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 .
Notice to Applicants
This action is in response to the Application filed on 10/17/2024.
Claims 1-20 are pending.
Priority
The present Application claims priority to Provisional Application 63/544,562 with the filing date of 10/17/2023, which is acknowledged.
Information Disclosure Statement
The Information Disclosure Statement (IDS) filed on 02/27/2025 has been fully considered by the examiner.
Claim Objections
Claim 20 is objected to.
Regarding claim 20, claim 20 is an exact duplicate of claim 10. The examiner believes that claim 20 was intended to depend upon claim 17 instead of claim 7, in which case the structure of the two claim trees of independent claims 1 and 11 would then be identical. In this case, claim 20 should be amended to read in part: “The system of claim 17, further comprising the operations of:” (emphasis added).
In the event that claim 20 was intended to depend upon claim 7, the following note would then apply.
Applicant is advised that should claim 10 be found allowable, claim 20 will be objected to under 37 CFR 1.75 as being a substantial duplicate thereof. When two claims in an application are duplicates or else are so close in content that they both cover the same thing, despite a slight difference in wording, it is proper after allowing one claim to object to the other as being a substantial duplicate of the allowed claim. See MPEP § 608.01(m).
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.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 9 and 19 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claim 9, the claim recites “removing tiles of the subset of smaller images that have any pen marks, scanning artifacts, tissue folds”, which is clear. However, the claim further expands these options to include “or other degrading characteristics in the tile”, which reads as subjective terminology. Paragraphs 0126 and 0167 of the originally-filed specification appear to be the only mention of this embodiment, and do not offer any further examples of degrading characteristics, or any other way of determining what would make a characteristic “degrading” or not. Thus, the recited determination of other degrading characteristics, and respectively of which tiles to remove, is unclear and requires the exercise of subjective judgement, which renders the claim indefinite. See MPEP 2173.05(b).IV.
Regarding claim 19, this claim is rejected for the same reasons as claim 9 above.
The examiner notes that claims 1 and 11 recite in part “identifying whether the cells in the subsets of smaller images indicate whether a prostate cancer patient is at a risk of progression among a clinically intermediate risk group.” This identification of whether a prostate cancer patient is “at risk” of progression is, at face-value, a subjective term. However, the originally-filed specification provides many objective standards for making this determination, for example in paragraphs 0112-0114.
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 1-9 and 11-19 are rejected under 35 U.S.C. 101 because the claimed invention is directed to abstract ideas without significantly more.
Analysis for claim 1 is provided in the following. Claim 1 is reproduced in the following (annotation added):
A method for identifying prostate cancer patients at high-risk of progression among clinically intermediate risk group, comprising:
obtaining images of patient cells;
tiling the images into subsets of smaller images;
performing a morphology quantification process on the subsets of smaller images, comprising: inputting a portion of the images into one or more trained machine learning models; determining by the one or more trained machine learning models likely cancer cells and a grading of the cancer cells;
and identifying whether the cells in the subsets of smaller images indicate whether a prostate cancer patient is at a risk of progression among a clinically intermediate risk group.
Step 1: Does the claim belong to one of the statutory categories? Claim 1 is directed to a process, which is a statutory category of invention (YES).
Step 2A Prong One: Does the claim recite a judicial exception? Steps d and e are regarded as reciting mental processes, including observations, evaluations, judgements, or opinions, that can be practically performed in the human mind.
Part d recites performing a morphology quantification process on the smaller images; this process as claimed only requires inputting the images to one or more trained machine learning models, which then determine likely cancer cells and a grading of the cancer cells. The claim does not recite any further characteristics of the models, only the inputs and outputs. Thus, considering that the courts do not distinguish between claims that recite mental processes performed by humans and claims that recite mental processes performed on a computer (see MPEP 2106.04(a)(2).III), a human can practically mentally achieve the same result as the models, i.e. observing the smaller images and determining therefrom likely cancer cells and a grading of said cancer cells. Note that paragraphs 0084 of the originally-filed specification describe how experienced pathologists can likewise determine the ground-truth data for the model from said images.
Part e recites identifying if the cells in the smaller images indicate if a prostate cancer patient is at a risk of progression. The claim does not appear to require that this step be performed by a trained machine learning model. Thus, this step can easily be mentally performed by a human, such as a pathologist (YES).
