DETAILED ACTION
Response to Arguments
Applicant’s amendments to claims 11 and 16 submitted 5/19/2026 have been recorded. As such Examiner’s previous objections to the claims are withdrawn.
Applicant has amended claims 11-12, and 15-16; claims 11-16 are currently elected and pending.
Applicant's arguments filed 5/19/2026 have been fully considered but they are not persuasive. Applicant argues that Masmoudi ((Masmoudi H, Hewitt SM, Petrick N, Myers KJ, Gavrielides MA. Automated quantitative assessment of HER-2/neu immunohistochemical expression in breast cancer. IEEE transactions on medical imaging. 2009 Jan 19;28(6):916-25.) fails to teach the claim limitation “the second machine learning model is trained to generate the predictive HER2 score using classification data predicted based on feature representations of one or more membrane features and one or more nuclei features of the input image.” Masmoudi utilizes a second machine learning model to output a HER2 score which is trained using extracted features called membrane completeness and mean membrane intensity (Masmoudi Section III. Methods – E. Slide Classification – found on p. 920-921; extracted features (mean membrane completeness and mean membrane intensity, which utilize classified pixels – see Section III. Methods- B. Epithelial Nuclei Segmentation, C. Membrane Modeling Using adaptive Ellipse-fitting and D. Membrane Feature Extraction – found on p. 919-920)). Although Masmoudi describes only utilizing mean membrane intensity and mean membrane completeness these values are calculated using feature values of nuclei (see Section III. Methods - D. Membrane Feature Extraction – ¶4 found on p. 920 ) in addition to membrane features (see Section III. Methods - D. Membrane Feature Extraction – ¶2-3 found on p. 920 ). Therefore, “classification data predicted based on feature representations of one or more membrane features and one or more nuclei features of the input image” is considered to be taught. A limitation positively reciting the type of nuclei features utilized would likely overcome the reference. As such this action is made FINAL.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 11, 13-14, and 16 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Masmoudi (Masmoudi H, Hewitt SM, Petrick N, Myers KJ, Gavrielides MA. Automated quantitative assessment of HER-2/neu immunohistochemical expression in breast cancer. IEEE transactions on medical imaging. 2009 Jan 19;28(6):916-25.).
Regarding claim 11, Masmoudi discloses A method for training a predictive Human growth factor 2 (HER2) tissue scoring model, comprising: (Masmoudi Abstract; an automated HER2 tissue scoring method is disclosed.) receiving a first training data set including a first plurality of images comprising stained tissue samples; training a first machine learning model using the first training data set to classify segments of an input image as nuclei or membrane, wherein the input image comprises an image of stained tissue sample, and the first plurality of images comprises labeled training data identifying membrane and nuclei in the plurality of images; and (Masmoudi Section III. Methods – A. Color Pixel Classifier – found on p. 918-919; ¶1 explains that pixels are classified as nuclei, membrane, or background. ¶2 discloses that a linear regression classifier identifies membrane pixels. It is trained using labeled pixels from stained slides. ¶6 discloses nuclei pixel classification. It is trained using labeled pixels from stained slides. Full classification is considered to be the first machine learning model.) training a second machine learning model using a second training data set to generate a predictive HER2 score for the input image, wherein: the second training data set comprises a second plurality of images labeled to identify membrane and/or nuclei in the plurality of images; the second plurality of images comprises training classification data corresponding to a plurality of features associated with membrane and nuclei in the second plurality of images; (Masmoudi Section III. Methods – E. Slide Classification – found on p. 920-921; extracted features (mean membrane completeness and mean membrane intensity, which utilize classified pixels – see Section III. Methods- B. Epithelial Nuclei Segmentation, C. Membrane Modeling Using adaptive Ellipse-fitting and D. Membrane Feature Extraction – found on p. 919-920) are used to classify each slide with a 1+, 2+ or 3+ HER2 classification score.) and the second machine learning model is trained to generate the predictive HER2 score using classification data predicted based on feature representations of one or more membrane features and one or more nuclei features of the input image. (Masmoudi Section III. Methods – E. Slide Classification – found on p. 920-921; extracted features (mean membrane completeness and mean membrane intensity, which utilize classified pixels – see Section III. Methods- B. Epithelial Nuclei Segmentation, C. Membrane Modeling Using adaptive Ellipse-fitting and D. Membrane Feature Extraction – found on p. 919-920) are used to classify each slide with a 1+, 2+ or 3+ HER2 classification score. The classifier is trained using mean membrane completeness and mean membrane intensity. Although the values are called mean membrane intensity and mean membrane completeness the values use feature values of nuclei in their calculation (see Section III. Methods - D. Membrane Feature Extraction – ¶4 found on p. 920 ). Therefore, the second model is trained based on membrane and nuclei features.)
