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 .
Information Disclosure Statement
The information disclosure statement (IDS) was submitted on 3/03/2025. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to abstract ideas of “mental processes” or “concepts relating to data comparisons that can be performed mentally or are analogous to human mental work” without significantly more.
Analyses of the subject matter eligibility tests are performed for each of the independent claims and associated dependent claims below.
Regarding independent claim 1, the claim recites:
The limitation of “extracting, via the processing circuitry, first frames corresponding to at least one echocardiogram view from the echocardiogram data” is considered to be an abstract idea of a mental process and concept relating to data comparisons that can be performed mentally or are analogous to human mental work as a user may merely think and receive within the mind about the frames that correspond to a particular echocardiogram view. The limitation of “extracting, via the processing circuitry, second frames corresponding to ventricular systole from the first frames corresponding to the at least one echocardiogram view” is considered to be an abstract idea of a mental process and concept relating to data comparisons that can be performed mentally or are analogous to human mental work as a user may merely think and receive within the mind about the frames that correspond to ventricular systole from the first frames. The limitation of “determining, via at least one machine learning model executed by the processing circuitry, an RHD risk score based on the second frames corresponding to ventricular systole” is considered to be an abstract idea of a mental process and concept relating to data comparisons that can be performed mentally or are analogous to human mental work as a user may merely think and receive within the mind about an RHD risk score based upon the second frames observed. Therefore, the claim is directed to an abstract idea and a judicial exception.
Step 2A Prong 2 Analysis (Claim 1): This judicial exception is not integrated into a practical application because it does not recite any elements that integrate the abstract idea into a practical application such as improving the operation of the diagnostic device, or effecting a particular treatment or prophylaxis for a disease or medical condition. The claims do not recite any features of components that integrates the judicial exception into a practical application because the additional recited elements of “receiving, via processing circuitry, echocardiogram data” form extra-solution activity of mere data gathering that is executed on a generic computer of processing circuitry. Therefore, all of these claimed elements are not sufficient to improve the functioning of a diagnostic device or form of technology. Furthermore, while directed to activity for medical diagnostics, the claimed steps do not effect a particular treatment or prophylaxis for a disease or medical condition as it is only claiming diagnostic measurement steps and not altering a particular treatment in any way.
Step 2B Analysis (Claim 1): The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional recited elements of “receiving, via processing circuitry, echocardiogram data” form extra-solution activity of mere data gathering that is executed on a generic computer of processing circuitry. The limitations do not include improvements to the functioning of a computer or to any other technology or technical field, and the elements of the claim further do not effect a particular treatment or prophylaxis for a disease or medical condition. Furthermore, there are no claimed features that provide elements to identify improvements to general computing technologies based on the claimed features. As discussed above, limitations form insignificantly extra-solution activity, and link the judicial exception to generic medical diagnostics. Therefore the additional elements do not amount to significantly more.
Independent claims 13 and 20 include similar features to claim 1 and are similarly rejected.
Dependent claims 2 and 14 includes limitations that are directed to narrowing the form of acquired data in the extra solution activity of data gathering and therefore it does not integrate the judicial exception of the independent claim into a practical application or amount to significantly more.
Dependent claims 3 and 15 includes limitations that are directed to narrowing the mental processing abstract idea of the independent claim as a user may think within the mind about the echocardiogram view type in the extraction of a view in the acquired data. Therefore, it does not integrate the judicial exception of the independent claim into a practical application or amount to significantly more.
Dependent claim 4 includes limitations that are directed to adjusting the weight associated with various input data, which is directed to narrowing the mental processing abstract idea of the independent claim as a user may think within the mind about the second frames weighing a larger amount in the mental calculation of a risk score. Therefore, it does not integrate the judicial exception of the independent claim into a practical application or amount to significantly more.
Dependent claims 5 and 16 includes limitations that are directed to particular identifying and characterizing of features within the observed images which is directed to narrowing the mental processing abstract idea of the independent claim as a user may think within the mind about features within the images. Therefore, it does not integrate the judicial exception of the independent claim into a practical application or amount to significantly more.
Dependent claims 6 and 17 includes limitations that are directed to identifying and characterizing of features within the observed images which is directed to narrowing the mental processing abstract idea of the independent claim as a user may think within the mind about features within the images. Therefore, it does not integrate the judicial exception of the independent claim into a practical application or amount to significantly more.
