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 .
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 1,3,7-9, 11-13, 21 and 23 are rejected under 35 U.S.C. 103 as being unpatentable over FENG (US 20220319704 A1) in view of Cook (US 20140272986 A1), Mahajan ( US 20230152322 A1).
With respect to claim 1, Feng teaches a method of treating uveal melanoma (“uveal melanoma” paragraphs 266 and 267) in a subject at least partially using a computer, the method comprising: capturing one or more images of one or more ocular tissues or portions thereof from the subject having the uveal melanoma to generate at least one captured image (“Images can be obtained from a tissue sample (human biological sample), such as a sectional sample (for example, obtained through a surgical excision) or a needle biopsy sample. In some embodiments, for example when the cancer is a liquid cancer, the tissue sample is obtained through a blood drawn. The tissue sample is taken from a cancer or suspected cancer.” Paragraph 0150); matching, by the computer, one or more properties of the captured image with one or more properties of at least one uveal melanoma model that is trained on a plurality of reference images of ocular tissues or portions thereof from reference subjects to produce a matched property set (see fig. 2), which properties of the uveal melanoma model are indicative of uveal melanoma (“The image data derived corresponding to an image of a cancer may be used as test image data (i.e., image data inputted in a trained learning model for the purpose of characterizing the cancer associated with the inputted image data), or as training and/or validation image data.” Paragraph 0156); Feng further teaches classifying, by the computer a cancer status (see fig. 5 and “the model is trained to learn a mapping from an input image of a cancer to an HR status (HRD probability) for the cancer” paragraph 0043). Feng does not explicitly teach GEP classes nor a treatment inclusive of administering therapies.
Cook teaches uveal melanoma can be classified based on GEP classes (“A GEP signature has recently been developed that can accurately distinguish uveal melanoma tumors that have a low risk of metastasis from those that have a high risk.sup.14,20. To assess genetic expression RT-PCR analysis is performed for fifteen genes (twelve discriminating genes and three control genes) that are differentially expressed in tumors with known metastatic activity compared to tumors with no evidence of metastasis. The uveal melanoma gene signature separates cases into a low risk group that has greater than 95% metastasis free survival five years after diagnosis, and a high risk group with less than 20% metastasis free survival at the same time point. The signature has been extensively validated in the clinical setting, and has been shown to provide a significant improvement in prognostic accuracy compared to classification by TNM staging criteria.sup.20,21.” Paragraph 0006) and classifying, by the computer, melanoma of the subject as gene expression profile (GEP) class 1 or GEP class 2 using the matched property set to generate a melanoma classification (“comparing the gene-expression profile to the gene-expression profile of a predictive training set; and (d) providing an indication as to whether the primary cutaneous melanoma tumor is class 1 or class 2 of metastasis when the gene expression profile indicates that expression levels of at least eight genes are altered in a predictive manner as compared to the gene expression profile of the predictive training set” paragraph 0009);
Cook is analogous art in the same field of endeavor as the claimed invention. Cook is directed towards predictive analysis of GEP classes (“making a determination as to whether the gene-expression level of the at least one gene is altered in a predictive manner; and (d) targeting the at least one gene for therapy when the determination is made in the affirmative.” Paragraph 12). A person of ordinary skill in the art would find it obvious to utilize Cook’s teachings of Uveal Melanoma in in combination with its predictive analysis system (enabled by a simple obvious to try substitution motivated by its own teachings of the relationship between Uveal Melanoma and GEP classes (“A GEP signature has recently been developed that can accurately distinguish uveal melanoma tumors that have a low risk of metastasis from those that have a high risk.sup.14,20. To assess genetic expression RT-PCR analysis is performed for fifteen genes (twelve discriminating genes and three control genes) that are differentially expressed in tumors with known metastatic activity compared to tumors with no evidence of metastasis. The uveal melanoma gene signature separates cases into a low risk group that has greater than 95% metastasis free survival five years after diagnosis, and a high risk group with less than 20% metastasis free survival at the same time point. The signature has been extensively validated in the clinical setting, and has been shown to provide a significant improvement in prognostic accuracy compared to classification by TNM staging criteria.sup.20,21” paragraph 0006)) by utilizing the image trained model of Feng to classify the input image sample, with the expectation that doing so would lead to better prognostic accuracy for cancer patients (“Inaccurate prognosis for metastatic risk has profound effects upon patients that are treated according to a population approach rather than an individual or personalized approach.” Paragraph 005 and “One such signature has been used for prognostication of uveal melanoma, a tumor of melanocytic origin that develops in the eye. Like cutaneous melanoma, treatment of the primary uveal tumor is highly effective. 2-4% of uveal melanoma patients present with evidence of clinical metastasis at the time of diagnosis, yet up to 50% of uveal melanoma patients develop systemic metastases within five years of diagnosis regardless of primary eye tumor treatment (radiation therapy or enucleation).sup.19. This means that a micrometastatic event has occurred in approximately 50% of uveal melanoma patients prior to primary eye tumor treatment. A GEP signature has recently been developed that can accurately distinguish uveal melanoma tumors that have a low risk of metastasis from those that have a high risk.sup.14,20. … The signature has been extensively validated in the clinical setting, and has been shown to provide a significant improvement in prognostic accuracy compared to classification by TNM staging criteria.sup.20,2 paragraph 0006).
Mahajan teaches administering one or more therapies to the subject based on the uveal melanoma classification (“In certain embodiments, the method further comprises administering adjuvant systemic therapy, radiotherapy, or performing surgery if the patient is diagnosed with GEP class 2 uveal melanoma or PRAME positive uveal melanoma indicating that the patient has a high risk of metastasis.” Paragraph 0025), thereby treating uveal melanoma in the subject (“In certain embodiments, the method further comprises administering adjuvant systemic therapy, radiotherapy, or performing surgery if the patient is diagnosed with GEP class 2 uveal melanoma or PRAME positive uveal melanoma indicating that the patient has a high risk of metastasis.” Paragraph 0025).
