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 .
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 April 27, 2026 has been entered.
Response to Amendment
Claims 1, 4-6, 8-13, 15, 18-24, 30-34, and 39-45 are currently pending. Claims 1, 4, 8-13, 15, 18, 21, 23, 24, 31, 32, 34, and 39-44 have been amended. Claim 44 has been added. Claims 2, 3, 7, 13, 16, 17, 25-29, and 35-38 have been cancelled.
Response to Arguments
Applicant's arguments filed 04/27/2026 have been fully considered but they are not persuasive.
The claims remain directed to a judicial exception, namely an abstract idea, and the additional recited elements do not integrate that abstract idea into a practical application or amount to significantly more than the abstract idea itself.
The claims, even as amended, are directed to the collection and analysis of medical imaging and clinical data to generate diagnostic or predictive information regarding liver disease or other organ/tissue disease. The claims recite receiving data, segmenting the imaging data, extracting radiomic and deep features, applying one or more machine learning models, predicting disease-related outcomes, and communicating the results to a user. These steps, individually and in combination, amount to data gathering, analysis, and reporting of a medical diagnostic conclusion. Such concepts are abstract ideas under § 101.
1. Argument: The claims include subject matter that cannot be performed by the human mind
Applicant argues that the amended claims now include limitations, such as radiomic feature extraction and deep feature extraction, that “cannot be performed by the human mind,” and therefore the claims are eligible under § 101.
This argument is not persuasive.
The mere fact that a claim recites computer-implemented operations, or operations that may be difficult or impractical for a human to perform manually, does not automatically render the claim patent eligible. The eligibility inquiry is not satisfied simply because a claim requires computer execution or includes mathematical processing. Claims directed to abstract ideas remain abstract even when implemented using a computer or other technology.
Here, the recited limitations of segmenting MRI data, extracting radiomic features, extracting deep features, applying machine learning models, and predicting disease-related outcomes are all directed to the analysis of information to arrive at a diagnosis or prediction. This is a classic abstract idea. The claim language largely describes the results of the analysis rather than a specific technological improvement to the computer or imaging system itself.
In particular, the claimed features such as “high throughput extraction of quantitative imaging features,” “decoding image-based aberrations,” and “modeling complex abstractions of patterns through non-linear transformations” are functional descriptions of data processing operations. They do not, on their face, recite a specific unconventional technical solution that improves the operation of a computer, improves MRI acquisition, or improves image-processing technology itself.
Accordingly, the recitation that the process cannot be performed by the human mind is not sufficient, by itself, to overcome the § 101 rejection.
2. Argument: Radiomic feature extraction and deep feature extraction are beyond mental processes
Applicant relies on the recited radiomic and deep feature extraction steps as evidence that the claims are not directed to a mental process.
This argument is not persuasive.
Even if some portions of the claimed analysis are not practically performable by a human mind alone, the claims still recite an abstract diagnostic workflow. The claims are not directed to a specific improvement in computer functionality or to a specific improvement in machine learning architecture. Rather, they use computer-implemented feature extraction and classification tools to accomplish the abstract goal of diagnosing disease.
The claims recite:
receiving MRI and clinical data,
segmenting the MRI data,
extracting radiomic features,
extracting deep features,
applying machine learning models,
and communicating a diagnostic result.
This sequence is a form of information processing and medical diagnosis. The use of neural networks, radiomic features, and deep learning models does not, without more, transform the underlying concept into patent-eligible subject matter. The claims do not recite a particular improvement to how MRI data is acquired, how a neural network is technically structured in a novel way, or how the computer itself is improved. Instead, they recite the application of known computational tools to a particular class of data.
Therefore, the recited feature extraction steps do not, by themselves, remove the claims from the realm of abstraction.
3. Argument: The claims recite a practical application because they use MRI data and clinical data
Applicant appears to argue that because the claims are tied to MRI data, clinical data, and diagnostic outputs, they are integrated into a practical application.
