DETAILED ACTION
Status of Claims
This action is in reply to the application filed on 6 September, 2024, and the communication filed on 21 March, 2025.
Claims 4, 21, 32, 36, 43, 87, 98, 108, and 109 have been amended.
Claims 3, 6 - 9, 13, 17, 19, 20, 25, 28, 30, 31, 33, 34, 44, 46 - 86, 89, 91 - 95, 97, 99 - 106, and 116 - 233 have been canceled.
Claims 1, 2, 4, 5, 10 - 12, 14 - 16, 18, 21 - 24, 26, 27, 29, 32, 35 - 43, 45, 87, 88, 90, 96, 98, and 107 - 115 are currently pending and have been examined.
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 .
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claims 1, 2, 4, 5, 10 - 12, 14 - 16, 18, 21 - 24, 26, 27, 29, 32, 35 - 43, 45, 87, 88, 90, 96, 98, and 107 - 115 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention. Claims 1 and 87 recite: generating a first and second plurality of image data by imaging one or more regions of a stained section of a biological sample, and providing the first and second plurality of image data to a trained predictive neural network to determine the presence of a biomarker in the biological sample. The claims further recite “reducing a parameter space of the first and second plurality of image data to produce a reduced first and second plurality of image data”.
However, the reduced image data is never used in the claimed process; and as such Examiner cannot determine the metes and bounds of the claims. In particular, whether the recited reduced image data or unreduced image data is used as input to the model. For example, the specification teaches that the reduced image data is used to train the model (@ 0006, 0076 as published), and that reduced image data is subsequently input to the trained model to determine a biomarker in a patient sample (@ Abstract). However, the specification also allows the image data that has not been reduced to be input to the model. (@ 0005) For example, image data from a first pass at 5X magnification is used to train a first model, and image data from a second pass at 20X magnification is used to train a second model. Features in the image data for both sets of image data may be reduced using known techniques such as PCA. (@ 0028, 0030) Appropriate correction and/or clarification is required.
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.
The following rejection is formatted in accordance with MPEP 2106.
Claim 1 is representative. Claim 1 recites:
A method of determining a presence of a biomarker in a biological sample, comprising:
obtaining a section of a biological sample, wherein the section of the biological sample has been treated with a stain;
imaging one or more regions of the stained section of the biological sample at a first resolution and a second resolution to generate a first and second plurality of image data;
reducing a parameter space of the first and second plurality of image data to produce a reduced first and second plurality of image data; and
providing the first and the second plurality of image data to a trained predictive neural network and
determining the presence of a biomarker in the biological sample as an output of the trained predictive neural network.
Claim 87 recites a system that executes the steps of the method recited in Claim 1.
Claims 1, 2, 4, 5, 10 - 12, 14 - 16, 18, 21 - 24, 26, 27, 29, 32, 35 - 43, 45, 87, 88, 90, 96, 98, and 107 - 115 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e. a law of nature, a natural phenomenon, or an abstract idea), and does not include additional elements that either: 1) integrate the abstract idea into a practical application, or 2) that provide an inventive concept – i.e. element that amount to significantly more than the abstract idea. The Claims are directed to an abstract idea because, when considered as a whole, the plain focus of the claims is on an abstract idea.
STEP 1
The claims are directed to a system and a method which are included in the statutory categories of invention.
STEP 2A PRONG ONE
The claims, as illustrated by Claim 1, recite limitations that encompass an abstract idea including:
obtaining a section of a biological sample, wherein the section of the biological sample has been treated with a stain;
imaging one or more regions of the stained section of the biological sample at a first resolution and a second resolution to generate a first and second plurality of image data;
determining the presence of a biomarker in the biological sample.
The claims, as illustrated by Claim 1, recite limitations that encompass an abstract idea within the “certain methods of organizing human activity” grouping –
managing personal behavior or relationships or interactions between people including social activities, teaching, and following rules or instructions.
