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 .
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 12/05/2025 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
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 1-20 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) without significantly more. Claims 1-14 and 15-16 are drawn to methods and claims 17-20 are drawn to a system, each of which is within the four statutory categories. Claims 1-20 are further directed to an abstract idea on the grounds set out in detail below. As discussed below, the claims do not include additional elements that are sufficient to amount to significantly more than the abstract idea because the additional computer elements, which are recited at a high level of generality, provide conventional computer functions that do not add meaningful limits to practicing the abstract idea (Step 1: YES).
Step 2A:
Prong One:
Claim 1 recites a computer-implemented method for processing at least one digital medical image to predict a first biomarker, the method comprising:
1) receiving the at least one a) digital medical image of one or more tissues of a patient, the at least one digital medical image including a plurality of tiles;
2) analyzing, via b) a foundation model, the plurality of tiles to determine an embedding vector for each of the plurality of tiles, the foundation model having been trained to predict embedding vectors at a tile-level based on a plurality of digital medical images; and
3) analyzing, via an aggregator model, the embedding vector for each of the plurality of tiles to predict the first biomarker of the digital medical image, wherein the aggregator model includes an attention mechanism configured to aggregate the embedding vector for each of the plurality of tiles into at least one slide-level prediction.
Claim 1 recites, in part, performing the steps of 1) receiving the at least one medical image of one or more tissues of a patient, the at least one medical image including a plurality of tiles, 2) analyzing the plurality of tiles to determine an embedding vector for each of the plurality of tiles, and 3) analyzing, via an aggregator model, the embedding vector for each of the plurality of tiles to predict the first biomarker of the medical image, wherein the aggregator model includes an attention mechanism configured to aggregate the embedding vector for each of the plurality of tiles into at least one slide-level prediction. These steps correspond to Certain Methods of Organizing Human Activity, more particularly, managing personal behavior or relationships or interactions between people (including following rules or instructions). For example, the claim recites how one could assess a medical image to predict a biomarker.
Claim 1 recites, in part, performing the step of 3) analyzing, via an aggregator model, the embedding vector for each of the plurality of tiles to predict the first biomarker of the medical image, wherein the aggregator model includes an attention mechanism configured to aggregate the embedding vector for each of the plurality of tiles into at least one slide-level prediction. This step corresponds to Mathematical Concepts.
Going forward, the abstract ideas above will be considered as a singular abstract idea for further analysis. Independent claim 17 recites similar limitations and is/are also directed to an abstract idea under the same analysis.
Claim 15 recites a method for training an aggregator model to predict at least one biomarker, comprising:
4) receiving a plurality of a) digital medical images associated with a plurality of patients;
5) receiving genomic abnormality data associated with the plurality of patients; and
h) training the aggregator model to 6) predict the at least one biomarker based on the plurality of digital medical images and the genomic abnormality data.
Claim 15 recites, in part, performing the steps of 4) receiving a plurality of medical images associated with a plurality of patients, 5) receiving genomic abnormality data associated with the plurality of patients, and 6) predict the at least one biomarker based on the plurality of medical images and the genomic abnormality data. These steps correspond to Certain Methods of Organizing Human Activity, more particularly, managing personal behavior or relationships or interactions between people (including following rules or instructions). For example, the claim recites how one could assess a medical image to predict a biomarker.
Depending claims 2-14, 16, and 18-20 include all of the limitations of claims 1, 15, and 17, and therefore likewise incorporate the above described abstract idea. Depending claims 4-10, 12-13, 18-20 add additional functional steps to the claims, where claims 5, 7-8, 13, and 18-19 add additional elements to the claims in the form of training limitations. These additional elements are further addressed below in Prong Two. Additionally, the limitations of depending claims 2-3, 11, 14, and 16 further specify elements from the claims from which they depend on without adding any additional steps. These additional limitations only further serve to limit the abstract idea. Thus, depending claims 2-14, 16, and 18-20 are nonetheless directed towards fundamentally the same abstract idea as independent claims 1, 15, and 17 (Step 2A (Prong One): YES).
