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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 08/26/2026 has been entered.
Response to Amendment
This communication is filed in response to the application filed on 08/26/2026.
Claim 1 is currently amended. Claims 1, and 3-6 are pending.
Response to Arguments
Applicant’s arguments filed on 08/26/2026 on pages 1-7, under REMARKS with respect to 35 U.S.C. 102 and 103 claim rejections to claims 1, and 3-6 have been fully considered and are persuasive. The rejections to the claims have been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of US 11,238,586 B2.
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 non-obviousness.
Claims 1, and 4-6 are/is rejected under 35 § U.S.C. 103 as being obvious over US 2019/0183366 A1 to DEHGHAN MARVAST et al. (hereinafter “MARVAST”) in view of US 11,238,586 B2 to MINCHENKOV ET AL. (hereinafter “MINCHENKOV”).
As per claim 1, MARVAST discloses a method for training a medical image classification model using a computing device (a system and method for using and training of a medical image classification model wherein the model is based on plurality of neural networks wherein the described models are run and executed on a computer comprising computing components and trains said models using a training method; abstract; figs 1A-1C, and 3-4; paragraphs [0005], [0018-0021]), the method comprising: training, by using a training dataset including raw medical image data (training using input training data and the input training data is a medical image data set of raw image data; abstract; figs 1A-1C, and 2; paragraph [0072]), a plurality of first neural network models to classify medical image data into a predetermined class (training components 120-180 implementing machine learning/deep learning mechanisms, which are neural networks, trained using aforementioned raw images in a training medical image dataset as provided in corpus 240 the neural networks making up the cognitive system 200 after training comprise triage cognitive logic 232 that performs triage support operations by classifying medical images of patients and ranking the severity of the medical conditions (predetermined classes of severity); fig 2; paragraph [0072], [0077]), wherein the plurality of first neural network models have different neural network model structures (the provided echocardiograph extraction component is provided to comprise CNNs trained to extract specific image features and would be provided to include different CNNs adapted for extraction of different features and are trained using training data and training logic 180; figs 1A-2, and 4; paragraphs [0019-0021], [0034], [0037-0040], [0070-0072]); auto-augmenting the raw medical image data to generate medical image augmentation data (the features of the raw echocardiogram medical images are extracted by the automated echocardiograph measurement extraction system 100 based on the learned associations of medical image and using medical image viewer 230 automatically augments the image renderings of the medical images with additional emphasis on features or of interest by for example highlighting abnormalities; fig 2; paragraphs [0070-0075]); sequentially filtering the medical image augmentation data by each of the plurality of first neural network models and selecting, as effective augmentation data, only medical image augmentation data that have a class probability equal to or greater than a predetermined criterion in each of the plurality of first neural network models (the computing system performs steps in order (sequentially) in order to filter the medical heart imaging data in order to determine which medical images are complete in order to reduce probability of a misclassification due to incomplete measurements and inputting only images verified by the neural networks as useful for training using the automated measurement extraction engine to perform additional operations for advising medical personnel which types of images needed in order to complete a echocardiography imaging study and is adapted to inform the technician when the echocardiography medical imaging study has been completed, i.e. all necessary measurements needed for the particular study have been obtained from the images captured and the data needed to perform classification using component 130 and comparing it to as an example, there are 80 medical images generated from an echocardiography study of the patient, each may be evaluated via the CNN 160 of the illustrative embodiments to identify corresponding measurements from the learned best viewpoint images for the particular desired measurements, the measurements are compared to criteria, which are present in predefined rules, medical knowledge sources ingested by the cognitive system 190, medical guidelines, and the like, to identify where abnormalities may be present in the classified images; fig 2, 4; paragraphs [0018-0021], [0024], [0036], [0053-0056], [0068-0072], [0075], [0093]); and training, by using a training dataset including the effective augmentation data and the raw medical image data, a second neural network model to classify medical image data into a predetermined class (component 130 which is a deep learning neural network trained using the augmented annotated medical images, further deep learning viewpoint classification component 130 is trained using medical images annotated or labeled by a specialist in a training phase with the particular viewpoint information so that the trained viewpoint classification component 130 is able to classify new medical images of various modes with regard to their viewpoint based on the similarity of the characteristics of the medical image to those upon which the training is performed; fig 2; paragraphs [0037], [0072]). MARVAST fails to disclose wherein, for each first neural network model subsequent to an initial first neural network model in the sequential filtering, only medical image augmentation data that have a class probability equal to or greater than a predetermined criterion in the immediately preceding first neural network model are input to that subsequent first neural network model.