This argument is not persuasive.
Tying an abstract idea to a particular field of use, such as medicine or medical imaging, does not by itself make the claim eligible. The claims still focus on the abstract process of analyzing data to predict or diagnose disease. The use of MRI data, biopsy-derived histologic data, demographic data, or laboratory data merely provides the information on which the abstract analysis is performed.
The claims do not recite a specific technological improvement in MRI scanning, image segmentation, feature extraction architecture, or machine learning model operation. Instead, they use data from a medical context as inputs to a generalized analytic process.
Under the current claim language, the purported practical application is the diagnosis or prediction itself. However, the recited steps do not go beyond using generic computer-implemented techniques to reach that result. The claims therefore remain directed to the abstract idea of collecting, analyzing, and outputting medical diagnostic information.
4. Argument: The machine learning model limitations provide eligibility
Applicant asserts that the claims are eligible because they recite one or more machine learning models, including U-shaped convolutional neural networks, models with short and long residual connections, ensemble models, transfer learning, saliency maps, and feature ranking processes.
This argument is not persuasive.
Reciting machine learning or deep learning models, without more, does not automatically confer patent eligibility. The claims must still be evaluated for whether they are directed to an abstract idea and whether any additional elements amount to significantly more.
Here, the machine learning components are recited functionally and at a high level. The claims do not specify a particular technical improvement to neural network operation, training methodology, data structure, or computer architecture that solves a technological problem in a novel way. Rather, the machine learning models are used as tools to analyze MRI and clinical data for the purpose of diagnosis and prediction.
The addition of a U-shaped CNN, residual connections, transfer learning, ensemble learning, saliency maps, and feature ranking approaches appears to describe the type of algorithmic framework being used, but not a concrete technological improvement to a computer or imaging system. These limitations are still directed to the abstract task of extracting information and classifying disease-related outcomes.
Accordingly, these machine learning limitations do not integrate the abstract idea into a practical application and do not amount to significantly more than the abstract idea itself.
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, 4-6, 8-13, 15, 18-24, 30-34, and 39-45 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more.
After careful consideration of Applicant’s amendments and remarks, the claimed invention is directed to an abstract idea, namely the collection, analysis, and evaluation of medical imaging and clinical data to determine or predict disease-related information, including diagnosis, disease stage, fibrosis percentage, liver stiffness, and related outputs. The claims, considered as a whole, do not integrate the judicial exception into a practical application, and the additional claim elements, individually and in ordered combination, do not amount to significantly more than the exception itself.
Step 2A, Prong One: The claims recite a judicial exception
The claims recite steps and systems for:
receiving multiparametric MRI data and clinical data,
segmenting the MRI data,
extracting radiomic features and deep features,
applying one or more machine learning models,
predicting or diagnosing aspects of liver disease or other organ/tissue disease, and
communicating the resulting information to a user.
These recited activities fall within the abstract idea groupings of mental processes and certain methods of organizing human activity / information analysis, as they are directed to evaluating information and producing a diagnostic or predictive conclusion. The claims focus on analyzing data to reach a medical assessment, which is an abstract idea.
Although Applicant asserts that certain steps cannot be performed by the human mind, the claims nonetheless recite the abstract concept of data analysis and diagnosis implemented using computer-based tools. Merely performing an abstract idea on a computer does not render the claims non-abstract.
Step 2A, Prong Two: The claims do not integrate the judicial exception into a practical application
The claims do not recite a specific improvement to computer functionality, MRI acquisition, image segmentation technology, or machine learning architecture itself. Rather, the claims use generic data-processing components and machine learning terminology at a high level of generality to accomplish the abstract diagnostic task.
For example, the claims recite:
segmenting MRI data using a U-shaped convolutional neural network,
extracting radiomic features,
extracting deep features through non-linear transformations,
using ensemble or multimodal deep learning models,
applying saliency maps and feature ranking,
and outputting diagnostic information.