Dependent claims 7 and 18 includes limitations that are directed to identifying and characterizing of features within the observed images which is directed to narrowing the mental processing abstract idea of the independent claim as a user may think within the mind about features within the images. Therefore, it does not integrate the judicial exception of the independent claim into a practical application or amount to significantly more.
Dependent claim 8 includes limitations that are directed to factors to be considered when providing a risk score which is directed to narrowing the mental processing abstract idea of the independent claim as a user may think within the mind about what elements of the gathered data to include in the mental analysis. Therefore, it does not integrate the judicial exception of the independent claim into a practical application or amount to significantly more.
Dependent claims 9 and 19 includes limitations that are directed to identifying and characterizing of features within the observed images which is directed to narrowing the mental processing abstract idea of the independent claim as a user may think within the mind about features within the images. Therefore, it does not integrate the judicial exception of the independent claim into a practical application or amount to significantly more.
Dependent claim 10 includes limitations that are directed to adjusting the weight associated with various input data, which is directed to narrowing the mental processing abstract idea of the independent claim as a user may think within the mind about the second frames weighing a larger amount in the mental calculation of a risk score. Therefore, it does not integrate the judicial exception of the independent claim into a practical application or amount to significantly more.
Dependent claim 11 includes limitations that are directed to narrowing the type of model used in the analysis. It does not integrate into a practical application or amount to significantly more because it does not differentiate the mental processing steps of the claimed invention in such a way that precludes a human from performing the steps within the mind. Therefore, it does not integrate the judicial exception of the independent claim into a practical application or amount to significantly more.
Dependent claim 12 includes limitations that are directed to narrowing the output of the mental processing abstract idea of the independent claim as a user may determine the type of RHD from observed input data. Therefore, it does not integrate the judicial exception of the independent claim into a practical application or amount to significantly more.
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 1-3, 8-9, 11, 13-15, and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Hare, II et al. (U.S. Pub. No. 20200178940) hereinafter Hare, in view of Fornwalt et al. (U.S. Pub. No. 20210150693) hereinafter Fornwalt.
Regarding claim 1, primary reference Hare teaches:
A method for detecting heart disease (HD) based on at least an echocardiogram (abstract), the method comprising:
receiving, via processing circuitry, echocardiogram data ([0033]-[0037], echocardiogram images; [0054], figure 3, “a process for performed by the echo workflow engine 12 to automatically recognize and analyze both 2D and Doppler modality echo images to perform automated measurements and the diagnosis”; [0055], echocardiogram images; [0056]; claim 1);
extracting, via the processing circuitry, first frames corresponding to at least one echocardiogram view from the echocardiogram data ([0057]-[0058], 2D images are extracted which correspond to first frames of an echocardiogram view (see classified by view type); [0059]-[0062]; figure 3);
extracting, via the processing circuitry, second frames corresponding to ventricular systole from the first frames corresponding to the at least one echocardiogram view ([0057]-[0058] and [0081], extracting of second images with annotations corresponding to systolic end points of ventricles from the 2D images corresponding to the echocardiogram view; [0059]-[0062]); and
determining, via at least one machine learning model executed by the processing circuitry, an HD risk score based on the second frames corresponding to ventricular systole ([0046]-[0047]; [0059]-[0062]; [0081]; [0091]-[0100]; [0110], determining using the echo workflow engine, which is a trained machine learning model, a prediction and prognosis of heart disease in the form of a score based upon, in part, in the second images corresponding to the systolic end points of ventricles; figures 3, 4A, and 4B).
Primary reference Hare fails to teach:
Rheumatic heart disease
However, the analogous art of Fornwalt of a method for determining a predicted risk level of a health condition for a patient (abstract) teaches:
Rheumatic heart disease ([0010], trained neural networks for echocardiographic analysis of conditions such as diagnosis of chronic rheumatic heart disease)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the machine learning model based echocardiogram analysis for heart disease method of Hare to incorporate the rheumatic heart disease diagnosis via neural network as taught by Fornwalt because technology, such as artificial intelligence and machine learning, can manage an abundance of data and ultimately provide intelligent computer assistance and precise diagnosis to physicians (Fornwalt, [0002]). By enabling diagnosis of particular conditions such as rheumatic heart disease, more accuracy in diagnostics can be obtained leading to more effective clinical interventions.