The claims recite generating a diagnosis – i.e. determining the presence of a biomarker in a biological sample - based on an analysis imaging data. In particular here, the claims recite obtaining a stained section of a biological sample, and imaging regions of the stained sample at two resolutions as an extra-solution data gathering step. The specification discloses that “H & E stained slides are routinely and universally generated” in medicine (@ 0025). The slides are digitized using known systems and techniques, such as the “Aperio ScanScope System” or the “Hamamatsu Photonics Nanozoomer System” as disclosed (@ 0045, 0056). Generating a diagnosis based on data obtained about a patient is process that merely organizes this human activity. (See MPEP 2016.04 (a)(2) II C finding that “a mental process that a neurologist should follow when testing a patient for nervous system malfunctions” is a method of organizing human activity, In re Meyer, 688 F.2d 789, 791-93, 215 USPQ 193, 194-96 (CCPA 1982). As such, the claims recite an abstract idea within the certain methods of organizing human activity grouping.
The claims, as illustrated by Claim 1, also recite limitations that encompass an abstract idea within the mathematical formula or relationship grouping; including:
reducing a parameter space of the first and second plurality of image data to produce a reduced first and second plurality of image data.
The claims reduce a parameter space of image data. The specification discloses the reduction is a “dimensionality reduction using principal component analysis and k-means clustering”. @ (0024). PCA and k-means clustering techniques are old and well-known mathematical relationships. As such, the claims recite a mathematical formula or relationship.
STEP 2A PRONG TWO
The claims recite limitations that include additional elements beyond those that encompass the abstract idea above including:
providing the first and the second plurality of image data to a trained predictive neural network; and determining the presence of a biomarker in the biological sample as an output of the trained predictive neural network.
However, these additional elements do not integrate the abstract idea into a practical application of that idea in accordance with the MPEP. (see MPEP 2106.05)
The trained predictive neural network is recited at a high level of generality such that it amounts to no more than instructions to apply the abstract idea using a generic computer component. These elements merely add instructions to implement the abstract idea on a computer, and generally link the abstract idea to a particular technological environment.
In particular, the claims apply established methods of machine learning to an abstract diagnostic process in a new data environment – i.e. applying a trained machine learning model to the image data. The specification teaches that the machine learning model is known – i.e. the multiple instance learning (MIL) ResNet18 convolutional neural network – and may be trained to output diagnosis information such as the presence or absence of a biomarker; using labelled image data acquired using establish databases such as TCGA (the Cancer genome Atlas), CPTA and METABRIC cancer cohorts (@ 0031, 0037). Machine learning limitations reciting broad, functionally described, well-known techniques executed by generic and conventional computing devices does not provide a practical application of the abstract diagnostic process. “Today we hold only that patents that do no more than claim the application of generic machine learning to new data environments, without disclosing improvements to the machine learning models to be applied, are patent ineligible under §101.” (Recentive Analytics, Inc. v. Fox Corp. (Fed. Cir. 2025)).
Nothing in the claim recites specific limitations directed to an improved computer system, processor, memory, network, database or Internet. Similarly, the specification is silent with respect to these kinds of improvements. A general purpose computer that applies a judicial exception by use of conventional computer functions, as is the case here, does not qualify as a particular machine, nor does the recitation of a generic computer impose meaningful limits in the claimed process. (see Ultramercial, Inc. v. Hulu, LLC, 772 F.3d 709, 716-17 (Fed. Cir. 2014)). As such, the additional elements recited in the claim do not integrate the abstract biomarker detection process into a practical application of that process.
STEP 2B
The additional elements identified above do not amount to significantly more than the abstract biomarker detection process. Staining a section of a biological sample and imaging regions in the section are conventional technique. For example, the specification discloses generating slides and images is routine, and are well-known in the art (@ 0025).
The additional structural elements or combination of elements in the claims, other than the abstract idea per se, amount to no more than a recitation of generic computer structure (i.e. a processor, computer-readable medium with instructions). Each of the above components are disclosed in the specification as being purely conventional and/or known in the industry. Because the specification describes these additional elements in general terms, without describing particulars, Examiner concludes that the claim limitations may be broadly, but reasonably construed, as reciting well-understood, routine and conventional computer components and techniques. The specification describes the elements in a manner that indicates that they are sufficiently well-known that the specification does not need to describe the particulars in order to satisfy U.S.C. 112. Considered as an ordered combination the limitations recited in the claims add nothing that is not already present when the steps are considered individually. As such, the additional elements recited in the claim do not provide significantly more than the abstract biomarker detection process, or an inventive concept.
