Patent Examiner, Art Unit 3795
Prosecution Insights