Step 2A Prong Two: Does the claim recite additional elements that integrate the judicial exception into a practical application? Part a is a non-limiting preamble, as its limitations are also present in step e. Part b recites obtaining the images of the patient cells, which amounts to mere data gathering. Part c recites tiling the images into subsets of smaller images, which does not integrate the recited mental processes into a practical application (NO).
Step 2B: Does the claim as a whole amount to significantly more than the recited exception? The claim as a whole recites a method including data gathering and image tiling, both of which are well-understood, routine, conventional activities in the fields of image processing and machine learning. The claim then recites multiple steps that can all be practically performed in the human mind (NO). Claim 1 is not eligible.
Similar analysis is applicable to independent claim 11. Claim 11 further recites a system comprising one or more processors that perform a similar method to claim 1, which amounts to a computerized system at a high level of generality, which does not integrate the mental processes into a practical application. Claim 11 is not eligible.
Claims 2-3, 5, 12-13, and 15 recite different species of cell gradings and patient classifications, all of which are still mentally determinable. Claims 2-3, 5, 12-13, and 15 are not eligible.
Claims 4 and 14 recite that the models are trained on multiple images of cancer cells and benign stroma, which does not integrate the mental processes into a practical application, as training models on images of different cell types is a well-understood, routine, conventional activity in the fields of image processing and machine learning. Claims 4 and 14 are not eligible.
Claims 6-7 and 16-17 recite performing feature encoding on the smaller images, wherein the feature encoding can include semi-supervised encoding, patient-level aggregation, and dimensionality reduction, all of which are directed to mathematical calculations. The recited patient-level aggregation can also be practically performed in the human mind. Claims 6-7 and 16-17 are not eligible.
Claims 8 and 18 recite that the tiling comprises dividing the image slides into a plurality of tiles of a predetermined size, which is a well-understood, routine, conventional activity in the fields of image processing and machine learning. Claims 8 and 18 are not eligible.
Claims 9 and 19 recite removing tiles that have any pen marks, scanning artifacts, tissue folds, or other degrading characteristics in the tile, which is a well-understood, routine, conventional activity in the fields of image processing and machine learning. Claims 9 and 19 are not eligible.
Claims 10 and 20 recite combining the output of the morphology quantification process and the feature encoding process as covariants, which is not practically performable in the human mind or a mathematical calculation as recited, and is also not a well-understood, routine, conventional activity. The claim further recites inputting the covariant into a final survival model that is trained to output a score between 0 and 1, with the score indicating a risk of biochemical recurrence, with 1 being the highest likelihood of recurrence. Determining this score by analyzing covariants instead of images is not practically performable in the human mind. Thus, claims 10 and 20 integrate the judicial exceptions into a practical application. Claims 10 and 20 are eligible.
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.
(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, 3-4, 6-8, 11, 13-14, and 16-18 are rejected under 35 U.S.C. 102(a)(1) and 102(a)(2) as being anticipated by Jain et al. (U.S. Publ. US-2021/0193323-A1).
Regarding claim 1, Jain discloses a method (see figure 2) for identifying prostate cancer patients (paragraph 0056 specifies that the disclosed methods and systems are agnostic to the type of cancer, and would thus include prostate cancer patients) at high-risk of progression among clinically intermediate risk group (see figure 1 and paragraphs 0044-0046), comprising:
obtaining images of patient cells (see figure 2, images 202 and paragraph 0058, where whole slide images of patient cells are obtained);
tiling the images into subsets of smaller images (see figure 2, patch generator 206 and paragraph 0058, where the images are divided into tiles/patches);
performing a morphology quantification process on the subsets of smaller images, comprising: inputting a portion of the images into one or more trained machine learning models; determining by the one or more trained machine learning models likely cancer cells and a grading of the cancer cells (see figure 2, disease detection & grading module 208, disease labels 210, submorphology detector 212 and paragraph 0059, where the patches are input to the module 208, which assigns the disease labels 210 to each patch, and then the detector 212 recognizes further morphological sub-patterns within each label; paragraphs 0073-0074 specify that the labels assigned by the module 208 and detector 212 can differentiate between low, medium, or high grade cancers and different non-cancer cell types);
and identifying whether the cells in the subsets of smaller images indicate whether a prostate cancer patient is at a risk of progression among a clinically intermediate risk group (see figure 2, ROI & outcome prediction module 214 and paragraphs 0059-0060, 0091, where the module 214 ranks each patch, then combines the patch scores to obtain a patient-level score ranking the patient's predicted outcome on a scale from adverse to good; paragraphs 0085-0087 specify that the patient outcome data can further include length of time of progression-free survival).