The dependent claims add additional features including:
those that merely serve to further narrow the abstract idea above such as:
determine the presence of the biomarker with a preset accuracy relative to genomic sequencing (Claim 2, 88);
further specifying two predictive models (Claim 4, 90);
further limiting the biomarker to a particular one or group (Claims 5, 10, 11, 12, 14, 15, 16, 18, 21, 22);
further limiting the type of section (Claim 23);
further limiting the type of neural network (Claim 24, 96);
further limiting the magnification and parameter space reduction percentage (Claim 26);
further limiting the reducing by PCA (Claim 27, 98);
further limiting the type of clustering to k-means (Claim 38, 109);
further limiting the training dataset to the top 15% of variance or top 50th percentile (Claim 39, 40, 110, 111);
further limiting the type of tissue (Claim 29, 32);
further limiting the type of stain (Claim 35);
further limiting the resolution magnification (Claim 36, 107);
further limiting the number of regions (Claim 43, 114);
further limiting the type of device with the processor (Claim 115);
those that recite additional abstract ideas such as:
clustering image data (Claim 37, 108);
averaging the predicted probability of two neural networks (Claim 42, 113);
those that recite well-understood, routine and conventional activity or computer functions such as:
determining a biomarker label using genomic sequencing (Claims 41, 112);
removing nodes of a neural network during training (Claim 45);
those that recite insignificant extra-solution activities; or those that are an ancillary part of the abstract idea.
The limitations recited in the dependent claims, in combination with those recited in the independent claims add nothing that integrates the abstract idea into a practical application, or that amounts to significantly more. These elements merely narrow the abstract idea, recite additional abstract ideas, or append conventional activity to the abstract process. As such, the additional element do not integrate the abstract idea into a practical application, or provide an inventive concept that transforms the claims into a patent eligible invention.
The apparatus claims are no different from the method claims in substance. “The equivalence of the method, system and media claims is readily apparent.” “The only difference between the claims is the form in which they were drafted.” (Bancorp). The method claims recite the abstract idea implemented on a generic computer, while the apparatus claims recite generic computer components configured to implement the same idea. Specifically, Claims 87, 88, 90, 96, 98, and 107 - 115 merely add the generic hardware noted above that nearly every computer will include. The apparatus claim’s requirement that the same method be performed with a programmed computer does not alter the method’s patentability under U.S.C. 101 (In re Grams). Therefore, the claims are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
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.
Claims 1, 4, 10, 11, 14, 15, 18, 21 - 24, 29, 35 - 37, 42, 43, 45, 87, 90, 96, 107, 108 and 113 – 115 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Yip et al.: (US PGPUB 2020/0258223 A1).
CLAIMS 1 and 87
Yip discloses a system and method for determining biomarkers from histopathology slides images that includes the following limitations:
A method of determining a presence of a biomarker in a biological sample; (Yip 0019)
Yip discloses a computer-implemented method of identifying biomarkers in a digital image of a stained slide of target tissue.
comprising: obtaining a section of a biological sample, wherein the section of the biological sample has been treated with a stain; imaging one or more regions of the stained section of the biological sample at a first resolution and a second resolution to generate a first and second plurality of image data; (Yip 0009, 0018, 0108, 0115, 0137, 0190, 0265).
Yip discloses that a biopsy is performed to collect tissue samples from a patient and a medical lab generates histopathology images, at multiple resolutions or magnifications, from the tissue sample using known staining techniques such as H&E staining. Notably, the specification in the present application discloses that “H & E stained slides are routinely and universally generated” in medicine (@ 0025); and that the slides are digitized using known systems and techniques, such as the “Aperio ScanScope System” or the “Hamamatsu Photonics Nanozoomer System” as disclosed (@ 0045, 0056).
reducing a parameter space of the first and second plurality of image data to produce a reduced first and second plurality of image data; (Yip 0018, 0028, 0035 – 0037, 0413).
Yip discloses that a whole slide image (WSI) is separated or partitioned into a plurality of tile images, and a tile selection process infers a class status for each tile, and discards tiles not corresponding to a desired class - i.e. reducing a parameter space of the image data. Yip further discloses dimensionality reduction techniques in the neural network.
providing the first and the second plurality of image data to a trained predictive neural network and determining the presence of a biomarker in the biological sample as an output of the trained predictive neural network; (Yip 0010 - 0013, 0018 – 0020, 0051.
Yip discloses that computer vision tools, such as deep learning applications, are trained to analyze whole slide images in medical diagnostic applications, including to identify a plurality of different biomarkers. Yip trains a predictive model such as a neural network to identify a plurality of different biomarkers in a target tissue from digitized slide images made at different resolutions of magnifications.