Mahajan is analogous art in the same field of endeavor as the claimed invention. Mahajan is directed toward determining Uveal Melanoma GEP classes using a model (“A likelihood score can also be used to distinguish among uveal melanoma disease subtypes, including classifying uveal melanoma by GEP class (i.e., GEP class 1 or class 2) and/or PRAME status (i.e., PRAME positive or negative). The models and/or algorithms can be provided in machine readable format, and may be used to correlate biomarker levels or a biomarker profile with a disease state, and/or to designate a treatment modality for a patient or class of patients” paragraph 0123). A person of ordinary skill in the art before the effective filing date of the claimed invention would have found it obvious to combine the teachings of Mahajan with the combined system of Feng and Cook by utilizing its (Mahajan’s) teachings of degerming uveal melanoma treatment based on model determined GEP class (“A likelihood score can also be used to distinguish among uveal melanoma disease subtypes, including classifying uveal melanoma by GEP class (i.e., GEP class 1 or class 2) and/or PRAME status (i.e., PRAME positive or negative). The models and/or algorithms can be provided in machine readable format, and may be used to correlate biomarker levels or a biomarker profile with a disease state, and/or to designate a treatment modality for a patient or class of patients” paragraph 0123), in combination with Feng and Cook’s combined image based GEP classification model, with the expectation that doing so would lead to earlier prognosis and treatments improving survivability (“Thus, there is a critical unmet need to develop rapid and precise diagnostic tools and treatments for uveal melanoma. Earlier detection of metastatic UM may allow for more effective treatments and prolonged survival.” Paragraph 0007 and “Compositions, methods, and kits are provided for diagnosing and treating uveal melanoma” paragraph 0008).
With respect to claim 3, Feng, Cook, and Mahajan teach the method of claim 1. Feng further teaches the method of claim 1, comprising: dividing, by the computer, the reference images of the ocular tissues or portions thereof from the reference subjects (“Images can be obtained from a tissue sample (human biological sample), such as a sectional sample (for example, obtained through a surgical excision) or a needle biopsy sample. In some embodiments, for example when the cancer is a liquid cancer, the tissue sample is obtained through a blood drawn. The tissue sample is taken from a cancer or suspected cancer.” Paragraph 0150) into at least two tiles to generate tile sets (“In some embodiments, an image is divided into a plurality of tiles” paragraph 0154 ), which ocular tissues or portions thereof comprise the uveal melanoma (“In embodiments, the image analysis system has an image pre-processor to process an image of a cancer received as input in preparation for processing by the ML model. The image pre-processor may process an input image for any one or more cropping, re-orienting, re-sizing, creating image portions (e.g. into patches or tiles, as is disclosed elsewhere herein)” paragraph 0015);retaining, by the computer, tiles in the tile sets (“The training image data within each labeled set includes a plurality of images, and the images are optionally divided into tiles” paragraph 0163) that comprise images of the ocular tissues or portions thereof that comprise the uveal melanoma (“Images can be obtained from a tissue sample (human biological sample), such as a sectional sample (for example, obtained through a surgical excision) or a needle biopsy sample. In some embodiments, for example when the cancer is a liquid cancer, the tissue sample is obtained through a blood drawn. The tissue sample is taken from a cancer or suspected cancer.” Paragraph 0150) to generate retained tile sets (“The training image data within each labeled set includes a plurality of images, and the images are optionally divided into tiles” paragraph 0163); Feng further discloses inputting, by the computer, the retained tile sets into a neural network (“As mentioned hereinabove, because a whole slide image is too big to feed into a neural network, each slide is partitioned into small tiles of size 512×512 pixels and the learning is done at tile level” paragraph 0353) comprising a classification layer that outputs survival outcome predictions for melanoma to train the neural network to produce a model (“the model is trained to learn a mapping from an input image of a cancer to an HR status (HRD probability) for the cancer” paragraph 0043 and “ predicting or diagnosing the HR (e.g. HRD) status (or microsatellite (in)stability or tumor mutation burden) of a cancer from an image” paragraph 122 and fig 9). Feng does not explicitly teach GEP classes.
Cook teaches GEP classes as predictors for survival outcomes(“A GEP signature has recently been developed that can accurately distinguish uveal melanoma tumors that have a low risk of metastasis from those that have a high risk.sup.14,20. Paragraph 0006) and Cook further teaches inputting, by the computer, images into a classification layer that outputs survival outcome predictions for the uveal melanoma (“A GEP signature has recently been developed that can accurately distinguish uveal melanoma tumors that have a low risk of metastasis from those that have a high risk.sup.14,20. To assess genetic expression RT-PCR analysis is performed for fifteen genes (twelve discriminating genes and three control genes) that are differentially expressed in tumors with known metastatic activity compared to tumors with no evidence of metastasis. The uveal melanoma gene signature separates cases into a low risk group that has greater than 95% metastasis free survival five years after diagnosis, and a high risk group with less than 20% metastasis free survival at the same time point. The signature has been extensively validated in the clinical setting, and has been shown to provide a significant improvement in prognostic accuracy compared to classification by TNM staging criteria.sup.20,21.” Paragraph 0006) to train models and algorithms to produce a melanoma model (“determining a gene-expression profile signature comprising the gene expression levels of the at least eight genes; (c) comparing the gene-expression profile to the gene-expression profile of a predictive training set; and (d) providing an indication as to whether the primary cutaneous melanoma tumor is class 1 or class 2 of metastasis when the gene expression profile indicates that expression levels of at least eight genes are altered in a predictive manner as compared to the gene expression profile of the predictive training se” paragraph 0009).
