DETAILED ACTION
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 1-10 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more. The claim recites limitations that fall under the grouping of abstract ideas, specifically “Certain Methods of Organizing Human Activity,” such as managing medical diagnosis and classification (Step 2A, Prong One), and “Mental Processes,” including concepts such as observation, evaluation, judgment, and opinion that can be performed in the human mind or with pen and paper. In particular, the steps of receiving imaging data, identifying cell nuclei and probe indications, comparing the results to reference patterns, making a diagnostic classification (i.e., identifying a sample as containing circulating tumor cells), and generating a report represent processes that amount to collecting, analyzing, and evaluating information followed by a mental conclusion. These are all abstract processes, commonly found in diagnostic reasoning and biological data analysis.
This judicial exception is not integrated into a practical application (Step 2A, Prong Two). Although the claim involves the use of a convolutional neural network (CNN) and 3D fluorescence imaging, it does not recite any specific improvement to the underlying technology of imaging, microscopy, or neural network implementation. The claim merely applies conventional image processing and classification techniques using standard computing tools. The recited CNN is a generic machine learning model applied in a routine manner to classify probe patterns, and the processing of 3D image stacks is likewise conventional in digital microscopy. As such, the application of these technologies to identify probe deviations and generate a diagnostic report does not amount to a practical application of the abstract idea.
Furthermore, the claim does not recite additional elements that amount to significantly more than the judicial exception (Step 2B). The use of a processor, processor-readable medium, and CNN are all well-understood, routine, and conventional elements in the field of image analysis and machine learning. There is no technological innovation or unconventional arrangement of components that provides an inventive concept. Rather, the claim merely automates the abstract mental process of comparing biological imaging data with a known healthy reference using generic computing components. Thus, when viewed as an ordered combination, the claim elements amount to no more than the implementation of an abstract idea using routine computer technology, as outlined in MPEP § 2106.05(d).
Dependent claims 2-10 are also rejected under 35 U.S.C. § 101 because the claims are directed to a judicial exception without significantly more. As with claim 1, the dependent claims recite steps that can be performed with routine image processing and analysis using conventional computer technology.
Claim 2 recites identifying nuclei based on an intensity threshold in 3D image data. This is a conventional image segmentation technique and represents a basic mathematical operation applied to digital images, falling under “mathematical concepts” and “mental processes.” It does not add a meaningful limitation beyond the abstract idea.
Claim 3 describes a specific decision rule of identifying tumor cells based on a CNN-detected “gain” of probe indications compared to an expected pattern. While this adds some specificity to the diagnostic logic, it remains an abstract mental process and amounts to routine implementation of a classification algorithm. The method of comparing against a reference pattern is abstract, and the threshold-based decision logic is conventional in diagnostic systems.
Claim 4 recites classifying pixels and segmenting areas in each image to detect probe indications. This is a routine image analysis task commonly used in biomedical imaging. These are conventional processing steps that do not improve the underlying technology of image segmentation or analysis, and therefore, they do not integrate the abstract idea into a practical application.
Claim 5 limits the detection to lung cancer cells. Merely specifying a particular disease category does not transform the claim into a technological invention.
Claims 6-7 involve applying different CNNs for each 3D image or for each probe pattern. The use of multiple models remains a routine, conventional strategy in machine learning applications. The claims still recite abstract processing steps (analyzing, classifying, comparing), and the manner in which CNNs are applied is not inventive or non-conventional.
Claim 8 recites counting probe indications based on spatial position and depth. This is a conventional post-processing step that follows from the detection of features in 3D image stacks. It is routine in digital pathology and image analysis and does not add a significantly more element beyond the judicial exception.
Claim 9 recites applying the CNN in 3D space. Although this indicates the CNN may be a 3D CNN (as opposed to 2D slice-by-slice), this is a standard approach in processing volumetric image data and does not provide a technological improvement over conventional techniques.
Claim 10 recites using three specialized CNNs to reduce false positives based on different probe patterns (e.g., spreading, satellite, splitting). However, without details of how these CNNs are trained or how this setup achieves a technical improvement over prior systems, claim 10 is characterized as an abstract idea implemented with routine AI components.
