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 .
Applicant’s Response
In Applicant’s Response dated 7/10/26, the Applicant amended Claims 1, 2 and argued previously rejected claims in the Office Action dated 4/10/26. Claims 1-12 are pending examination.
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 1-12 are rejected under 35 U.S.C. 101 because the claimed invention is directed to abstract idea without significantly more. The claim recites “using a first machine learning model to generate a first numerical likelihood associated with a lesion in a medical scan”, “using a second machine learning model to generate a second
numerical likelihood associated with the lesion using one or more pathomic features
associated with the lesion”; and “generating a combined medical prediction associated with the lesion using the first numerical likelihood and the second medical prediction
numerical likelihood as inputs to a third model”. The broadest reasonable interpretation of steps is that those steps fall within the mental process groupings of abstract ideas because they cover concepts performed in the human mind, including observation, evaluation, judgment, and opinion. See MPEP 2106.04(a)(2), subsection III. When read in light of the specification, the “predicting” encompasses mental observations or evaluations that are practically performed in the human mind. A user can look at scans and predict a prognosis.
The limitations that include “using a model” provide nothing more than mere instructions to implement an abstract idea on a generic computer. See MPEP 2106.05(f). MPEP 2106.05(f) provides the following considerations for determining whether a claim simply recites a judicial exception with the words “apply it” (or an equivalent), such as mere instructions to implement an abstract idea on a computer.
The trained “mode;” is used to generally apply the abstract idea without placing any limits on how the trained model functions. Rather, these limitations only recite the outcome of models and do not include any details about how the “predicting” and is accomplished. See MPEP 2106.05(f). Thus, This judicial exception is not integrated into a practical application.
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)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-5, 8-12 are rejected under 35 U.S.C. 102(a)(2) as being anticipate by Rathore et al., “Radiopathomics: Integration of radiographic and histologic characteristics for prognostication in glioblastoma” (hereinafter “Rathore”).
Claim 1:
Rathore discloses:
A method, comprising:
using a first machine learning model to generate a first numerical likelihood associated with a lesion in a medical scan using one or more intra-lesional radiomic features associated with the lesion and one or more peri-lesional radiomic features associated with a peri-lesional region around the lesion (see page 2-3 “Introduction” and page 4 “2.4. Feature Extraction”). Rathore teaches using an algorithm to extract features and make quantitative predictions based on the medical images of tumors using the radiomic features;
using a second machine learning model to generate a second numerical likelihood associated with the lesion using one or more pathomic features associated with the lesion (see page 2-3 “Introduction” and page 4 “2.4. Feature Extraction”). Rathore teaches using an algorithm to extract features and make predictions based on the medical images of tumors using the pathomic features. Both are independently analyzed to make independent quantitative predictions; and
generating a combined medical prediction associated with the lesion using the first numerical likelihood and the second likelihood as inputs to a third model (see page 6 “3.2 performance of the radiopathomic classification model”). Rathore teaches generating a combined medical quantitative prediction using a third model could facilitate characterization of the heterogeneity of brain tumors across the entire breadth of the tissue specimen or radiographic appearance of the tumor. These tools can help in patient stratification into appropriate treatments, and identification of patients with relatively highly heterogeneous tumors, who would benefit from more extensive histopathological and molecular analysis through multiple samples, as well as by combination treatments.
Claim 2:
Rathore discloses:
A method, comprising:
inputting, to a first machine learning model, one or more intra-lesional radiomic features associated with a lesion in a medical scan and one or more peri-lesional radiomic features associated with a peri-lesional region around the lesion, the first machine learning model having been pre-trained to make a medical prediction based on the one or more intra-lesional radiomic features and the one or more peri-lesional radiomic features (see page 2-3 “Introduction” and page 4 “2.4. Feature Extraction”). Rathore teaches using an algorithm to extract features and make prediction based on the medical images of tumors using the radiomic features. Apply supervised learning algorithm on multiple data streams to exploit the complementary information provided by these imaging sequences for improved prognostication.;
receiving a first numerical likelihood associated with the lesion from the first machine learning model in response to said inputting (see page 2-3 “Introduction” and page 4 “2.4. Feature Extraction”). Rathore teaches applying supervised learning algorithm on multiple data streams to exploit the complementary information provided by these imaging sequences for improved prognostication.;
inputting, to a second machine learning model, one or more pathomic features associated with the lesion, the second machine learning model having been pre-trained to make a medical prediction based on the one or more pathomic features (see page 2-3 “Introduction” and page 4 “2.4. Feature Extraction”). Rathore teaches using an algorithm to extract features and make quantitative prediction based on the medical images of tumors using the pathomic features. Both are independently analyzed to make independent quantitative predictions;
receiving a second numerical likelihood associated with the lesion from the second machine learning model in response to said inputting (see page 2-3 “Introduction” and page 4 “2.4. Feature Extraction”). Rathore teaches applying supervised learning algorithm on multiple data streams to exploit the complementary information provided by these imaging sequences for improved prognostication; and
generating a combined numerical likelihood associated with the lesion using the first medical prediction and the second numerical likelihood as inputs to a third model (see page 6 “3.2 performance of the radiopathomic classification model”). Rathore teaches generating a combined medical prediction using a third model could facilitate characterization of the heterogeneity of brain tumors across the entire breadth of the tissue specimen or radiographic appearance of the tumor. These tools can help in patient stratification into appropriate treatments, and identification of patients with relatively highly heterogeneous tumors, who would benefit from more extensive histopathological and molecular analysis through multiple samples, as well as by combination treatments.