Cook is analogous art in the same field of endeavor as the claimed invention. Cook is directed towards predictive analysis of GEP classes (“making a determination as to whether the gene-expression level of the at least one gene is altered in a predictive manner; and (d) targeting the at least one gene for therapy when the determination is made in the affirmative.” Paragraph 12). A person of ordinary skill in the art would find it obvious to utilize Cook’s teachings of Uveal Melanoma in in combination with its predictive analysis system (enabled by a simple obvious to try substitution motivated by its own teachings of the relationship between Uveal Melanoma and GEP classes (“A GEP signature has recently been developed that can accurately distinguish uveal melanoma tumors that have a low risk of metastasis from those that have a high risk.sup.14,20. To assess genetic expression RT-PCR analysis is performed for fifteen genes (twelve discriminating genes and three control genes) that are differentially expressed in tumors with known metastatic activity compared to tumors with no evidence of metastasis. The uveal melanoma gene signature separates cases into a low risk group that has greater than 95% metastasis free survival five years after diagnosis, and a high risk group with less than 20% metastasis free survival at the same time point. The signature has been extensively validated in the clinical setting, and has been shown to provide a significant improvement in prognostic accuracy compared to classification by TNM staging criteria.sup.20,21” paragraph 0006)) by utilizing the image trained model of Feng to classify the input image sample, with the expectation that doing so would lead to better prognostic accuracy for cancer patients (“Inaccurate prognosis for metastatic risk has profound effects upon patients that are treated according to a population approach rather than an individual or personalized approach.” Paragraph 005 and “One such signature has been used for prognostication of uveal melanoma, a tumor of melanocytic origin that develops in the eye. Like cutaneous melanoma, treatment of the primary uveal tumor is highly effective. 2-4% of uveal melanoma patients present with evidence of clinical metastasis at the time of diagnosis, yet up to 50% of uveal melanoma patients develop systemic metastases within five years of diagnosis regardless of primary eye tumor treatment (radiation therapy or enucleation).sup.19. This means that a micrometastatic event has occurred in approximately 50% of uveal melanoma patients prior to primary eye tumor treatment. A GEP signature has recently been developed that can accurately distinguish uveal melanoma tumors that have a low risk of metastasis from those that have a high risk.sup.14,20. … The signature has been extensively validated in the clinical setting, and has been shown to provide a significant improvement in prognostic accuracy compared to classification by TNM staging criteria.sup.20,2 paragraph 0006).
With respect to claim 7, Feng, Cook, and Mahajan teach the method of claim 3. Cook further teaches the relationship between GEP classes and Uveal Melanoma (“A GEP signature has recently been developed that can accurately distinguish uveal melanoma tumors that have a low risk of metastasis from those that have a high risk.sup.14,20. To assess genetic expression RT-PCR analysis is performed for fifteen genes (twelve discriminating genes and three control genes) that are differentially expressed in tumors with known metastatic activity compared to tumors with no evidence of metastasis. The uveal melanoma gene signature separates cases into a low risk group that has greater than 95% metastasis free survival five years after diagnosis, and a high risk group with less than 20% metastasis free survival at the same time point. The signature has been extensively validated in the clinical setting, and has been shown to provide a significant improvement in prognostic accuracy compared to classification by TNM staging criteria.sup.20,21” paragraph 0006). Additionally, Cook teaches a binary classification layer that classifies samples as the GEP class 1 or the GEP class 2 (“determining a gene-expression profile signature comprising the gene expression levels of the at least eight genes; (c) comparing the gene-expression profile to the gene-expression profile of a predictive training set; and (d) providing an indication as to whether the primary cutaneous melanoma tumor is class 1 or class 2 of metastasis when the gene expression profile indicates that expression levels of at least eight genes are altered in a predictive manner as compared to the gene expression profile of the predictive training se” paragraph 0009).
With respect to claim 8, Feng, Cook, and Mahajan teach the method of claim 1. Feng further teaches the method of claim 1, comprising obtaining the ocular tissues or portions thereof from the subject (“Images can be obtained from a tissue sample (human biological sample), such as a sectional sample (for example, obtained through a surgical excision) or a needle biopsy sample. In some embodiments, for example when the cancer is a liquid cancer, the tissue sample is obtained through a blood drawn. The tissue sample is taken from a cancer or suspected cancer.” Paragraph 0150 and “uveal melanoma” paragraphs 266 and 267).
With respect to claim 9, Feng, Cook, and Mahajan teach the method of claim 1. Mahajan further teaches the method of claim 1, wherein the properties comprise one or more patterns (“In some embodiments, one or more pattern recognition methods can be used in analyzing the data for biomarker levels. The quantitative values may be combined in linear or non-linear fashion to calculate one or more risk scores for uveal melanoma for an individual. In some embodiments, measurements for a biomarker or combinations of biomarkers are formulated into linear or non-linear models or algorithms (e.g., a ‘biomarker signature’) and converted into a likelihood score. This likelihood score indicates the probability that a vitreous sample is from a patient who may exhibit no evidence of disease, who may exhibit uveal melanoma. A likelihood score can also be used to distinguish among uveal melanoma disease subtypes, including classifying uveal melanoma by GEP class (i.e., GEP class 1 or class 2)” paragraph 0123).
With respect to claim 11, Feng, Cook, and Mahajan teach the method of claim 1. Mahajan further teaches the method of claim 1, further comprising repeating the method at one or more later time points (“In some embodiments, the methods described herein are used for monitoring uveal melanoma in a subject. For example, a first vitreous sample can be obtained from the patient at a first time point and a second vitreous sample can be obtained from the subject at a second (later) time point. In one embodiment, uveal melanoma is monitored in the patient” paragraph 0100) to monitor progression of the uveal melanoma in the subject (“In particular, biomarkers have been identified that can be used to diagnose uveal melanoma and subtype tumors according to their GEP class or PRAME status. These biomarkers can be used alone or in combination with one or more additional biomarkers or relevant clinical parameters in prognosis, diagnosis, or monitoring treatment of uveal melanoma.” Paragraph 0053).
With respect to claim 12, Feng, Cook, and Mahajan teach the method of claim 1. Mahajan further teaches the method of claim 1,wherein the uveal melanoma model comprises one or more selected therapies indexed to the uveal melanoma of the subject (“The methods described herein may be used to determine an appropriate treatment regimen for a patient and, in particular, whether a patient should be treated for uveal melanoma. For example, a patient is selected for treatment for uveal melanoma if the patient has a positive diagnosis for uveal melanoma based on a biomarker expression profile, as described herein. The treatment for uveal melanoma may comprise, for example, administering adjuvant systemic therapy, radioactive plaque therapy, external beam proton therapy, laser therapy, enucleation, evisceration, exenteration, iridectomy, choroidectomy, iridocyclectomy, eyewall resection, chemotherapy, brachytherapy, transpupillary thermotherapy, resection of the eye tumor, gamma knife stereotactic radiosurgery, or a combination thereof.” Paragraph 0099).