Regarding claim 13, Masmoudi discloses the claim limitations with regards to claim 11, as described above. Masmoudi further discloses wherein the plurality of features associated with membrane and nuclei in the second plurality of images comprises features corresponding to one or more of the following: an intensity of membrane stain, a completeness of membrane stain, an underlying color of nuclei, an underlying color of membrane, a ratio of membrane and nuclei, a membrane stain deviation, a nuclei stain deviation, an area of completely stained membrane, and a stained membrane cell percentage. (Masmoudi III. Methods; features include color (see A. Color Pixel Classifier ¶2 and ¶6 p. 919), membrane completeness, membrane staining intensity (see D. Membrane Feature Extraction ¶1), percentage of membrane pixels (stained membrane cell percentage see De. Membrane Feature Extraction ¶2).)
Regarding claim 14, Masmoudi discloses the claim limitations with regards to claim 11, as described above. Masmoudi further discloses wherein the second machine learning model comprises one or more of a random forest machine learning model, a support vector machine, a decision tree, a convolutional neural network, or any other machine learning model capable of learning and solving classification problems. (Masmoudi Section III. Methods – E. Slide Classification – p. 920-921; a classifier that utilizes minimum cluster distance is disclosed.)
Regarding claim 16, Masmoudi discloses the claim limitations with regards to claim 11, as described above. Masmoudi further discloses wherein training the second machine learning model to generate a predictive HER2 score for the input image based on the second training data set further comprises training the second machine learning model based on the plurality of features relevant to American Society of Clinical Oncology( ASCO)/ College of American Pathologist (CAP) guidelines for HER2 scoring of IHC stained breast cancer tissue cells. (Masmoudi Section I. Introduction ¶3-4 – found on p. 916-917; CAP/ASCO HER2 evaluation recommendations are discussed. ¶7 the disclosed methods uses staining intensity, as recommended by CAP/ASCO, to provide HER2 scoring.)
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.
Claim(s) 12 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Masmoudi (Masmoudi H, Hewitt SM, Petrick N, Myers KJ, Gavrielides MA. Automated quantitative assessment of HER-2/neu immunohistochemical expression in breast cancer. IEEE transactions on medical imaging. 2009 Jan 19;28(6):916-25.).) in view of Schmidt (Pub. No. WO2022054009A2).
Regarding claim 12, Masmoudi discloses the claim limitations with regards to claim 11, as described above.
Masmoudi does not explicitly disclose wherein the first machine learning model comprises a deep-learning neural network machine learning model having convolutional layers configured to jointly detect nuclei and membrane in whole slide images.
However, Schmidt discloses wherein the first machine learning model comprises a deep-learning neural network machine learning model having convolutional layers configured to jointly detect nuclei and membrane in whole slide images. (Schmidt ¶153, ¶155 and Fig. 15; discloses a CNN U-Net with convolutional layers to perform segmentation of nuclei and membranes. Fig. 15 shows that the same CNN outputs probabilities of each pixel is the nucleus or the membrane, therefore they are jointly detected.)
It would have been obvious, before the effective filing date of the claimed invention, to one of ordinary skill in the art to modify training method of Masmoudi with the teachings of Schmidt by utilizing a u-net CNN to perform segmentation of nuclei and membrane in order to utilize a method that can do pixel level segmentation for both classes in one step rather than multiple linear classification steps.
Regarding claim 15, Masmoudi discloses the claim limitations with regards to claim 11, as described above.
Masmoudi does not explicitly disclose wherein training the first machine learning model to classify segments of the input image as nuclei or membrane comprises the first machine learning model extracting learned features of membrane and nuclei, and utilizing the learned features as shared training weights for detecting both membrane and nuclei in a single pass
However, Schmidt discloses wherein training the first machine learning model to classify segments of the input image as nuclei or membrane comprises training the first machine learning model to classify both nuclei and the first machine learning model extracting learned features of membrane and nuclei, and utilizing the learned features as shared training weights for detecting both membrane and nuclei in a single pass. (Schmidt ¶153 and ¶155; discloses a CNN U-Net to perform segmentation of nuclei and membranes. Training weights are for both nuclei and membranes i.e. shared. The described structure would segment both nuclei and membrane in the same pass.)
It would have been obvious, before the effective filing date of the claimed invention, to one of ordinary skill in the art to modify training method of Masmoudi with the teachings of Schmidt by utilizing a u-net CNN to perform segmentation of nuclei and membrane in order to utilize a method that can do pixel level segmentation for both classes in one step rather than multiple linear classification steps.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MEREDITH TAYLOR whose telephone number is (571)270-5805. The examiner can normally be reached M-Th 7:30-5. Examiner’s email is Meredith.taylor@uspto.gov.
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, Vincent Rudolph can be reached at (571)272-8243. 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.
/MEREDITH TAYLOR/Examiner, Art Unit 2671
/VINCENT RUDOLPH/Supervisory Patent Examiner, Art Unit 2671
Prosecution Insights