Prong Two:
This judicial exception is not integrated into a practical application. In particular, the claims recite the additional elements of – using a) digital medical image(s), b) a foundation model, the foundation model having been trained to predict embedding vectors at a tile-level based on a plurality of digital medical images, c) at least one memory storing instructions (from claim 17), d) at least one processor configured to execute the instructions to perform operations (from claim 17), e) a foreground detection model, the foreground detection model being a fully convolutional neural network trained to detect foreground in the plurality of tiles (from claims 5 and 18), f) a sizing model, the sizing model having been trained to predict the tumor size based on a plurality of embedding vectors (from claims 7 and 19), g) a purity model, the purity model having been trained to predict the tumor purity based on a plurality of embedding vectors (from claims 8 and 19), and h) training the aggregator model, using the training data, to infer the first biomarker of the digital medical image based on the respective one or more digital medical images (from claims 13 and 15) to perform the claimed steps.
The a) digital medical image(s), c) at least one memory storing instructions, and d) at least one processor configured to execute the instructions to perform operations in these steps are recited at a high-level of generality (i.e., as generic components performing generic computer functions) such that they amount to no more than mere instructions to apply the exception using generic computer components (see: Applicant’s specification, paragraph [0108] where the processor can be generic and paragraph [0028] where the memory can be generic, see MPEP 2106.05(f)).
Additionally, the training limitations (b) a foundation model, the foundation model having been trained to predict embedding vectors at a tile-level based on a plurality of digital medical images, e) a foreground detection model, the foreground detection model being a fully convolutional neural network trained to detect foreground in the plurality of tiles, f) a sizing model, the sizing model having been trained to predict the tumor size based on a plurality of embedding vectors, g) a purity model, the purity model having been trained to predict the tumor purity based on a plurality of embedding vectors, and h) training the aggregator model, using the training data, to infer the first biomarker of the digital medical image based on the respective one or more digital medical images) in these steps are recited at a high-level of generality (i.e., as generic components performing generic computer functions) such that they amount to no more than mere instructions to apply the exception using generic computer components (see MPEP 2106.05(f)).
Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation and do not impose a meaningful limit to integrate the abstract idea into a practical application.
Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea (Step 2A (Prong Two): NO).
Step 2B:
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of using a) digital medical image(s), b) a foundation model, the foundation model having been trained to predict embedding vectors at a tile-level based on a plurality of digital medical images, c) at least one memory storing instructions, d) at least one processor configured to execute the instructions to perform operations, e) a foreground detection model, the foreground detection model being a fully convolutional neural network trained to detect foreground in the plurality of tiles, f) a sizing model, the sizing model having been trained to predict the tumor size based on a plurality of embedding vectors, g) a purity model, the purity model having been trained to predict the tumor purity based on a plurality of embedding vectors, and h) training the aggregator model, using the training data, to infer the first biomarker of the digital medical image based on the respective one or more digital medical images to perform the claimed steps amounts to no more than insignificant extra-solution activity in the form of WURC activity (well-understood, routine, and conventional activity), a general linking to a particular technological field, or mere instructions to apply the exception using a generic computer component that does not offer “significantly more” than the abstract idea itself because the claims do not recite an improvement to another technology or technical field, an improvement to the functioning of any computer itself, or provide meaningful limitations beyond generally linking an abstract idea to a particular technological environment. It should be noted that the claims do not include additional elements that amount to significantly more than the judicial exception because the Specification recites mere generic computer components, as discussed above that are being used to apply certain method steps of organizing human activity or certain mathematical steps. Specifically, MPEP 2106.05(f) recites that the following limitations are not significantly more:
Adding the words "apply it" (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, e.g., a limitation indicating that a particular function such as creating and maintaining electronic records is performed by a computer, as discussed in Alice Corp., 134 S. Ct. at 2360, 110 USPQ2d at 1984 (see MPEP § 2106.05(f)).
The current invention generates predicts biomarkers utilizing a) digital medical image(s), c) at least one memory storing instructions, and d) at least one processor configured to execute the instructions to perform operations, thus these computing components are adding the words “apply it” with mere instructions to implement the abstract idea on a computer.