Regarding claim 2, the combined references of Hare and Fornwalt teach all of the limitations of claim 1. Primary reference Hare further teaches:
wherein the echocardiogram data includes Doppler echocardiogram data, color Doppler echocardiogram data, or B-mode ultrasound data ([0057], echocardiogram data includes doppler modality images; figure 3).
Regarding claim 3, the combined references of Hare and Fornwalt teach all of the limitations of claim 1. Primary reference Hare further teaches:
wherein the at least one echocardiogram view includes an apical 4-chamber (A4CC) view and/or a parasternal long axis (PLAXC) view ([0058], echocardiogram view includes apical 4-chamber view and parasternal long axis view).
Regarding claim 8, the combined references of Hare and Fornwalt teach all of the limitations of claim 1. Primary reference Hare further teaches:
wherein the determining the risk score (note that secondary reference Fornwalt teaches to RHD diagnostics) is based on patient demographic and/or clinical information, information from other valvular heart conditions, and/or image-based information obtained from a deep learning model ([0057]-[0059]; [0091]-[0100]; [0110]; figure 3, image based information obtained from a deep learning model ([0050], CNN is a class of deep learning model)).
Regarding claim 9, the combined references of Hare and Fornwalt teach all of the limitations of claim 1. Primary reference Hare further teaches:
further comprising localizing frame data corresponding to at least one atrium region in the second frames corresponding to ventricular systole ([0057]-[0058]; [0081]; [0091], localizing image data corresponds to left-right atriums in the annotated images of systolic and points of ventricles from the 2D images; figure 3, 4A).
Regarding claim 11, the combined references of Hare and Fornwalt teach all of the limitations of claim 1. Primary reference Hare further teaches:
wherein the at least one machine learning model is an ensemble model including at least one machine learning classifier, and outputs of the at least one machine learning classifier are fused to determine the RHD risk score (figure 3; [0046]-[0047]; [0057]-[0059]; [0091]-[0100]; [0110]; machine learning model of the echo flow engine comprises multiple neural network which process and classify images (classifiers) as shown in figure 3 and the outputs of these neural networks are fused together to determine the prediction and prognosis of heart disease in the form of a score; note that Fornwalt teaches to the RHD diagnosis particularly).
Regarding claim 13, primary reference Hare teaches:
A non-transitory computer-readable storage medium for storing computer- readable instructions that, when executed by a computer, cause the computer to perform a method for detecting heart disease (HD) based on at least an echocardiogram (abstract), the method comprising:
receiving echocardiogram data ([0033]-[0037], echocardiogram images; [0054], figure 3, “a process for performed by the echo workflow engine 12 to automatically recognize and analyze both 2D and Doppler modality echo images to perform automated measurements and the diagnosis”; [0055], echocardiogram images; [0056]; claim 1);
extracting first frames corresponding to at least one echocardiogram view from the echocardiogram data ([0057]-[0058], 2D images are extracted which correspond to first frames of an echocardiogram view (see classified by view type); [0059]-[0062]; figure 3);
extracting second frames corresponding to ventricular systole from the first frames corresponding to the at least one echocardiogram view ([0057]-[0058] and [0081], extracting of second images with annotations corresponding to systolic end points of ventricles from the 2D images corresponding to the echocardiogram view; [0059]-[0062]); and
determining, via at least one machine learning model, an HD risk score based on the second frames corresponding to ventricular systole (([0046]-[0047]; [0059]-[0062]; [0081]; [0091]-[0100]; [0110], determining using the echo workflow engine, which is a trained machine learning model, a prediction and prognosis of heart disease in the form of a score based upon, in part, in the second images corresponding to the systolic end points of ventricles; figures 3, 4A, and 4B).
Primary reference Hare fails to teach:
Rheumatic heart disease
However, the analogous art of Fornwalt of a method for determining a predicted risk level of a health condition for a patient (abstract) teaches:
Rheumatic heart disease ([0010], trained neural networks for echocardiographic analysis of conditions such as diagnosis of chronic rheumatic heart disease)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the machine learning model based echocardiogram analysis for heart disease processing of Hare to incorporate the rheumatic heart disease diagnosis via neural network as taught by Fornwalt because technology, such as artificial intelligence and machine learning, can manage an abundance of data and ultimately provide intelligent computer assistance and precise diagnosis to physicians (Fornwalt, [0002]). By enabling diagnosis of particular conditions such as rheumatic heart disease, more accuracy in diagnostics can be obtained leading to more effective clinical interventions.