Claim 3:
Rathore discloses:
wherein the first machine learning model and the second machine learning model are different from one another (page 5 “2.5 Machine learning and correlation analysis”). Rathore teaches trained separate support vector regression (SVR) models in a LOOCV configuration for the prediction of survival with continuous values.
Claim 4:
Rathore discloses:
wherein the lesion comprises a solid tumor (see page 1 “Abstract”). Rathore teaches images captured from tissue samples are currently acquired as standard clinical practice for glioblastoma tumors.
Claim 5:
Rathore discloses:
wherein the combined medical prediction comprises a combined prognosis (see page 2 “Introduction” and page 6 “3.2 performance of the radiopathomic classification model”). Rathore teaches generating a combined medical prediction using a third model could facilitate characterization of the heterogeneity of brain tumors across the entire breadth of the tissue specimen or radiographic appearance of the tumor. The combined evaluation of Rad and Path images will even further improve prognostication, and will enhance our understanding of the disease.
Claim 8:
Rathore discloses:
wherein the third model comprises a machine learning model (see page 2 “Introduction” and page 6 “3.2 performance of the radiopathomic classification model”). Rathore teaches generating a combined medical prediction using a third model could facilitate characterization of the heterogeneity of brain tumors across the entire breadth of the tissue specimen or radiographic appearance of the tumor.
Claim 9:
Although Claim 9 is a non-transitory machine readable medium, it is interpreted and rejected for the same reasons as the method of Claim 2.
Claim 10:
Rathore discloses:
wherein the combined medical prediction concerns treatment of the lesion (see Page 1 “Abstract”, “Introduction” and Page 8 “Discussion”). Rathore teaches the combination of radiomic images/prediction and patholic images/predictions to diagnose and generate treatment plans.
Claim 11:
Rathore discloses:
wherein the combined medical prediction concerns diagnosis of the lesion (see Page 1 “Abstract”, “Introduction” and Page 8 “Discussion”). Rathore teaches the combination of radiomic images/prediction and patholic images/predictions to diagnose and generate treatment plans for the tumors.
Claim 12:
Rathore discloses:
wherein the combined medical prediction concerns monitoring of the lesion (Page 8 “Discussion”). Rathore teaches having a panel of computational tools combining histology and radiographic sequences is likely to improve our ability to target the right patients with the right treatments, and to monitor response over the whole course of the disease.
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 6 is rejected under 35 U.S.C. 103 as being unpatentable over Rathore, in view of Lim et al., WO 2017014694 (hereinafter “Lim”).
Claim 6:
Rathore fails to expressly disclose disease-free survival (DFS), non-DFS, or a likelihood of DFS.
Lim discloses:
wherein the combined medical prediction is one of disease-free survival (DFS), non-DFS, or a likelihood of DFS (see paragraph [0087]). Lim teaches predicting a disease free survival prediction.
Accordingly, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention was made to modify the method disclosed by Rathore to include a DFS prediction for the purpose of efficiently determining characteristics of the tumor/disease, as taught by Lim.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Rathore, in view of Land et al., WO 2018098241 (hereinafter “Land”)
Claim 7:
Rathore fails to expressly the combined model being a nomogram.
Land discloses:
wherein the third model comprises a nomogram (see page 40 lines 13-19). Land teaches a combined nomogram model for the prediction.
Accordingly, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention was made to modify the method disclosed by Rathore to include a nomogram for the combined prediction model for the purpose of efficiently making more accurate predictions, as taught by Land.
Pertinent Art
2016/0196648 – fusing radiomic and pathomic features medical data for prognosis. Doesn’t list multiple algorithms or models.
Response to Arguments
Applicant's arguments filed 7/10/26 have been fully considered but they are not persuasive.
102 and 103 Predictions
Applicant argues In response, and as discussed during the telephone interview of July 1, 2026, Applicant has amended the two independent claims to recite that the first and second machine learning models produce first and second "numerical likelihood[s] associated with the lesion." A third model uses these numerical likelihoods to produce a "combined medical prediction." As was discussed during the interview, both independent claims are also highly specific about the locations from which the radiomic features are taken. In the words of claim 1, the methods "us[e] one or more intra-lesional radiomic features and one or more peri-lesional radiomic features[.]"
The Examiner disagrees.
Rathore teaches an algorithm to extract pathomic features for a prediction, and an algorithm to extract radiomic features for a prediction. After further consideration of the art, the algorithm using to extract the features also produce quantitative prediction data based on the inputted image (see page 4, section 2.4 feature extraction). The features from the algorithm for each type of data output quantitative data used for the prediction. An algorithm to output pathomic and radiomic features. The claims also does not train the machine learning models, therefore the trained machine learning models are simply used to output data, which is what Rathore algorithm does, it output features from pathomic images and outputs features from radiomic images uses those features from both types of images as input into the prediction model to produce another output. Thus, Rathore teaches the limitations of the independent claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TIONNA M BURKE whose telephone number is (571)270-7259. The examiner can normally be reached M-F 8a-4p.
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, Stephen Hong can be reached at (571)272-4124. 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.
/TIONNA M BURKE/Examiner, Art Unit 2178 8/8/26
Prosecution Insights