Additionally, the current invention generates predicts biomarkers utilizing training steps (b) a foundation model, the foundation model having been trained to predict embedding vectors at a tile-level based on a plurality of digital medical images, e) a foreground detection model, the foreground detection model being a fully convolutional neural network trained to detect foreground in the plurality of tiles, f) a sizing model, the sizing model having been trained to predict the tumor size based on a plurality of embedding vectors, g) a purity model, the purity model having been trained to predict the tumor purity based on a plurality of embedding vectors, and h) training the aggregator model, using the training data, to infer the first biomarker of the digital medical image based on the respective one or more digital medical images), thus these steps are adding the words “apply it” with mere instructions to implement the abstract idea using machine learning.
Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. The claims are not patent eligible (Step 2B: NO).
Claims 1-20 are therefore rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
(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 1-4, 6, 13-17, and 20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by U.S. 2024/0273718 to Probert et al.
As per claim 1, Probert et al. teaches a computer-implemented method for processing at least one digital medical image to predict a first biomarker, (see: paragraph [0071] where there is such a method) the method comprising:
--receiving the at least one digital medical image of one or more tissues of a patient, (see: 212 of FIG. 2B where there is reception of at least one image from a patient) the at least one digital medical image including a plurality of tiles; (see: paragraph [0032] where the medical image has a plurality of tiles)
--analyzing, via a foundation model, the plurality of tiles to determine an embedding vector for each of the plurality of tiles, (see: paragraph [0032] where there is first module (foundation model) of the machine learning model which is trained to generate tile-level embeddings based on a plurality of tiles of the medical image. Also see: paragraph [0227] where the embeddings can be a vector representation. There is analysis here of a plurality of tiles to determine an embedding vector for each of the tiles) the foundation model having been trained to predict embedding vectors at a tile-level based on a plurality of digital medical images; (see: paragraph [0032] where the first module (foundation model) has been trained to predict embeddings at a tile-level. Also see: paragraph [0227] where the embeddings can be a vector representation) and
--analyzing, via an aggregator model, the embedding vector for each of the plurality of tiles to predict the first biomarker of the digital medical image, (see: paragraph [0032] where the tile-level embeddings are input into a second module (aggregator model) of the machine learning model. Also see: paragraph [0006] where there is prediction an activity of the molecular analyte. Also see: paragraph [0073] where the activity data includes gene expression data and paragraph [0071] where there is identification of one or more relevant biomarkers) wherein the aggregator model includes an attention mechanism configured to aggregate the embedding vector for each of the plurality of tiles into at least one slide-level prediction (see: paragraph [0033] where at least a subset of the tile-level embeddings are averaged/aggregated prior to being input into the second module (aggregator model) of the machine learning model. Also see: paragraph [0034] where the second module comprises an attention mechanism).
As per claim 2, Probert et al. teaches the method of claim 1, see discussion of claim 1. Probert et al. further teaches wherein the at least one digital medical image includes at least one of a whole slide image (WSI), a hematoxylin and eosin (H&E) stain, an immunohistochemistry (IHC) slide, an immunofluorescent slide, or a Computerized Topography (CT) scan (see: paragraph [0339] where there is a whole slide image and a hematoxylin and eosin (H&E) stain which is included as the image).
As per claim 3, Probert et al. teaches the method of claim 1, see discussion of claim 1. Probert et al. further teaches wherein the biomarker is at least one of a genetic alteration biomarker, a histologic-subtype biomarker, a treatment-associated biomarker, a pathway biomarker, a chromosomal instability biomarker, a transcriptomic biomarker, a proteomic biomarker, an epigenetic biomarker, or a prognostic biomarker (see: paragraph [0297] where there is histological subtyping. Also see: paragraph [0188] where there is an IHC biomarker which is used for a drug within the context of a patient cohort (a treatment-associated biomarker)).
As per claim 4, Probert et al. teaches the method of claim 1, see discussion of claim 1. Probert et al. further teaches:
--determining, based on the first biomarker, a diagnosis of a subtype of cancer (see: paragraph [0340] where there is a determining of a cancer subtype classification).