MINCHENKOV discloses wherein, for each first neural network model subsequent to an initial first neural network model in the sequential filtering, only medical image augmentation data that have a class probability equal to or greater than a predetermined criterion in the immediately preceding first neural network model are input to that subsequent first neural network model (the computing system is adapted to perform sequential filtering on sequentially captured medical images in order to sort the images by class using class probabilities and comparing them to a probability threshold and based on being greater than the threshold of accuracy/quality or the tracked image feature/criteria the medical image in this case an oral dental image is classified by the model; figs 5A-B, 8A, and 12; column 7, line 32-column 8, line 32; column 21, lines 15-67; column 25, lines 4-44).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention to modify MARVAST to have a class probability equal to or greater than a predetermined criterion of MINCHENKOV reference. The Suggestion/motivation for doing so would have been to provide if the probability of the excess material class is greater than the threshold then the pixel is classified as excess material. If the probability is lower than the probability threshold, then the pixel is not classified as excess material for removal purposes after/following a dental procedure but could be applied to any different medical procedure where tissue/material types must be differentiated as suggested by column 21, lines 44-54 of MINCHENKOV. Further, one skilled in the art could have combined the elements as described above by known method with no change in their respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine MINCHENKOV with MARVAST to obtain the invention as specified in claim 1.
As per claim 4, MARVAST in view of MINCHENKOV discloses the method of claim 1. Modified MARVAST further discloses wherein the plurality of first neural network models and the second neural network models are deep neural networks “DNNs” (the neural networks used are deep learning neural networks; fig 2; paragraphs [0072-0073]).
As per claim 5, MARVAST in view of MINCHENKOV discloses the medical image classification model according to claim 1. Modified MARVAST further discloses a method for classifying a medical image (after training the cognitive system 190 comprising the trained neural networks for classification, performs a method of classifying medical images of patients and ranking the severity of the medical conditions of the patients at least partially based on the measurements generated by the automated echocardiograph measurement extraction system 100; fig 2; paragraphs [0037], [0055], [0070-0075]), the method comprising classifying medical image data into a predetermined class by using a second neural network model trained by the method for training the medical image classification model according to claim 1 (the method of classification occurs using a trained neural network component provided as deep learning viewpoint classification component 130 is trained using medical images annotated or labeled by a specialist in a training phase with the particular viewpoint information so that the trained viewpoint classification component 130 is able to classify new medical images of various modes with regard to their viewpoint (predetermined classes) based on the similarity of the characteristics of the medical image to those upon which the training is performed; fig 2; paragraphs [0037], [0072]).
As per claim 6, MARVAST in view of MINCHENKOV discloses the medical image classification model according to claim 1. Modified MARVAST further discloses a non-transitory computer-readable recording medium recording a program for executing the method for training the medical image classification model according to claim 1 (the system comprises a computer and comprises components including a processor and computer readable medium/memory to store instruction executable by said processor to perform the methods described; paragraphs [0006], [0024], [0026]).
Claim 3 is rejected under 35 § U.S.C. 103 as being obvious over US 2019/0183366 A1 to DEHGHAN MARVAST et al. (hereinafter “MARVAST”) in view of US 2023/0097169 A1 to Dwivedi et al. (hereinafter “DWIVEDI”).
As per claim 3, MARVAST discloses the method of claim 1. MARVAST fails to disclose wherein one of the plurality of first neural network models and the second neural network model have a same neural network model structure.
DWIVEDI discloses wherein one of the plurality of first neural network models and the second neural network model have a same neural network model structure (wherein during training the reformatted first model 218 and second model 220, represented as one or more data structures, can be analyzed by the first processor 206 to identify at least one common feature, such as a common neural network architecture, common layers, such as nodes representing resolutions or features, and/or common connections, such as operations e.g., convolution operations, smoking operations or weights, in the reformatted first and second models; paragraph [0082]).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention to modify MARVAST to have one of the plurality of first neural network models and the second neural network model have a same neural network model structure of DWIVEDI reference. The Suggestion/motivation for doing so would have been to aid model manager 222 in order to provide a common feature of the models for training purposes and management purposes as suggested by DWIVEDI paragraph [0082]. Further, one skilled in the art could have combined the elements as described above by known method with no change in their respective functions, and the combination would have yielded nothing more than predictable results. Therefore, it would have been obvious to combine DWIVEDI with MARVAST to obtain the invention as specified in claim 3.
Conclusion
Examiner's Note: Examiner has cited figures, and paragraphs in the references as applied to the claims above for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested for the applicant, in preparing the responses, to fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner. Examiner has also cited references in PTO892 but not relied on, which are relevant and pertinent to the applicant’s disclosure, and may also be reading (anticipatory/obvious) on the claims and claimed limitations. Applicant is advised to consider the references in preparing the response/amendments in-order to expedite the prosecution.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DEVIN JACOB DHOOGE whose telephone number is (571) 270-0999. The examiner can normally be reached 7:30-5:00.
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, Andrew Bee can be reached on (571) 270-5183. 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.
/D J DHOOGE/Examiner, Art Unit 2677
Prosecution Insights