Allowable Subject Matter
Claims 1-10 would be allowable if rewritten or amended to overcome the rejection(s) under 35 U.S.C. 101, set forth in this Office action.
The following is a statement of reasons for the indication of allowable subject matter:
Regarding claim 1, the prior art of record, alone or in combination, fails to teach at least “apply a convolutional neural network (CNN) to each 3D image to identify probe indications within the identified plurality of cell nuclei in each 3D image; identify the sample as containing circulating tumor cells when a comparison of the identified probe indications and reference probe indications corresponding to an expression pattern associated with chromosomal DNA of a healthy cell deviates by a pre-determined threshold”.
At best, Shetty et al (US 20140235472) teaches in ¶128 “b) hybridizing the test and reference DNA products to a tiling density DNA microarray comprising genomic DNA sequences, wherein the there is a 3-12 base pair overlap of DNA oligomeric probes; and (c) comparing the pattern and extent of hybridization of the test amplified DNA product with the reference amplified DNA product to the DNA microarray”.
At best, Edwards et al (US 6783961 B1) teaches in col 98 lines 30-40 as chromosome markers or tags (when labeled) to identify chromosomes or to map related gene positions; to compare with endogenous DNA sequences in patients to identify potential genetic disorders.
Response to Arguments
Applicant's arguments filed 10/22/2025 have been fully considered but they are not persuasive.
Regarding claims 1-10, the applicant argues that the claim “integrates the alleged abstract idea into a practical application” because the CNN processes 3D image stacks and because the system ultimately identifies circulating tumor cells (CTCs). Regarding this argument, the examiner disagrees. Step 2A, Prong 2 requires more than using the abstract idea (data analysis and diagnostic correlation), more than applying it a specific field (microscopy, oncology), and more than invoking improved results from conventional tools. It requires that the claim improve the functioning of a computer or another technology, by recited technical means, not by unclaimed advantages. Nothing in claim 1 recites a new microscopy method, a new 3D imaging technique, a new CNN architecture, a new probe chemistry, a new image-acquisition protocol, or any specific technical means that improve image formation or computer operation. The claim merely uses conventional microscopy images as input and applies a CNN to them. That is not a technical improvement. It is an application of an abstract mathematical model to a conventional dataset.
The applicant’s technical improvement arguments rely exclusively on unclaimed features. Applicant argues and points to specific paragraphs about using Z-stacks instead of single-plane images, achieving 94.72% recall vs. prior models, reducing misclassifications by 62.14%, and producing a 2D projection output from 3D input. However, none of these features are claimed. The claim does not require any specific CNN structure or architecture, any particular training procedure, any required Z-stack depth, any specific type of microscope or focal-plane sampling, any accuracy improvement, or any output format other than a “report”. The claim simply receives images, identifies nuclei, runs CNN classification, and compares probe signals to a reference threshold.
While the applicant argues that the office must treat the additional steps as “significantly more”, the examiner disagrees. The claimed imaging and CNN steps are routine, conventional, and do not constitute significantly more. Each additional step is routine in the field, such as standard microscopy workflow, routine segmentation, routine AI pattern recognition, mathematical analysis, and post-solution activity (e.g. generating a report). Under Step 2B, these elements do not provide an inventive concept. Next, while the applicant argues that the combined use of 3D stacks and CNNs produces better CTC recall, this does not recite unconventional technology. Because each recited step is routine biological, imaging, or computation operation, the claim fails Steps 2B.
Lastly, the applicant argues that the examiner does not consider the claim as a whole. The examiner disagrees. Taken as a whole, the claims still amount to nothing more than routine image acquisition, routine image processing, routine AI classification, and an ineligible diagnostic correlation.
The claims recite abstract human activity, mental processes, and mathematical analysis. The additional elements are generic and conventional, and the technical improvements as argued rely on unclaimed features. Thus, the rejection under 35 U.S.C. 101 is properly maintained.
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 KEVIN KY whose telephone number is (571)272-7648. The examiner can normally be reached Monday-Friday 9-5PM.
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.
/KEVIN KY/Primary Examiner, Art Unit 2671