As per claim 6, Probert et al. teaches the method of claim 1, see discussion of claim 1. Probert et al. further teaches:
--determining, by the aggregator model, a second biomarker for the digital medical image, the second biomarker being a different biomarker type than the first biomarker (see: paragraphs [0071] and [0099] where there is a determination of one or more biomarkers. There is a determination of at least a second biomarkers here which is different from the first one as determining one or more biomarkers means determining separate biomarkers).
As per claim 13, Probert et al. teaches the method of claim 1, see discussion of claim 1. Probert et al. further teaches wherein the aggregator model has been trained by:
--receiving, as training data, a plurality of digital medical images associated with a plurality of patients and genomic abnormality data associated with the plurality of patients; (see: paragraph [0073] where the activity data is from a plurality of patients and it includes gene expression data. Also see: paragraphs [0192] and [0196] where there is training of a model using this activity data from a cohort, therefore this data is being received. The received activity data here includes gene expression data/genomic abnormality data) and
--training the aggregator model, using the training data, to infer the first biomarker of the digital medical image based on the respective one or more digital medical images (see: 206 where there is such a training step for the second model (aggregator model) to predict at least one biomarker/molecular analyte based on a plurality of embeddings (information based on the plurality of digital images) and activity data (genomic abnormality data)).
As per claim 14, Probert et al. teaches the method of claim 13, see discussion of claim 13. Probert et al. further teaches wherein the training data further includes at least one of histological subtype data, treatment association data, genomic pathway data, or chromosomal instability data (see: paragraph [0183] where there is histological embedding data being used to train a model. Also see: paragraph [0297] where there is histological subtyping data).
As per claim 15, Probert et al. teaches a method for training an aggregator model to predict at least one biomarker, comprising:
--receiving a plurality of digital medical images associated with a plurality of patients; (see: 202 of FIG. 2A where there is reception of a plurality of images from a first cohort)
--receiving genomic abnormality data associated with the plurality of patients; (see: paragraph [0073] where the activity data is from a plurality of patients and it includes gene expression data. Also see: paragraphs [0192] and [0196] where there is training of a model using this activity data from a cohort, therefore this data is being received. The received activity data here includes gene expression data/genomic abnormality data) and
--training the aggregator model to predict the at least one biomarker based on the plurality of digital medical images and the genomic abnormality data (see: 206 where there is such a training step for the second model (aggregator model) to predict at least one biomarker/molecular analyte based on a plurality of embeddings (information based on the plurality of digital images) and activity data (genomic abnormality data)).
As per claim 16, Probert et al. teaches the method of claim 15, see discussion of claim 15. Probert et al. further teaches wherein:
--the at least one digital medical image includes at least one of a whole slide image (WSI), a hematoxylin and eosin (H&E) stain, an immunohistochemistry (IHC) slide, an immunofluorescent slide, or a Computerized Topography (CT) scan; (see: paragraph [0339] where there is a whole slide image and a hematoxylin and eosin (H&E) stain which is included as the image) and
--the biomarker is at least one of a genetic alteration biomarker, a histologic-subtype biomarker, a treatment-associated biomarker, a pathway biomarker, a chromosomal instability biomarker, a transcriptomic biomarker, a proteomic biomarker, an epigenetic biomarker, or a prognostic biomarker (see: paragraph [0297] where there is histological subtyping. Also see: paragraph [0188] where there is an IHC biomarker which is used for a drug within the context of a patient cohort (a treatment-associated biomarker)).
As per claim 17, claim 17 is similar to claim 1 and is therefore rejected in a similar manner to claim 1. Probert et al. further teaches a system for processing at least one digital medical image to predict a first biomarker, comprising:
--at least one memory storing instructions; (see: paragraph [0006] where there is a memory storing instructions) and
--at least one processor configured to execute the instructions to perform operations (see: paragraph [0006] where there is a processor executing instructions).
As per claim 20, claim 20 is similar to claim 13 and is therefore rejected in a similar manner to claim 13.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
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.
Claims 5 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. 2024/0273718 to Probert et al. in view of U.S. Patent No. 12,361,542 to Braman et al.