With respect to CLAIM 87, Yip discloses the following computer components configured to execute the method of Claim 1:
A computer system configured to determine a presence of a biomarker in a biological sample, comprising: one or more processors; and a non-transitory computer readable storage medium including software stored thereon, wherein the software comprises executable instructions that, as a result of execution, cause the one or more processors of the computer system to [perform the method of Claim 1]; (Yip 0049, 0113, 0411, 0412).
CLAIMS 4, 10, 11, 14, 15, 18, 21, 22, 23, 24, 29, 35, 36, 42, 43, 45, 90, 96, 107, 113, 114, 115
Yip discloses the limitations above relative to Claims 1 and 87. Additionally, Yip discloses the following limitations:
wherein the trained predictive neural network comprises a first predictive model trained on the first plurality of image data and a second predictive model neural network trained on the second plurality of image data; (Yip 0025, 0130, 0131, 0196).
With respect to Claims 4 and 90, Yip discloses training one or mode models based on the biomarker to be identified using one or more training data sets.
wherein the biomarker comprises a presence of at least one of a microsatellite instable (MSI) defect or a mismatch repair (MMR) gene defect, wherein the MMR gene defect includes at least one of POLE, MLH1, MLH3, MGMT, MSH6, MSH3, MSH2, PMS1, or PMS2; wherein the biomarker comprises a presence of high tumor mutational burden; (Yip 0260).
With respect to Claims 10 and 11,Yip discloses numerous biomarkers including microsatellite instability (MSI) and a high tumor mutational burden.
wherein the biomarker comprises a presence of homologous recombination deficiency (HRD); wherein the biomarker comprises a presence of HRD negative or homologous recombination proficiency (HRP) or HRD positive; (Yip 0043, 0105, 0107, 0134).
With respect to Claims 14 and 15,Yip discloses numerous biomarkers including HRD, HRD negative or HRD positive.
wherein the biomarker comprises a presence of a genomic instability score (GIS) including one or more of:
patterns or signatures of loss of heterozygosity (LOH);
a number of telomeric imbalances corresponding to a number of regions with allelic imbalance that extend to a sub-telomere but not across a centromere; or
large-scale state transitions (LST) corresponding to chromosome breaks,
wherein the telomeric imbalances include telomeric allelic imbalances (TAI),
wherein the chromosome breaks include deletions, translocations, and inversions; (Yip 0105, 0107, 0126).
With respect to Claim 18, Yip discloses loss of heterozygosity and chromosomal instability construed as including chromosome breaks.
wherein the biomarker comprises a presence of potentially actionable genomic alterations, including in at least one of: ABL1,AKT1, ALK, APC, ATM, BRAF, RET, ROS, KRAS, NRAS, HRAS, RAF1, IDH1, IDH2,JAK1/2/3,JAK1, JAK2, JAK3, KDR, KIT, MAP2K1, MAPK, MTAP, MET, NTRK, NTRK1, CCNE, CCNE1, CDK4/6, CCND1/2, AR, PDGFRA, PIK3CA, PTEN, CDH1, CDKN2A, CSF1R, CTNNB1, DDR2, DNMT3A, EGFR, ERBB2, ERBB3, ERBB4, HER2/NEU, EZH2, FBXW7, FGF, FGFR, FGFR1, FGFR2, FGFR3, FLT3, FOXL2, GNA11, GNAQ, GNAS, HNF1A, MLH1, MPL, MSH6, NOTCHI, VEGFA, HGF, NPM1, PTPN11, RB1, SMAD4, SMARCB1, SMO, SRC, STK11, TP53, TSC1, VHL, ESR1, MAPK3K1, GATA3, CDH1, FBXW7, NF1, KMT2C, CTNNB1, GNA13, GNAQ, GNA11, RRAS2, KIF1A, or NRG1KIF5B; (Yip 0179);
wherein the biomarker indicates at least one of immunohistochemical alterations, and copy number alterations, deletions, amplifications, fusions, mutation clusters, mutation signatures or any combination thereof a genome of the biological sample; (Yip 0163, 0179).
With respect to Claims 21 and 22, Yip discloses biomarkers including at least EGFR, copy number variations, amplifications, and mutations.
wherein the section of the biological sample comprises a paraffin embedded section, a formalin fixed section, a frozen section, a fresh section, or a combination thereof; (Yip 0340).