With respect to claim 13, Feng, Cook, and Mahajan teach the method of claim 1. Feng further teaches the method of claim 1, comprising capturing the images of the ocular tissues or portions thereof from the subject with a camera (“Typically, the image is a digital image (or digital image data), for example obtained by a digital imaging (image capture or recording) system (e.g. a digital camera or a digital scanner), such as is known for digital pathology, for instance for obtaining a digital image of a whole slide image. In embodiments, the image is image data representing a whole slide image.” Paragraph 0025).
With respect to claim 21, Feng, Cook, and Mahajan teach the method of claim 1. Feng further teaches wherein the tissues or portions thereof comprise cells, organelles, and/or biomolecules. (“Typically, the image is of a stained cancer sample, especially where the image is a histology image. Staining may be by any conventional technique, particularly staining by hematoxylin and eosin (commonly referred to as ‘H&E stain’). Obtaining H&E-stained histological images for cancer samples is standard procedure in clinical settings” paragraph 0020 and “For those aspects and embodiments of the invention using a learning model, the use of image portions (tiles) may follow the approach as set out in Coudray N et al, Classification and mutation prediction from non-small lung cancer histopathology image using deep learning, Nature Medicine (2018).” Paragraph 0032).
With respect to claim 23, Feng teaches a system, comprising: at least one camera (“Typically, the image is a digital image (or digital image data), for example obtained by a digital imaging (image capture or recording) system (e.g. a digital camera or a digital scanner), such as is known for digital pathology, for instance for obtaining a digital image of a whole slide image. In embodiments, the image is image data representing a whole slide image.” Paragraph 0025) that is configured to capture one or more images of ocular tissues or portions thereof from a subject having uveal melanoma (“uveal melanoma” paragraphs 266 and 267 and “Images can be obtained from a tissue sample (human biological sample), such as a sectional sample (for example, obtained through a surgical excision) or a needle biopsy sample. In some embodiments, for example when the cancer is a liquid cancer, the tissue sample is obtained through a blood drawn. The tissue sample is taken from a cancer or suspected cancer.” Paragraph 0150);at least one controller that is operably connected, or connectable, at least to the camera (see fig. 4 and “Typically, the image is a digital image (or digital image data), for example obtained by a digital imaging (image capture or recording) system (e.g. a digital camera or a digital scanner), such as is known for digital pathology, for instance for obtaining a digital image of a whole slide image. In embodiments, the image is image data representing a whole slide image. Whole slide images may be acquired by commercially available whole slide imaging systems, such as the Philips IntelliSite (DEN160056) and Aperio AT2 DX System (K190332)). The invention (including any one or more of the system, method, computer program product and computer-readable storage medium) may be implemented in or incorporated into (e.g. integrated into) an imaging system, e.g. for imaging slides, such as those disclosed herein, for example a histology/histopathology/pathology slide scanner.” Paragraph 0025), wherein the controller comprises, or is capable of accessing, computer readable media comprising non-transitory computer executable instructions (see fig. 4 and “Typically, the one or more processors will be part of a computer device (or computer module) or computer system which further comprises one or memory stores for storing an image of a cancer and the image analysis system (or parts thereof, e.g. learning model and/or the image (pre-)processor) and/or the learning model “ paragraph 0034) which, when executed by at least one electronic processor (“the image analysis system (or parts thereof, e.g. learning model and/or the image (pre-)processor) and/or the learning model “ paragraph 0034), perform at least: capturing the images of the ocular tissues or portions thereof from the subject with the camera to generate captured images (“Images can be obtained from a tissue sample (human biological sample), such as a sectional sample (for example, obtained through a surgical excision) or a needle biopsy sample. In some embodiments, for example when the cancer is a liquid cancer, the tissue sample is obtained through a blood drawn. The tissue sample is taken from a cancer or suspected cancer.” Paragraph 0150);matching one or more properties of the captured images with one or more properties of at least one uveal melanoma model that is trained on a plurality of reference images of ocular tissues or portions thereof [[of]] from reference subjects to produce a matched property set (see fig. 2), which properties of the uveal melanoma model are indicative of uveal melanoma (“The image data derived corresponding to an image of a cancer may be used as test image data (i.e., image data inputted in a trained learning model for the purpose of characterizing the cancer associated with the inputted image data), or as training and/or validation image data.” Paragraph 0156); Feng further teaches classifying, by the computer a cancer status (see fig. 5 and “the model is trained to learn a mapping from an input image of a cancer to an HR status (HRD probability) for the cancer” paragraph 0043 and “ predicting or diagnosing the HR (e.g. HRD) status (or microsatellite (in)stability or tumor mutation burden) of a cancer from an image” paragraph 0122 and fig 9). Feng does not explicitly teach GEP classes nor a treatment inclusive of administering therapies.