Regarding claim 3, Jain discloses wherein the trained machine learning model determines whether patient cells are cancerous cells or benign stroma (paragraph 0073 specifies that the labels can include various grades of cancerous cells and stromal cells).
Regarding claim 4, Jain discloses wherein the one or more trained machine learning networks are trained on multiple images of cancer cells and benign stroma (see paragraphs 0069 and 0073, where the models are trained on images to learn to identify the labels, which can include the cancer and stromal labels).
Regarding claim 6, Jain discloses performing a feature encoding process on the subsets of smaller images (see paragraph 0059, where the disease detection & grading module 208 transforms/encodes the patches into feature vectors).
Regarding claim 7, Jain discloses wherein the feature encoding process, comprises: performing semi-supervised encoding (paragraph 0059 specifies that the disease detection & grading module 208 performs supervised encoding, and that the submorphology detector 212 performs unsupervised encoding);
performing patient level aggregation (see paragraphs 0059-0060 and 0091, where the module 214 ranks each patch, then combines the patch scores to obtain a patient-level score ranking the patient's predicted outcome on a scale from adverse to good);
and performing dimensionality reduction (any of the above encoding steps of claims 6 or 7 can be said to reduce the large dimensions of the input image to smaller, vectorized dimensions).
Regarding claim 8, Jain discloses wherein tiling the images comprises: dividing a first set of patient tissue image slides into a plurality of tiles of a predetermined pixel size (see paragraphs 0058 and 0087, where predetermined sizes, such as 256 x 256 pixels, can be used for the patches).
Regarding claim 11, Jain discloses a system (see figure 2, Patient outcome prediction system 200 and paragraph 0058) for identifying prostate cancer patients (paragraph 0056 specifies that the disclosed methods and systems are agnostic to the type of cancer, and would thus include prostate cancer patients) at high-risk of progression among clinically intermediate risk group (see figure 1 and paragraphs 0044-0046),
the system comprising one or more processors configured to perform the operations of (paragraph 0056 specifies that the discloses systems and methods are implemented by computers, which necessarily include any type of processor).
The remainder of claim 11 recites steps identical to those of claim 1. Therefore, Jain anticipates claim 11 as applied to claim 1 above.
Regarding claim 13, Jain discloses claim 13 as applied to claim 3 above.
Regarding claim 14, Jain discloses claim 14 as applied to claim 4 above.
Regarding claim 16, Jain discloses claim 16 as applied to claim 6 above.
Regarding claim 17, Jain discloses claim 17 as applied to claim 7 above.
Regarding claim 18, Jain discloses claim 18 as applied to claim 8 above.
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.
Claims 2 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Jain et al. (U.S. Publ. US-2021/0193323-A1) in view of Steiner et al. (U.S. Publ. US-2023/0122392-A1) and Ho et al. (U.S. Publ. US-2023/0036156-A1).
Regarding claim 2, Jain fails to disclose the limitations of claim 2.
Pertaining to the same field of endeavor, Steiner discloses wherein the grading of the cancer cells classifies cells as GP3, GP5 (see paragraphs 0036-0038, where AI tools classify tissue regions by Gleason score/patterns/GP, before the final Gleason Grade Group/GGG classification in paragraph 0039; paragraphs 0074-0077 specify that the models are trained on all standard Gleason patterns and scores/grades, which would include GP3 and GP5).
Jain and Steiner are considered analogous art, as they are both directed to machine learning models for analyzing pathological cellular images. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Steiner into Jain by identifying Gleason patterns because using AI assistance significantly improves Pathologists' Gleason Grading accuracy (see Steiner paragraph 0006).
Jain in view of Steiner fails to further disclose and/or necrotic cells.
Pertaining to the same field of endeavor, Ho discloses and/or necrotic cells (see paragraphs 0139 and 0157, where a model is trained to measure cell death in microscopic images).