Regarding claim 14, the combined references of Hare and Fornwalt teach all of the limitations of claim 13. Primary reference Hare further teaches:
wherein the echocardiogram data includes Doppler data, color Doppler echocardiogram data, or B-mode ultrasound data ([0057], echocardiogram data includes doppler modality images; figure 3).
Regarding claim 15, the combined references of Hare and Fornwalt teach all of the limitations of claim 13. Primary reference Hare further teaches:
wherein the at least one echocardiogram view includes an apical 4-chamber (A4CC) view and/or a parasternal long axis (PLAXC) view ([0058], echocardiogram view includes apical 4-chamber view and parasternal long axis view).
Regarding claim 19, the combined references of Hare and Fornwalt teach all of the limitations of claim 13. Primary reference Hare further teaches:
further comprising localizing frame data corresponding to at least one atrium region in the second frames corresponding to ventricular systole ([0057]-[0058]; [0081]; [0091], localizing image data corresponds to left-right atriums in the annotated images of systolic and points of ventricles from the 2D images; figure 3, 4A).
Regarding claim 20, primary reference Hare teaches:
An apparatus for detecting heart disease (HD) based on at least an echocardiogram (abstract), comprising:
processing circuitry configured to receive echocardiogram data ([0033]-[0037], echocardiogram images; [0054], figure 3, “a process for performed by the echo workflow engine 12 to automatically recognize and analyze both 2D and Doppler modality echo images to perform automated measurements and the diagnosis”; [0055], echocardiogram images; [0056]; claim 1),
extract first frames corresponding to at least one echocardiogram view from the echocardiogram data ([0057]-[0058], 2D images are extracted which correspond to first frames of an echocardiogram view (see classified by view type); [0059]-[0062]; figure 3),
extract second frames corresponding to ventricular systole from the first frames corresponding to the at least one echocardiogram view ([0057]-[0058] and [0081], extracting of second images with annotations corresponding to systolic end points of ventricles from the 2D images corresponding to the echocardiogram view; [0059]-[0062]), and
determine, via at least one machine learning model, an HD risk score based on the second frames corresponding to ventricular systole ([0046]-[0047]; [0059]-[0062]; [0081]; [0091]-[0100]; [0110], determining using the echo workflow engine, which is a trained machine learning model, a prediction and prognosis of heart disease in the form of a score based upon, in part, in the second images corresponding to the systolic end points of ventricles; figures 3, 4A, and 4B).
Primary reference Hare fails to teach:
Rheumatic heart disease
However, the analogous art of Fornwalt of a method for determining a predicted risk level of a health condition for a patient (abstract) teaches:
Rheumatic heart disease ([0010], trained neural networks for echocardiographic analysis of conditions such as diagnosis of chronic rheumatic heart disease)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the machine learning model based echocardiogram analysis for heart disease apparatus of Hare to incorporate the rheumatic heart disease diagnosis via neural network as taught by Fornwalt because technology, such as artificial intelligence and machine learning, can manage an abundance of data and ultimately provide intelligent computer assistance and precise diagnosis to physicians (Fornwalt, [0002]). By enabling diagnosis of particular conditions such as rheumatic heart disease, more accuracy in diagnostics can be obtained leading to more effective clinical interventions.
Claims 5-7 and 16-18 are rejected under 35 U.S.C. 103 as being unpatentable over Hare, in view of Fornwalt as applied to claims 1 or 13 above, and further in view of Steeds, R., et al., (“Imaging assessment of mitral and aortic regurgitation: current state of the art,” Education in Heart. Vol 106, 2020. P. 1769-1776) hereinafter Steeds (see NPL reference of applicant’s IDS of 3/03/2025 for citations).
Regarding claims 5 and 16, the combined references of Hare and Fornwalt teach all of the limitations of claims 1 or 13. Primary reference Hare further fails to teach:
further comprising identifying and characterizing a mitral valve regurgitation (MR) jet in the second frames corresponding to ventricular systole and/or an aortic valve regurgitation (AR) jet
However, the analogous art of Steeds of an imaging assessment of heart conditions in heart disease patients (abstract) teaches:
further comprising identifying and characterizing a mitral valve regurgitation (MR) jet in the second frames corresponding to ventricular systole and/or an aortic valve regurgitation (AR) jet (figures 4, 5; page 1771, col 1, paragraph 2 through page 1774, col 1, paragraph 1, identifying and characterizing a MR jet in image A (second frames) and AR jet in image B corresponding to ventricular systole).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the machine learning model-based echocardiogram analysis for heart disease apparatus of Hare and Fornwalt to incorporate the characterization of a jet as taught by Steeds because a timely diagnosis of features such as regurgitation of jets can lead to careful monitoring and faster interventions, which improves overall clinical outcomes for patients (Steeds, Introduction).