Cook teaches uveal melanoma can be classified based on GEP classes (“A GEP signature has recently been developed that can accurately distinguish uveal melanoma tumors that have a low risk of metastasis from those that have a high risk.sup.14,20. To assess genetic expression RT-PCR analysis is performed for fifteen genes (twelve discriminating genes and three control genes) that are differentially expressed in tumors with known metastatic activity compared to tumors with no evidence of metastasis. The uveal melanoma gene signature separates cases into a low risk group that has greater than 95% metastasis free survival five years after diagnosis, and a high risk group with less than 20% metastasis free survival at the same time point. The signature has been extensively validated in the clinical setting, and has been shown to provide a significant improvement in prognostic accuracy compared to classification by TNM staging criteria.sup.20,21.” Paragraph 0006) and classifying, by the computer, melanoma of the subject as gene expression profile (GEP) class 1 or GEP class 2 using the matched property set to generate a melanoma classification (“comparing the gene-expression profile to the gene-expression profile of a predictive training set; and (d) providing an indication as to whether the primary cutaneous melanoma tumor is class 1 or class 2 of metastasis when the gene expression profile indicates that expression levels of at least eight genes are altered in a predictive manner as compared to the gene expression profile of the predictive training set” paragraph 0009);
Cook is analogous art in the same field of endeavor as the claimed invention. Cook is directed towards predictive analysis of GEP classes (“making a determination as to whether the gene-expression level of the at least one gene is altered in a predictive manner; and (d) targeting the at least one gene for therapy when the determination is made in the affirmative.” Paragraph 12). A person of ordinary skill in the art would find it obvious to utilize Cook’s teachings of Uveal Melanoma in in combination with its predictive analysis system (enabled by a simple obvious to try substitution motivated by its own teachings of the relationship between Uveal Melanoma and GEP classes (“A GEP signature has recently been developed that can accurately distinguish uveal melanoma tumors that have a low risk of metastasis from those that have a high risk.sup.14,20. To assess genetic expression RT-PCR analysis is performed for fifteen genes (twelve discriminating genes and three control genes) that are differentially expressed in tumors with known metastatic activity compared to tumors with no evidence of metastasis. The uveal melanoma gene signature separates cases into a low risk group that has greater than 95% metastasis free survival five years after diagnosis, and a high risk group with less than 20% metastasis free survival at the same time point. The signature has been extensively validated in the clinical setting, and has been shown to provide a significant improvement in prognostic accuracy compared to classification by TNM staging criteria.sup.20,21” paragraph 0006)) by utilizing the image trained model of Feng to classify the input image sample, with the expectation that doing so would lead to better prognostic accuracy for cancer patients (“Inaccurate prognosis for metastatic risk has profound effects upon patients that are treated according to a population approach rather than an individual or personalized approach.” Paragraph 005 and “One such signature has been used for prognostication of uveal melanoma, a tumor of melanocytic origin that develops in the eye. Like cutaneous melanoma, treatment of the primary uveal tumor is highly effective. 2-4% of uveal melanoma patients present with evidence of clinical metastasis at the time of diagnosis, yet up to 50% of uveal melanoma patients develop systemic metastases within five years of diagnosis regardless of primary eye tumor treatment (radiation therapy or enucleation).sup.19. This means that a micrometastatic event has occurred in approximately 50% of uveal melanoma patients prior to primary eye tumor treatment. A GEP signature has recently been developed that can accurately distinguish uveal melanoma tumors that have a low risk of metastasis from those that have a high risk.sup.14,20. … The signature has been extensively validated in the clinical setting, and has been shown to provide a significant improvement in prognostic accuracy compared to classification by TNM staging criteria.sup.20,2 paragraph 0006).
Mahajan teaches administering one or more therapies to the subject based on the uveal melanoma classification (“In certain embodiments, the method further comprises administering adjuvant systemic therapy, radiotherapy, or performing surgery if the patient is diagnosed with GEP class 2 uveal melanoma or PRAME positive uveal melanoma indicating that the patient has a high risk of metastasis.” Paragraph 0025), thereby treating uveal melanoma in the subject (“In certain embodiments, the method further comprises administering adjuvant systemic therapy, radiotherapy, or performing surgery if the patient is diagnosed with GEP class 2 uveal melanoma or PRAME positive uveal melanoma indicating that the patient has a high risk of metastasis.” Paragraph 0025).
Mahajan is analogous art in the same field of endeavor as the claimed invention. Mahajan is directed toward determining Uveal Melanoma GEP classes using a model (“A likelihood score can also be used to distinguish among uveal melanoma disease subtypes, including classifying uveal melanoma by GEP class (i.e., GEP class 1 or class 2) and/or PRAME status (i.e., PRAME positive or negative). The models and/or algorithms can be provided in machine readable format, and may be used to correlate biomarker levels or a biomarker profile with a disease state, and/or to designate a treatment modality for a patient or class of patients” paragraph 0123). A person of ordinary skill in the art before the effective filing date of the claimed invention would have found it obvious to combine the teachings of Mahajan with the combined system of Feng and Cook by utilizing its (Mahajan’s) teachings of degerming uveal melanoma treatment based on model determined GEP class (“A likelihood score can also be used to distinguish among uveal melanoma disease subtypes, including classifying uveal melanoma by GEP class (i.e., GEP class 1 or class 2) and/or PRAME status (i.e., PRAME positive or negative). The models and/or algorithms can be provided in machine readable format, and may be used to correlate biomarker levels or a biomarker profile with a disease state, and/or to designate a treatment modality for a patient or class of patients” paragraph 0123), in combination with Feng and Cook’s combined image based GEP classification model, with the expectation that doing so would lead to earlier prognosis and treatments improving survivability (“Thus, there is a critical unmet need to develop rapid and precise diagnostic tools and treatments for uveal melanoma. Earlier detection of metastatic UM may allow for more effective treatments and prolonged survival.” Paragraph 0007 and “Compositions, methods, and kits are provided for diagnosing and treating uveal melanoma” paragraph 0008).
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Feng in view of Cook.
With respect to claim 2, Feng teaches a method of classifying uveal melanoma (“uveal melanoma” paragraphs 266 and 267) tissues or portions thereof in a subject (“Images can be obtained from a tissue sample (human biological sample), such as a sectional sample (for example, obtained through a surgical excision) or a needle biopsy sample. In some embodiments, for example when the cancer is a liquid cancer, the tissue sample is obtained through a blood drawn. The tissue sample is taken from a cancer or suspected cancer.” Paragraph 0150) at least partially using a computer, the method comprising:dividing, by the computer, a plurality of reference images of ocular tissues or portions thereof from reference subjects (“Images can be obtained from a tissue sample (human biological sample), such as a sectional sample (for example, obtained through a surgical excision) or a needle biopsy sample. In some embodiments, for example when the cancer is a liquid cancer, the tissue sample is obtained through a blood drawn. The tissue sample is taken from a cancer or suspected cancer.” Paragraph 0150) into at least two tiles to generate tile sets (“In some embodiments, an image is divided into a plurality of tiles” paragraph 0154 ), which ocular tissues or portions thereof comprise uveal melanoma (“In embodiments, the image analysis system has an image pre-processor to process an image of a cancer received as input in preparation for processing by the ML model. The image pre-processor may process an input image for any one or more cropping, re-orienting, re-sizing, creating image portions (e.g. into patches or tiles, as is disclosed elsewhere herein)” paragraph 0015) ;retaining, by the computer, tiles in the tile sets (“The training image data within each labeled set includes a plurality of images, and the images are optionally divided into tiles” paragraph 0163) that comprise images of the ocular tissues or portions thereof that comprise the uveal melanoma (“Images can be obtained from a tissue sample (human biological sample), such as a sectional sample (for example, obtained through a surgical excision) or a needle biopsy sample. In some embodiments, for example when the cancer is a liquid cancer, the tissue sample is obtained through a blood drawn. The tissue sample is taken from a cancer or suspected cancer.” Paragraph 0150) to generate retained tile sets (“The training image data within each labeled set includes a plurality of images, and the images are optionally divided into tiles” paragraph 0163); Feng further discloses inputting, by the computer, the retained tile sets into a neural network (“As mentioned hereinabove, because a whole slide image is too big to feed into a neural network, each slide is partitioned into small tiles of size 512×512 pixels and the learning is done at tile level” paragraph 0353) comprising a classification layer that outputs survival outcome predictions for melanoma to train the neural network to produce a model (“the model is trained to learn a mapping from an input image of a cancer to an HR status (HRD probability) for the cancer” paragraph 0043 and “ predicting or diagnosing the HR (e.g. HRD) status (or microsatellite (in)stability or tumor mutation burden) of a cancer from an image” paragraph 0122 and fig. 9). Feng does not explicitly teach GEP classes.