Jain and Ho are considered analogous art, as they are both directed to machine learning models for analyzing pathological cellular images. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Ho into Jain and Steiner by additionally classifying necrotic cells because doing so allows for separating tumor cell death from immune cell death and quantifying the effectiveness of current treatments (see Ho paragraphs 0081-0084 and 0165).
Regarding claim 12, Jain in view of Steiner and Ho discloses claim 12 as applied to claim 2 above.
Claims 5 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Jain et al. (U.S. Publ. US-2021/0193323-A1) in view of Steiner et al. (U.S. Publ. US-2023/0122392-A1).
Regarding claim 5, Jain fails to disclose the limitations of claim 5.
Pertaining to the same field of endeavor, Steiner discloses substratifying GGG2 patients and GGG3 patients with high statistical significance (see paragraphs 0039 and 0043-0045, where the AI models predict a final Gleason Grade Group score; paragraphs 0074-0077 specify that the models are trained on all standard Gleason patterns and scores/grades, which would include GGG2 and GGG3).
Jain and Steiner are considered analogous art, as they are both directed to machine learning models for analyzing pathological cellular images. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Steiner into Jain by identifying Gleason Grades for patients because using AI assistance significantly improves Pathologists' Gleason Grading accuracy (see Steiner paragraph 0006).
Regarding claim 15, Jain in view of Steiner discloses claim 15 as applied to claim 5 above.
Claims 9 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Jain et al. (U.S. Publ. US-2021/0193323-A1) in view of Alemi et al. (U.S. Publ. US-2023/0098732-A1).
Regarding claim 9, Jain fails to disclose the limitations of claim 9.
Pertaining to the same field of endeavor, Alemi discloses removing tiles of the subset of smaller images that have any pen marks, scanning artifacts, tissue folds or other degrading characteristics in the tile (see paragraphs 0108-0109, where an artifact detection identifies patches with artifacts present and then removes them; paragraph 0029 specifies that scanline artifacts are included; paragraph 0090 specifies that tissue folding artifacts are included; and paragraph 0111 specifies that pen marks are included).
Jain and Alemi are considered analogous art, as they are both directed to machine learning models for analyzing pathological cellular images. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Alemi into Jain by removing degraded tiles because removing image artifacts improves model training and performance (see Alemi paragraph 0107).
Regarding claim 19, Jain in view of Alemi discloses claim 19 as applied to claim 9 above.
Claims 10 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Jain et al. (U.S. Publ. US-2021/0193323-A1) in view of Madabhushi et al. (U.S. Publ. US-2018/0336395-A1).
Regarding claim 10, Jain fails to disclose the limitations of claim 10.
Pertaining to the same field of endeavor, Madabhushi discloses combining an output of the morphology quantification process, and an output of the feature encoding process as covariants (first see paragraphs 0018-0019, where cellular images are examined for prostate cancer, including morphology features and other features; then see figure 2, steps 230-250 and paragraphs 0039-0041, where two separate feature sets are obtained from the images and combined into a combined feature set/covariant);
and inputting the covariant into a final survival model which is trained to output a score between 0 and 1, with the score indicating a risk of biochemical recurrence, with 1 being the highest likelihood of recurrence (see figure 2, steps 260-280 and paragraphs 0042-0044, where the combined feature set is input to a machine learning classifier / survival model that outputs a probability of biochemical recurrence from 0 to 1).
Jain and Madabhushi are considered analogous art, as they are both directed to machine learning models for analyzing pathological cellular images. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Madabhushi into Jain by combining two separate feature sets and instead predicting the chance of recurrence therefrom because doing so improves recurrence prediction accuracy and appropriate treatment determination (see Madabhushi paragraph 0031).
Regarding claim 20, Jain in view of Madabhushi discloses claim 20 as applied to claim 10 above.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NICHOLAS JOHN HELCO whose telephone number is (703)756-5539. The examiner can normally be reached on Monday-Friday from 9:00 AM to 5:00 PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Matthew Bella, can be reached at telephone number 571-272-7778. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center. Status information for published applications may be obtained from Patent Center. Status information for unpublished applications is available through Patent Center for authorized users only. Should you have questions about access to Patent Center, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/NICHOLAS JOHN HELCO/Examiner, Art Unit 2667
/MATTHEW C BELLA/Supervisory Patent Examiner, Art Unit 2667
Prosecution Insights