As per claim 5, Probert et al. teaches the method of claim 1, see discussion of claim 1. Probert et al. further teaches wherein analyzing the plurality of tiles to determine the embedding vector for each of the plurality of tiles further includes:
--analyzing, via a foreground detection model, the plurality of tiles to select a plurality of foreground tiles, (see: paragraph [0339] where there is extraction/selection of a plurality of foreground tiles from a plurality of tiles) and
--analyzing, via the foundation model, the plurality of tiles to determine an embedding vector for each of the plurality of tiles, (see: paragraph [0032] where there is first module (foundation model) of the machine learning model which is trained to generate tile-level embeddings based on a plurality of tiles of the medical image. Also see: paragraph [0227] where the embeddings can be a vector representation. There is analysis here of a plurality of tiles to determine an embedding vector for each of the tiles) wherein the plurality of tiles comprises the plurality of foreground tiles (see: paragraph [0339] where the tiles include foreground tiles).
Probert et al. may not further, specifically teach the foreground detection model being a fully convolutional neural network trained to detect foreground in the plurality of tiles.
Braman et al. teaches:
--the foreground detection model being a fully convolutional neural network trained to detect foreground in the plurality of tiles (see: column 14, line 55 to column 15, line 29 where there is such a fully convolutional neural network. The model being for foreground detection was already taught in the Probert et al. reference above).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to substitute the foreground detection model being a fully convolutional neural network trained to detect foreground in the plurality of tiles as taught by Braman et al. for the model as disclosed by Probert et al. since each individual element and its function are shown in the prior art, with the difference being the substitution of the elements. In the present case, Probert et al. teaches of using a model in order to detect foreground thus one can replace that type of model for another type of model and obtain predictable results of using a model to perform detection. Thus, one of ordinary skill in the art could have substituted the one known element for the other to produce a predictable result (MPEP 2143).
Furthermore, one of ordinary skill before the effective filing date of the claimed invention would have found it obvious to have the foreground detection model be a fully convolutional neural network trained to detect foreground in the plurality of tiles as taught by Braman et al. in the method as taught by Probert et al. with the motivation(s) of improving outcome predictions (see: column 6, lines 1-3 of Braman et al.).
As per claim 18, Probert et al. teaches the system of claim 17, see discussion of claim 17. Probert et al. further teaches the operations further comprising:
--analyzing, via a foreground detection model, the at least one digital medical image to generate the plurality of tiles, (see: paragraph [0339] where there is extraction/generation of a plurality of foreground tiles from a plurality of tiles)
--wherein the plurality of tiles comprise tiles of the at least one digital medical image that include the foreground (see: paragraph [0339] where the tiles include foreground tiles).
Probert et al. may not further, specifically teach the foreground detection model being a fully convolutional neural network trained to detect foreground in the plurality of tiles.
Braman et al. teaches:
--the foreground detection model being a fully convolutional neural network trained to detect foreground in the plurality of tiles (see: column 14, line 55 to column 15, line 29 where there is such a fully convolutional neural network. The model being for foreground detection was already taught in the Probert et al. reference above).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to substitute the foreground detection model being a fully convolutional neural network trained to detect foreground in the plurality of tiles as taught by Braman et al. for the model as disclosed by Probert et al. since each individual element and its function are shown in the prior art, with the difference being the substitution of the elements. In the present case, Probert et al. teaches of using a model in order to detect foreground thus one can replace that type of model for another type of model and obtain predictable results of using a model to perform detection. Thus, one of ordinary skill in the art could have substituted the one known element for the other to produce a predictable result (MPEP 2143).
Furthermore, one of ordinary skill before the effective filing date of the claimed invention would have found it obvious to have the foreground detection model be a fully convolutional neural network trained to detect foreground in the plurality of tiles as taught by Braman et al. in the system as taught by Probert et al. with the motivation(s) of improving outcome predictions (see: column 6, lines 1-3 of Braman et al.).
Claims 7-12, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. 2024/0273718 to Probert et al. in view of U.S. 2021/0166785 to Yip et al.
As per claim 7, Probert et al. teaches the method of claim 1, see discussion of claim 1. Probert et al. may not further, specifically teach:
--analyzing, via a sizing model, the embedding vector for each of the plurality of tiles to predict a tumor size, the sizing model having been trained to predict the tumor size based on a plurality of embedding vectors.