With respect to Claim 23, Yip discloses frozen sections.
wherein the trained predictive neural network comprises a convolutional neural network; (Yip 0010).
With respect to Claim 24, Yip discloses a convolutional neural network.
wherein the biological sample comprises healthy tissue, unhealthy tissue, or any combination thereof tissues; (Yip 0004).
With respect to Claim 29, Yip discloses tumor tissue samples – i.e. unhealthy tissue.
wherein the stain comprises a hematoxylin and eosin stain; (Yip 0009, 0010).
With respect to Claim 35, Yip discloses widely used H&E stain.
wherein the first resolution comprises a low magnification of 5X magnification or l0X magnification, and wherein the second resolution comprises a high magnification of 20X magnification or 40X magnification; (Yip 0115, 0190).
With respect to Claims 36 and 107, Yip discloses images at low magnification @ 10X and high magnification @ 40X
wherein the output of the trained predictive neural network comprises an averaged predicted probability score of the first and second predictive neural network; (Yip 0374).
With respect to Claims 42 and 113, Yip discloses aggregating results from a tile-by-tile classification to obtain a slide classification – i.e. an average.
wherein the one or more regions comprise at least 100 regions and at most 10,000 regions; (Yip 0011, 0307).
With respect to Claims 43 and 114, Yip discloses 217 non-overlapping tiles – i.e. regions.
comprising removing one or more nodes of the trained predictive neural network when the trained predictive neural network is provided an input of the reduced first and second plurality of image data; (Yip 0413).
With respect to Claim 45, Yip discloses neural network trained using node dropout techniques – i.e. removing a node.
wherein the one or more processors comprise one or more processors of a smart phone, tablet, laptop, desktop, server, cloud computing architecture, or any combination thereof; (Yip 0113).
With respect to Claim 115, Yip discloses a computing device including a computer, tablet, mobile computing device, server, or cloud server.
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.
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 nonobviousness.
Claims 2 and 88 are rejected under 35 U.S.C. 103 as being unpatentable over Yip et al.: (US PGPUB 2020/0258223 A1) in view of Roessler et al.: (US PGPUB 2023/0196803 A1).
CLAIMS 2 and 88
Yip discloses the limitations above relative to Claims 1 and 87. With respect to the following limitations:
wherein the trained predictive neural network is configured to determine the presence of the biomarker with a preset accuracy, wherein the preset accuracy is at least 80% of an accuracy of genomic sequencing; (Roessler 0006, 0008, 0040, 0045, 0101, 0110, Table 1).
Yip discloses training the model to achieve a “higher accuracy” (@ 0377), but does not disclose a predetermined accuracy of at least 80 % compared to genomic sequencing (i.e. a ground truth label). Roessler discloses a system and method for classifying histological stain patterns on slides using a convolutional neural network trained to identify the presence or distribution of biomarkers within a tissue section depicted on a slide. Roessler discloses an iterative training process that is performed until the classification error is below a threshold, including an accuracy level of at least 80%. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the biomarker detection system of Yip so as to have included training the neural network to achieve at least 80% accuracy, in accordance with the teaching of Roessler, in order to insure accurate results.
Claims 5, 12 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Yip et al.: (US PGPUB 2020/0258223 A1) in view of Official Notice
CLAIMS 5, 12 and 16
Yip discloses the limitations above relative to Claim 1. With respect to the following limitations:
wherein the biomarker comprises loss of chromosome 9p;
wherein the biomarker comprises a presence of hypermutator mutational signatures selected from: POLE including POLE and MSI-COSMIC14;MSI combined MSI-COSMIC15, MSI-COSMIC20, MSI-COSMIC21, MSI-COSMIC26, and MSI - COSMIC6;
wherein the biomarker comprises a presence of at least one of breast cancer gene (BRCA)-1 mutation or BRCA-2 mutation.
Yip does not disclose these biomarkers; nonetheless, they are old and well-known diagnostic biomarkers, a fact for which Examiner takes Official Notice. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the biomarker detection system of Yip so as to have included detecting any number of biomarkers, including those recited above, in accordance with the Official Notice Taken, in order to determine the presence of biomarkers known to indicate a medical condition.