These limitations are recited in functional terms and describe the type of analysis performed, not a specific technological improvement in how the computer or imaging system operates. The claims do not recite a particular unconventional algorithm, a specific new network architecture that improves computer performance, or a specific technical solution to a technological problem.
Applicant’s assertion that radiomic feature extraction or deep feature extraction cannot be performed by the human mind is not sufficient to establish eligibility. The relevant inquiry is whether the claims, as a whole, are directed to an abstract idea and whether they are integrated into a practical application. Here, they are not.
The claims merely apply known or conventional computer-based analytic techniques to medical imaging and clinical data in order to produce a diagnosis or prediction. That is insufficient to integrate the abstract idea into a practical application.
Step 2B: The claims do not add significantly more
The additional elements, considered individually and as an ordered combination, do not amount to significantly more than the judicial exception itself.
The claims recite conventional data inputs and outputs, including:
MRI data,
clinical data,
biopsy-derived histologic data,
predicted fibrosis stage,
fibrosis percentage,
shear liver stiffness, and
communication of results to a user.
They also recite standard computer implementation elements such as machine learning models, neural networks, feature extraction, transfer learning, ensemble learning, saliency maps, and feature ranking. These elements, as claimed, are recited at a high level of generality and perform their ordinary functions in the context of the diagnostic workflow.
The specification and claim language do not sufficiently demonstrate that these elements are unconventional, non-generic, or used in a manner that yields an inventive concept beyond the abstract idea. The claims amount to applying generic machine-learning and image-processing techniques to analyze medical data and report a diagnostic conclusion.
Accordingly, the additional elements do not add an inventive concept sufficient to transform the abstract idea into patent-eligible subject matter.
Claim grouping
Independent claim 1
Claim 1 is rejected under 35 U.S.C. § 101 because it recites a method of analyzing MRI and clinical data to diagnose liver disease, including segmentation, radiomic feature extraction, deep feature extraction, and application of machine learning models to generate diagnostic information. This is an abstract diagnostic data-analysis concept and does not recite a practical application or significantly more.
Independent claim 15
Claim 15 is rejected under 35 U.S.C. § 101 for substantially the same reasons as claim 1. Although recited as a system, the claim still centers on receiving medical data, applying machine learning models, and outputting disease-related information. The system format does not change the abstract character of the claimed subject matter.
Independent claim 39
Claim 39 is rejected under 35 U.S.C. § 101 because it recites a system/pipeline configured to segment MRI data, extract radiomic and deep features, and quantify disease-related information using machine learning models. The claim remains directed to the abstract idea of medical data analysis for diagnosis.
New independent claim 45
Claim 45 is rejected under 35 U.S.C. § 101 because it recites the same abstract diagnostic workflow, merely broadened to “at least one of organ or tissue disease.” Broadening the anatomical context does not alter the underlying abstract concept of analyzing medical data to produce a disease-related conclusion.
Dependent claims
Claims 4–6, 8-13, 18–24, 30–34, and 40–44 fall with their respective independent claims because they do not add limitations that meaningfully alter the abstract character of the claimed subject matter.
Although some dependent claims recite additional details such as:
U-shaped convolutional neural networks,
short and long residual connections,
3-dimensional convolutional blocks,
instance normalization,
transfer learning,
ensemble learning,
saliency maps,
and feature ranking,
these features are recited as additional analytic tools within the same abstract diagnostic framework. They do not recite a specific technological improvement to computer functionality or image-processing technology, and therefore do not provide significantly more than the abstract idea.
Conclusion
For the reasons set forth above, claims 1, 4–6, 8-13, 15, 18–24, 30–34, and 39–45 are rejected under 35 U.S.C. § 101 as being directed to a judicial exception without significantly more.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BENNY QUOC TIEU whose telephone number is (571)272-7490. The examiner can normally be reached Monday-Friday.
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.
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.
/BENNY Q TIEU/ Supervisory Patent Examiner, Art Unit 2682
Prosecution Insights