Yip et al. teaches:
--analyzing, via a sizing model, the embedding vector for each of the plurality of tiles to predict a tumor size, (see: paragraph [0432] where there is analysis of the data using the trained model to predict the size of the cell. Also see: paragraph [0189] where there are prediction metrics involving the tumor’s size/number of cells) the sizing model having been trained to predict the tumor size based on a plurality of embedding vectors (see: paragraph [0432] where the trained model is trained to predict the size of the cell based on the inputted data).
One of ordinary skill before the effective filing date of the claimed invention would have found it obvious to analyze, via a sizing model, the embedding vector for each of the plurality of tiles to predict a tumor size, the sizing model having been trained to predict the tumor size based on a plurality of embedding vectors as taught by Yip et al. in the method as taught by Probert et al. with the motivation(s) of improving the forecasting of disease progression (see: paragraph [0013] of Yip et al.).
As per claim 8, Probert et al. teaches the method of claim 1, see discussion of claim 1. Probert et al. may not further, specifically teach:
--analyzing, via a purity model, the embedding vector for each of the plurality of tiles to predict a tumor purity, the purity model having been trained to predict the tumor purity based on a plurality of embedding vectors.
Yip et al. teaches:
--analyzing, via a purity model, the embedding vector for each of the plurality of tiles to predict a tumor purity, (see: paragraph [0432] where there is analysis of the data using the trained model to predict the size of the cell. Also see: paragraph [0189] where there are prediction metrics involving the tumor’s size/number of cells) the purity model having been trained to predict the tumor purity based on a plurality of embedding vectors (see: paragraph [0432] where the trained model is trained to predict the size of the cell based on the inputted data).
One of ordinary skill before the effective filing date of the claimed invention would have found it obvious to analyze, via a purity model, the embedding vector for each of the plurality of tiles to predict a tumor purity, the purity model having been trained to predict the tumor purity based on a plurality of embedding vectors as taught by Yip et al. in the method as taught by Probert et al. with the motivation(s) of improving the forecasting of disease progression (see: paragraph [0013] of Yip et al.).
As per claim 9, Probert et al. teaches the method of claim 1, see discussion of claim 1. Probert et al. may not further, specifically teach:
--based on the embedding vector for each of the plurality of tiles, generating a tile-level heatmap; and
--generating a display including the tile-level heatmap overlaid on the at least one digital medical image.
Yip et al. teaches:
--based on the embedding vector for each of the plurality of tiles, generating a tile-level heatmap; (see: paragraph [0249] where there is generation of a heat map/overlay map based on the tile information. The tile information being embedded vectors was already taught in the Probert et al. reference) and
--generating a display including the tile-level heatmap overlaid on the at least one digital medical image (see: paragraph [0249] where there is generation of a display of the overlay map/heat map overlaid on the histopathology image).
One of ordinary skill before the effective filing date of the claimed invention would have found it obvious to based on the embedding vector for each of the plurality of tiles, generate a tile-level heatmap and generating a display including the tile-level heatmap overlaid on the at least one digital medical image as taught by Yip et al. in the method as taught by Probert et al. with the motivation(s) of improving the forecasting of disease progression (see: paragraph [0013] of Yip et al.).
As per claim 10, Probert et al. and Yip et al. in combination teaches the method of claim 9, see discussion of claim 9. Probert et al. may not further, specifically teach:
--based on the tile-level heatmap, generating a cell-level heatmap; and
--generating the display including one or both of the tile-level heatmap or the cell-level heatmap overlaid on the at least one digital medical image.
Yip et al. teaches:
--based on the tile-level heatmap, generating a cell-level heatmap; (see: paragraph [0256] where there is generation of tumor cell heat maps) and
--generating the display including one or both of the tile-level heatmap or the cell-level heatmap overlaid on the at least one digital medical image (see: paragraph [0249] where there is generation of a display of the overlay map/heat map overlaid on the histopathology image).
One of ordinary skill before the effective filing date of the claimed invention would have found it obvious to based on the tile-level heatmap, generating a cell-level heatmap and generate the display including one or both of the tile-level heatmap or the cell-level heatmap overlaid on the at least one digital medical image as taught by Yip et al. in the method as taught by Probert et al. with the motivation(s) of improving the forecasting of disease progression (see: paragraph [0013] of Yip et al.).