Regarding claims 6 and 17, the combined references of Hare, Fornwalt, and Steeds teach all of the limitations of claims 5 or 16. Primary reference Hare further fails to teach:
wherein the determining the RHD risk score is based on morphological and/or physiological characteristics of the MR jet and/or morphological and/or physiological characteristics of the AR jet
However, the analogous art of Steeds of an imaging assessment of heart conditions in heart disease patients (abstract) teaches:
wherein the determining the RHD risk score is based on morphological and/or physiological characteristics of the MR jet and/or morphological and/or physiological characteristics of the AR jet (table 1, table 2; page 1769, col 2, paragraph 3 through page 1770, col 1, paragraph 1; page 1771, col 1 paragraph 2 through col 2, paragraph 1; determining the cause being rheumatic heart disease is based on morphological characteristics of the MR jet).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the machine learning model-based echocardiogram analysis for heart disease apparatus of Hare, Fornwalt, and Steeds to incorporate the characterization of a jet as taught by Steeds because a timely diagnosis of features such as regurgitation of jets can lead to careful monitoring and faster interventions, which improves overall clinical outcomes for patients (Steeds, Introduction).
Regarding claims 7 and 18, the combined references of Hare, Fornwalt, and Steeds teach all of the limitations of claims 6 or 17. Primary reference Hare further fails to teach:
wherein the morphological and/or physiological characteristics of the MR jet include at least one of a size descriptor, a shape descriptor, a ratio between an atrium area and an MR jet size, statistical measures related to MR jet intensity or velocity, and duration of the MR jet
However, the analogous art of Steeds of an imaging assessment of heart conditions in heart disease patients (abstract) teaches:
wherein the morphological and/or physiological characteristics of the MR jet include at least one of a size descriptor, a shape descriptor, a ratio between an atrium area and an MR jet size, statistical measures related to MR jet intensity or velocity, and duration of the MR jet (page 1771, col 1, paragraph 2 through col 2, paragraph 1, the morphological characteristics of the MR jet include size of the jet).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the machine learning model-based echocardiogram analysis for heart disease apparatus of Hare, Fornwalt, and Steeds to incorporate the characterization of a jet as taught by Steeds because a timely diagnosis of features such as regurgitation of jets can lead to careful monitoring and faster interventions, which improves overall clinical outcomes for patients (Steeds, Introduction).
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Hare, in view of Fornwalt as applied to claim 1 above, and further in view of Ali, F., et al., (“Detection of subclinical rheumatic heart disease in children using a deep learning algorithm on digital stethoscope: a study protocol,” BMJ Open. Vol 11, 2020. P. 1-7) hereinafter Ali (see NPL reference of applicant’s IDS of 3/03/2025 for citations).
Regarding claim 12, the combined references of Hare and Fornwalt teach all of the limitations of claims 1. Primary reference Hare further teaches:
further comprising the second frames corresponding to ventricular systole ([0057]-[0058] and [0081], extracting of second images with annotations corresponding to systolic end points of ventricles from the 2D images corresponding to the echocardiogram view; [0059]-[0062])
Primary reference Hare further fails to teach:
further comprising classifying a type of RHD based on the frames
However, the analogous art of Ali of detection of rheumatic heart diseases in patients (abstract) teaches:
further comprising classifying a type of RHD based on the frames (figure 1; page 1, col 1, paragraphs 1-2, categorize the RHD as either definite RHD or borderline RHD based on the echocardiographic image; see also pages 4-5).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the machine learning model-based echocardiogram analysis for heart disease apparatus of Hare and Fornwalt to incorporate the classification of a type of RHD as taught by Ali because correct estimation of the disease at an early stage can lead to more precise clinical interventions and improved patient outcomes (Ali, page 5, Potential impact).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SEAN A FRITH whose telephone number is (571)272-1292. The examiner can normally be reached M-Th 8:00-5:30 Second Fri 8:00-4:30.
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, Keith Raymond can be reached at 571-270-1790. 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.
/SEAN A FRITH/Primary Examiner, Art Unit 3798