Cook teaches inputting, by the computer, images into a classification layer that outputs survival outcome predictions for the uveal melanoma (“A GEP signature has recently been developed that can accurately distinguish uveal melanoma tumors that have a low risk of metastasis from those that have a high risk.sup.14,20. To assess genetic expression RT-PCR analysis is performed for fifteen genes (twelve discriminating genes and three control genes) that are differentially expressed in tumors with known metastatic activity compared to tumors with no evidence of metastasis. The uveal melanoma gene signature separates cases into a low risk group that has greater than 95% metastasis free survival five years after diagnosis, and a high risk group with less than 20% metastasis free survival at the same time point. The signature has been extensively validated in the clinical setting, and has been shown to provide a significant improvement in prognostic accuracy compared to classification by TNM staging criteria.sup.20,21.” Paragraph 0006) to train models and algorithms to produce a melanoma model (“determining a gene-expression profile signature comprising the gene expression levels of the at least eight genes; (c) comparing the gene-expression profile to the gene-expression profile of a predictive training set; and (d) providing an indication as to whether the primary cutaneous melanoma tumor is class 1 or class 2 of metastasis when the gene expression profile indicates that expression levels of at least eight genes are altered in a predictive manner as compared to the gene expression profile of the predictive training se” paragraph 0009), wherein the classification layer comprises a binary classification layer that classifies the melanoma in the retained tile sets as gene expression profile (GEP) class 1 or GEP class 2 (“determining a gene-expression profile signature comprising the gene expression levels of the at least eight genes; (c) comparing the gene-expression profile to the gene-expression profile of a predictive training set; and (d) providing an indication as to whether the primary cutaneous melanoma tumor is class 1 or class 2 of metastasis when the gene expression profile indicates that expression levels of at least eight genes are altered in a predictive manner as compared to the gene expression profile of the predictive training se” paragraph 0009); and,matching, by the computer, one or more properties of portions thereof from the subject with one or more properties of the uveal model (“determining a gene-expression profile signature comprising the gene expression levels of the at least eight genes; (c) comparing the gene-expression profile to the gene-expression profile of a predictive training set; and (d) providing an indication as to whether the primary cutaneous melanoma tumor is class 1 or class 2 of metastasis when the gene expression profile indicates that expression levels of at least eight genes are altered in a predictive manner as compared to the gene expression profile of the predictive training se” paragraph 0009), which properties of the uveal model are indicative of a GEP class 1 classification or a GEP class 2 classification (“determining a gene-expression profile signature comprising the gene expression levels of the at least eight genes; (c) comparing the gene-expression profile to the gene-expression profile of a predictive training set; and (d) providing an indication as to whether the primary cutaneous melanoma tumor is class 1 or class 2 of metastasis when the gene expression profile indicates that expression levels of at least eight genes are altered in a predictive manner as compared to the gene expression profile of the predictive training se” paragraph 0009), thereby classifying the uveal melanoma cells in the subject (“determining a gene-expression profile signature comprising the gene expression levels of the at least eight genes; (c) comparing the gene-expression profile to the gene-expression profile of a predictive training set; and (d) providing an indication as to whether the primary cutaneous melanoma tumor is class 1 or class 2 of metastasis when the gene expression profile indicates that expression levels of at least eight genes are altered in a predictive manner as compared to the gene expression profile of the predictive training se” paragraph 0009).
Cook is analogous art in the same field of endeavor as the claimed invention. Cook is directed towards predictive analysis of GEP classes (“making a determination as to whether the gene-expression level of the at least one gene is altered in a predictive manner; and (d) targeting the at least one gene for therapy when the determination is made in the affirmative.” Paragraph 12). A person of ordinary skill in the art would find it obvious to utilize Cook’s teachings of Uveal Melanoma in in combination with its predictive analysis system (enabled by a simple obvious to try substitution motivated by its own teachings of the relationship between Uveal Melanoma and GEP classes (“A GEP signature has recently been developed that can accurately distinguish uveal melanoma tumors that have a low risk of metastasis from those that have a high risk.sup.14,20. To assess genetic expression RT-PCR analysis is performed for fifteen genes (twelve discriminating genes and three control genes) that are differentially expressed in tumors with known metastatic activity compared to tumors with no evidence of metastasis. The uveal melanoma gene signature separates cases into a low risk group that has greater than 95% metastasis free survival five years after diagnosis, and a high risk group with less than 20% metastasis free survival at the same time point. The signature has been extensively validated in the clinical setting, and has been shown to provide a significant improvement in prognostic accuracy compared to classification by TNM staging criteria.sup.20,21” paragraph 0006)) by utilizing the image trained model of Feng to classify the input image sample, with the expectation that doing so would lead to better prognostic accuracy for cancer patients (“Inaccurate prognosis for metastatic risk has profound effects upon patients that are treated according to a population approach rather than an individual or personalized approach.” Paragraph 005 and “One such signature has been used for prognostication of uveal melanoma, a tumor of melanocytic origin that develops in the eye. Like cutaneous melanoma, treatment of the primary uveal tumor is highly effective. 2-4% of uveal melanoma patients present with evidence of clinical metastasis at the time of diagnosis, yet up to 50% of uveal melanoma patients develop systemic metastases within five years of diagnosis regardless of primary eye tumor treatment (radiation therapy or enucleation).sup.19. This means that a micrometastatic event has occurred in approximately 50% of uveal melanoma patients prior to primary eye tumor treatment. A GEP signature has recently been developed that can accurately distinguish uveal melanoma tumors that have a low risk of metastasis from those that have a high risk.sup.14,20. … The signature has been extensively validated in the clinical setting, and has been shown to provide a significant improvement in prognostic accuracy compared to classification by TNM staging criteria.sup.20,2 paragraph 0006).