As per claim 11, Probert et al. and Yip et al. in combination teaches the method of claim 10, see discussion of claim 10. Probert et al. further teaches wherein generating the cell-level heatmap is further based on the embedding vector for each of the plurality of tiles (see: paragraphs [0356] and [0359] and FIGS. 18A and 18B where there is generation of a cell-level heatmap based on the basis of the embeddings).
As per claim 12, Probert et al. teaches the method of claim 1, see discussion of claim 1. Probert et al. may not further, specifically teach:
--based on at least one of the first biomarker, a second biomarker, a tumor size, a tumor purity, a tile-level heatmap, or a cell-level heatmap, generating a request for review; and
--transmitting the request for review to a third-party device.
Yip et al. teaches:
--based on at least one of the first biomarker, a second biomarker, a tumor size, a tumor purity, a tile-level heatmap, or a cell-level heatmap, generating a request for review; (see: paragraph [0224] where there is a request which is generated based on biomarker statistics (first/second biomarker)) and
--transmitting the request for review to a third-party device (see: paragraphs [0224] – [0225] where there is a request for a manual review to a device of a pathologist or team of pathologists).
One of ordinary skill before the effective filing date of the claimed invention would have found it obvious to have based on at least one of the first biomarker, a second biomarker, a tumor size, a tumor purity, a tile-level heatmap, or a cell-level heatmap, generating a request for review and transmit the request for review to a third-party device as taught by Yip et al. in the method as taught by Probert et al. with the motivation(s) of improving the forecasting of disease progression (see: paragraph [0013] of Yip et al.).
As per claim 19, Probert et al. teaches the system of claim 17, see discussion of claim 17. Probert et al. further teaches the operations further comprising:
--at least one of:
--determining, by the aggregator model, a second biomarker for the digital medical image, the second biomarker and the first biomarker being different, (see: paragraphs [0071] and [0099] where there is a determination of one or more biomarkers. There is a determination of at least a second biomarkers here which is different from the first one as determining one or more biomarkers means determining separate biomarkers)
--analyzing, via a sizing model, the embedding vector for each of the plurality of tiles to predict a tumor size, the sizing model having been trained to predict the tumor size based on a plurality of embedding vectors, (does not need to be met as the limitation above was met)
--analyzing, via a purity model, the embedding vector for each of the plurality of tiles to predict a tumor purity, the purity model having been trained to predict the tumor purity based on the plurality of embedding vectors, (does not need to be met as the limitation above was met) or
--generating a tile-level heatmap and a cell-level heatmap based on the embedding vector for each of the plurality of tiles (does not need to be met as the limitation above was met).
Probert et al. may not further, specifically teach
--based on at least one of the first biomarker, the second biomarker, the tumor size, the tumor purity, the tile-level heatmap, or the cell-level heatmap, generating a request for review; and
--transmitting the request for review to a third-party device.
Yip et al. teaches:
--based on at least one of the first biomarker, the second biomarker, the tumor size, the tumor purity, the tile-level heatmap, or the cell-level heatmap, generating a request for review; (see: paragraph [0224] where there is a request which is generated based on biomarker statistics (first/second biomarker)) and
--transmitting the request for review to a third-party device (see: paragraphs [0224] – [0225] where there is a request for a manual review to a device of a pathologist or team of pathologists).
One of ordinary skill before the effective filing date of the claimed invention would have found it obvious to have based on at least one of the first biomarker, the second biomarker, the tumor size, the tumor purity, the tile-level heatmap, or the cell-level heatmap, generating a request for review and transmit the request for review to a third-party device as taught by Yip et al. in the system as taught by Probert et al. with the motivation(s) of improving the forecasting of disease progression (see: paragraph [0013] of Yip et al.).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Steven G.S. Sanghera whose telephone number is (571)272-6873. The examiner can normally be reached M-F 7:30-5:00 (alternating Fri).
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, Shahid Merchant can be reached at 571-270-1360. 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.
/STEVEN G.S. SANGHERA/Primary Examiner, Art Unit 3684