Claims 26, 37 and 108 are rejected under 35 U.S.C. 103 as being unpatentable over Yip et al.: (US PGPUB 2020/0258223 A1) in view of Pace et al.: (US PGPUB 2015/0142732 A1) and in view of Nguyen et al.: (US PGPUB 2023/0016472 A1)
CLAIM 26
Yip discloses the limitations above relative to Claim 1. With respect to the following limitations:
wherein the parameter space of the first and second plurality of image data indicates tiles at 5x magnification; (Pace 0041).
Yip discloses 20X and 40X magnification, but not 5X magnification. Pace discloses a system and method for continuous image analysis of a slide that includes 5X magnification. It would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the biomarker detection system of Yip so as to have included 5X magnification, in accordance with the teachings of Pace, in order to provide images at different resolutions. With respect to the following limitation:
wherein the parameter space of the first and second plurality of image data is reduced to 25%, 10%, or 5% of the tiles carrying predictive information; (Nguyen 0055)
Yip discloses reducing the number of tile, but does not specify a particular percentage. Nguyen discloses a system and method for digital pathology image analysis that includes reducing the number of tiles to 25%, 10% or 5%. It would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the biomarker detection system of Yip so as to have included reducing the number of tiles by a percentage, in accordance with the teachings of Nguyen, in order to reduce computational burden.
CLAIM 37 and 108
The combination of Yip/Pace/Nguyen discloses the limitations above relative to Claim 26 and 87. With respect to the following limitations:
clustering the reduced first and second plurality of image data to generate a first and second clustered dataset to perform training that produces the trained predictive neural network; (Yip 0019, 0038).
With respect to Claims 37 and 108, Yip discloses clustering image training data.
Claims 27, 38, 40, 41, 98, 109, 111 and 112 are rejected under 35 U.S.C. 103 as being unpatentable over Yip et al.: (US PGPUB 2020/0258223 A1) in view of Pace et al.: (US PGPUB 2015/0142732 A1) and in view of Nguyen et al.: (US PGPUB 2023/0016472 A1) in view of Barker et al.: (US PGPUB 2018/0374210 A1)
CLAIMS 27, 38, 40, 98, 109 and 111
The combination of Yip/Pace/Nguyen discloses the limitations above relative to Claims 26, 87 and 108 respectively. With respect to the following limitations:
wherein reducing is completed by principal component analysis; wherein clustering is completed by k-means clustering; (Barker 0094);
wherein the trained predictive neural network is trained with the first and second clustered dataset and corresponding biomarker label of the biological sample, wherein the first and second clustered dataset comprise clustered datasets with silhouette coefficients across all clusters of the first and second clustered dataset; (Barker 0094).
Barker discloses a computerized analysis of digital pathology images using tiles. The data set is reduced using PCA and k-means clustering techniques that are old and well-known, and then used to train the model. K-means clustering inherently includes determining the optimal number of clusters using silhouette coefficients. It would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the biomarker detection system of Yip so as to have included reducing the number of tiles using PCA and clustering using k-means, in accordance with the teachings of Barker, in order to reduce computational burden. Setting silhouette coefficients within the top 50th percentile is an ordinary design choice that would be obvious to one of ordinary skill in the art.
CLAIMS 41 and 112
The combination of Yip/Pace/Nguyen/Barker discloses the limitations above relative to Claims 40 and 111. With respect to the following limitations:
wherein the corresponding biomarker label of the biological sample is determined by genomic sequencing; (Yip 0014, 0038, 0175).
With respect to Claims 41 and 112, Yip discloses using genomic sequencing as ground truth for training the model.
Claim 32 is rejected under 35 U.S.C. 103 as being unpatentable over Yip et al.: (US PGPUB 2020/0258223 A1) in view of Smith et al.: (US PGPUB 2023/0281819 A1).
CLAIM 32
Yip discloses the limitations above relative to Claims 29. With respect to the following limitations:
wherein the unhealthy tissue includes virally infected tissue that comprises one or more of Epstein-Barr virus (EBV), Hepatitis B virus (HBV), Hepatitis C virus (HCV), Human immunodeficiency virus (HIV), Human herpes virus 8 (HHV-8), and/or Human T-cell leukemia virus type corresponding to human T-lymphotropic virus (HTLV-1); (Smith 0003, 0026, 0027, 0029, 0036).