Claims 14-17 are rejected under 35 U.S.C. 103 as being unpatentable over Feng, Cook, and Mahajan as applied to claim 13 above, and further in view of Takeda (US 20180025112 A1).
With respect to claim 14, Feng, Cook, and Mahajan teach the method of claim 13, however do not teach the rest of the limitations. Takeda teaches wherein the camera ("The medical information includes a medical image(s). The medical image is acquired with any kind of modality. For example, in ophthalmology... a fundus camera, ... color photography" paragraph 0036 lines 1-8) is operably connected to a database comprising an electronic medical record of the subject ("The communication system between the medical information processing system and the external devices is of an arbitrary type. For example, the communication system between the medical information processing system and the external devices may include wired communication and/or wireless communication" paragraph 0026 lines 1-6 And "The artificial intelligence engine classifies the medical image included in the medical information received in the step S1 based on the database in which known information, medical information, medical knowledge, etc. has been stored." Paragraph 0039 lines 1-5) and wherein the method further comprises retrieving data from the electronic medical record ("Prior to the commencement of the processes shown in FIG. 1, the following procedure or processes are performed, for example. An administrator of the medical information processing system etc. makes a contract with a medical institution, a research institution, or the like to receive the provision of medical information of patients (e.g., electronic health records, medical images, examination data, genetic data), medical knowledge, and the like" paragraph 0032) and/or populating the electronic medical record with at least one of the images and/or information related thereto ("The medical information processing system stores the medical knowledge acquired in the step S7 in the database. The medical knowledge stored in the database can be used for the process of the step S2 (classification of medical images), the process of the step S6 (machine learning), the process of the step S7 (acquisition of medical knowledge), or the like. In addition, the acquired knowledge can be given to medical institutions or the like." Paragraph 0055 lines 1-8).
Takeda is analogous art in the same field of endeavor as the claimed invention. Takeda is directed towards an AI enabled (“Any kinds of machine learning technology can be applied to embodiment.” Paragraph 0020) medical processing system (“Based on the database, an artificial intelligence engine can execute machine learning, data mining, reasoning (or inference), statistical processing, and the like. Medical knowledge acquired by the artificial intelligence engine can be stored in the database. The accuracy and precision of the processing executed by the medical information processing system can be improved by updating the database and/or updating the artificial intelligence engine (e.g., updating a parameter etc.) by the use of machine learning or the like” paragraph 0019). A person of ordinary skill before the effective filing date of the claimed invention would have found it obvious to combine the system of Feng, Cook, and Mahajan with the teachings of Takeda, by utilizing Takeda’s database and medical record integration teachings in combination with the combined systems Uveal Melanoma AI system, with the expectation that doing so would lead to increases in model precision and accuracy ("The medical information database 30 is installed in a medical institution or a research institution. Various kinds of medical information (e.g., medical information of patients, research data, or the like).." paragraph 0057 lines 6-9 and "Medical knowledge acquired by the artificial intelligence engine 11 can be stored in the database 12. The accuracy and precision of the processing executed by the medical information processing system 10 can be improved by updating the database 12" paragraph 0059 lines 8-13).
With respect to claim 15, Feng, Cook, and Mahajan teach the method of claim 13, however they do not teach any further limitations. Takeda teaches that the camera ("The medical information includes a medical image(s). The medical image is acquired with any kind of modality. For example, in ophthalmology... a fundus camera, ... color photography" paragraph 0036 lines 1-8) is wirelessly connected, or connectable, to the electronic medical record of the subject ("The medical information processing system stores the medical knowledge acquired in the step S7 in the database. The medical knowledge stored in the database can be used for the process of the step S2 (classification of medical images), the process of the step S6 (machine learning), the process of the step S7 (acquisition of medical knowledge), or the like. In addition, the acquired knowledge can be given to medical institutions or the like." Paragraph 0055 lines 1-8 and "The communication system between the medical information processing system and the external devices is of an arbitrary type. For example, the communication system between the medical information processing system and the external devices may include wired communication and/or wireless communication" paragraph 0026 lines 1-6, camera as external device).
Takeda is analogous art in the same field of endeavor as the claimed invention. Takeda is directed towards an AI enabled (“Any kinds of machine learning technology can be applied to embodiment.” Paragraph 0020) medical processing system (“Based on the database, an artificial intelligence engine can execute machine learning, data mining, reasoning (or inference), statistical processing, and the like. Medical knowledge acquired by the artificial intelligence engine can be stored in the database. The accuracy and precision of the processing executed by the medical information processing system can be improved by updating the database and/or updating the artificial intelligence engine (e.g., updating a parameter etc.) by the use of machine learning or the like” paragraph 0019). A person of ordinary skill before the effective filing date of the claimed invention would have found it obvious to combine the system of Feng, Cook, and Mahajan with the teachings of Takeda, by utilizing Takeda’s database and medical record integration teachings in combination with the combined systems Uveal Melanoma AI system, with the expectation that doing so would lead to increases in model precision and accuracy ("The medical information database 30 is installed in a medical institution or a research institution. Various kinds of medical information (e.g., medical information of patients, research data, or the like).." paragraph 0057 lines 6-9 and "Medical knowledge acquired by the artificial intelligence engine 11 can be stored in the database 12. The accuracy and precision of the processing executed by the medical information processing system 10 can be improved by updating the database 12" paragraph 0059 lines 8-13).