Yip does not disclose images of tissues infected with a virus; however, Smith does. Smith discloses detecting a virus using microscopy slide images and automated image analysis using a trained neural network to detect a virus in the image. It would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the biomarker detection system of Yip so as to have included images of viruses, in accordance with the teachings of Smith, in order to allow detection of viruses. The viruses in Smith broadly encompass known viruses including the recited EBV, HIV, hepatitis, herpes and leukemia, and renders them obvious.
Claim 39 is rejected under 35 U.S.C. 103 as being unpatentable over Yip et al.: (US PGPUB 2020/0258223 A1) in view of Pace et al.: (US PGPUB 2015/0142732 A1) and in view of Nguyen et al.: (US PGPUB 2023/0016472 A1) in view of Pourmohammad et al.: (US PGPUB 2019/0096217 A1 A1).
CLAIM 39
The combination of Yip/Pace/Nguyen discloses the limitations above relative to Claims 37. With respect to the following limitations:
wherein the trained predictive neural network is trained with the clustered datasets that represent the top 15% of a variance between clustered datasets of the first and second clustered datasets and corresponding biomarker labels; (Pourmohammad 0273).
Yip discloses reducing clustered training datasets by discarding data that is not relevant to the biomarker identification, but does not expressly disclose selecting data that represents a percentage of the variance, in particular 15%, from the ground truth biomarker label. Pourmohammad teaches a risk analysis system that uses a trained machine learning classifier. When training the classifier, not all of the features in the data are important to the outcome. Like Yip, Pourmohammad selects features that represent a preselected percent of the most important features. It would have been obvious to one of ordinary skill in the art, before the effective filing data of the claimed invention, to have modified the biomarker detection system of Yip so as to have included selecting data clusters that represent a preselected percentage of the variance, in accordance with the teachings of Pourmohammad, in order to reduce processing time. Pourmohammad uses 10% as an example percentage; however, 15% would be an obvious modification within a relevant range.
CONCLUSION
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US PGPUB 2020/0377879 A1 to Meyerson et al. discloses detecting biomarkers in cancer cells from histological slides, including deletions in chromosome 9p.
US PGPUB 2021/0073986 A1 to Kapur et al. discloses a system and method for processing H&E stained slide images using machine learning to detect biomarkers.
US PGPUB 2022/0351370 A1 to Wang et al. discloses a system and method for processing H&E stained slide images using machine learning to determine a diagnosis result.
US PGPUB 2023/0245303 A1 to Miller et al. discloses a system and method for processing H&E stained slide images using machine learning to detect biomarkers.
US PGPUB 2023/0377155 A1 to Raharja et al. discloses a system and method for processing H&E stained slide images using machine learning to detect biomarkers including POLE.
“Deep Learning for Whole Slide Image Analyses: An Overview”; Dimitriou et al. 22 November, 2019 discloses applying deep learning to whole slide images to detect biomarkers.
“Introduction to Digital Image Analysis in Whole Slide Imaging: A White Paper from Digital Pathology Association”; Aeffner et al.; 8 March, 2019 discloses applying machine learning to whole slide images to detect biomarkers.
Any inquiry of a general nature or relating to the status of this application or concerning this communication or earlier communications from the Examiner should be directed to John A. Pauls whose telephone number is (571) 270-5557. The Examiner can normally be reached on Mon. - Fri. 8:00 - 5:00 Eastern. If attempts to reach the examiner by telephone are unsuccessful, the Examiner’s supervisor, Robert Morgan can be reached at (571) 272-6773.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://portal.uspto.gov/external/portal/pair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866.217.9197.
Official replies to this Office action may now be submitted electronically by registered users of the EFS-Web system. Information on EFS-Web tools is available on the Internet at: http://www.uspto.gov/patents/process/file/efs/guidance/index.jsp. An EFS-Web Quick-Start Guide is available at: http://www.uspto.gov/ebc/portal/efs/quick-start.pdf.
Alternatively, official replies to this Office action may still be submitted by any one of fax, mail, or hand delivery. Faxed replies should be directed to the central fax at (571) 273-8300. Mailed replies should be addressed to “Commissioner for Patents, PO Box 1450, Alexandria, VA 22313-1450.” Hand delivered replies should be delivered to the “Customer Service Window, Randolph Building, 401 Dulany Street, Alexandria, VA 22314.”
/JOHN A PAULS/Primary Examiner, Art Unit 3683
Date: 5 November, 2025