With respect to claim 16, Feng, Cook, Mahajan, and Takeda teach the method of claim 14. Takeda further teaches that the camera ("The medical information includes a medical image(s). The medical image is acquired with any kind of modality. For example, in ophthalmology... a fundus camera, ... color photography" paragraph 0036 lines 1-8) and/or the database ("The medical information processing system stores the medical knowledge acquired in the step S7 in the database. The medical knowledge stored in the database can be used for the process of the step S2 (classification of medical images), the process of the step S6 (machine learning), the process of the step S7 (acquisition of medical knowledge), or the like. In addition, the acquired knowledge can be given to medical institutions or the like." Paragraph 0055 lines 1-8) is wirelessly connected, or connectable, to one or more communication devices of one or more remote users ("The communication system between the medical information processing system and the external devices is of an arbitrary type. For example, the communication system between the medical information processing system and the external devices may include wired communication and/or wireless communication" paragraph 0026 lines 1-6, camera and user devices as external device and medical information database as apart of medical information processing system) and wherein the remote users view at least one of the images of the ocular tissues or portions thereof of the subject and/or the electronic medical record of the subject using the communication devices ("The medical information processing system can communicate with various kinds of external devices (e.g., computers, computer systems, medical apparatuses). For example, the medical information processing system can communicate with a computer that is installed in a medical institution or a research institution, and receives medical information of patients and the like through a communication line." Paragraph 0025, viewable by workers at medical/research institution).
With respect to claim 17, Feng, Cook, Mahajan and Takeda teach the method of claim 16. Takeda further teaches that the communication devices comprise one or more mobile applications ("The user interface 14 may be a computer (e.g., a computer terminal, a mobile terminal" paragraph 0061 lines 5-6, mobile terminal indicating mobile application) that operably interface ("...the controller 15 controls the communication unit..." paragraph 0062 line 5 and "The controller 15 can execute control of an external apparatus installed outside the medical information processing system 10. For example, when the user interface 14 is not included in the medical information processing system 10, the controller 15 can executes control of the user interface 14. The controller 15 includes a computer program for executing various kinds of control and a processor that operates according to the computer program." Paragraph 0063) with the camera and/or the database ("The communication system between the medical information processing system and the external devices is of an arbitrary type. For example, the communication system between the medical information processing system and the external devices may include wired communication and/or wireless communication" paragraph 0026 lines 1-6, camera as external device, database as apart of medical information processing system).
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Feng, Cook, and Mahajan and Takeda as applied to claim 16 above, and further in view of Shah (Shah, Anoop Dinesh et al. Recording problems and diagnoses in clinical care: developing guidance for healthcare professionals and system designers. BMJ health & care informatics vol. 26,1 (2019) (Year: 2019)).
With respect to claim 18, Feng, Cook, Mahajan and Takeda teach the method of claim 16. Mahajan teaches identifying therapies and treatments based on Uveal Melanoma classification (“Further characterization of the tumor subtype based on expression profiling, as described herein, is useful in evaluating the severity of disease and determining prognosis. For example, patients having GEP class 1 tumors have a low risk of metastasis and patients having GEP class 2 tumors have a high risk of metastasis. In addition, patients having PRAME positive uveal melanoma have a higher risk of metastasis than patients having PRAME negative uveal melanoma. Patients identified as having a high-risk of metastasis based on GEP class (i.e., having GEP class 2 subtype) or PRAME status (i.e., having PRAME positive subtype) may be treated more aggressively, for example, with surgery, adjuvant systemic therapy, or radiotherapy, or recommended for clinical trials” paragraph 0099)
Takeda further teaches the electronic medical record of the subject ("The medical information processing system can communicate with various kinds of external devices (e.g., computers, computer systems, medical apparatuses). For example, the medical information processing system can communicate with a computer that is installed in a medical institution or a research institution, and receives medical information of patients and the like through a communication line." Paragraph 0025, viewable by workers at medical/research institution).
Shah teaches that the users input one or more entries into the electronic medical record of the subject ("As a first step, we propose standardisation of the information model of problem and diagnosis records, and implementation of an application programming interface that will allow the retrieval of diagnosis and problem lists from the GP record or any other NHS EHR" page 5 col.2 lines 21-25) in view of the detected ocular pathology of the subject ("The fundamental principle is that clinicians curate a list of a patient's pertinent health problems or diagnoses, and link them to other entries related to the problem, such as prescriptions or clinical notes.1" page 2 col. 1 lines 9-13), and/or wherein the users order one or more therapies ("The fundamental principle is that clinicians curate a list of a patient's pertinent health problems or diagnoses, and link them to other entries related to the problem, such as prescriptions or clinical notes.1" page 2 col. 1 lines 9-13, prescriptions as therapies) and/or additional analyses of the subject in view of the detected ocular pathology of the subject ("The fundamental principle is that clinicians curate a list of a patient's pertinent health problems or diagnoses, and link them to other entries related to the problem, such as prescriptions or clinical notes.1" page 2 col. 1 lines 9-13, clinical notes as analysis).
Shah is analogous art to the claimed invention, reasonably pertinent to the problem of medical record updating faced by the inventor. Shah is directed towards guidance for medical record recording for healthcare professionals ("As a first step, we propose standardisation of the information model of problem and diagnosis records, and implementation of an application programming interface that will allow the retrieval of diagnosis and problem lists from the GP record or any other NHS EHR" page 5 col.2 lines 21-25). A person of reasonable skill in the art, before the effective filing date of the claimed invention would have found it obvious to combine the teachings of Shah’s medical recording guidance with the combined system of Feng, Cook, Mahajan, and Takeda, with the expectation that doing so would result in "Detailed and accurate records of patient problems and diagnoses" (Shah page 1 col. 1 Background lines 1-2).
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Feng, Cook, Mahajan, Takeda as applied to claim 14 above, and further in view of Shah and McRae (US 20080270178 A1).
With respect to claim 20, Feng, Cook, Mahajan, and Takeda teach the method of claim 14. Mahajan teaches identifying therapies and treatments based on Uveal Melanoma classification (“Further characterization of the tumor subtype based on expression profiling, as described herein, is useful in evaluating the severity of disease and determining prognosis. For example, patients having GEP class 1 tumors have a low risk of metastasis and patients having GEP class 2 tumors have a high risk of metastasis. In addition, patients having PRAME positive uveal melanoma have a higher risk of metastasis than patients having PRAME negative uveal melanoma. Patients identified as having a high-risk of metastasis based on GEP class (i.e., having GEP class 2 subtype) or PRAME status (i.e., having PRAME positive subtype) may be treated more aggressively, for example, with surgery, adjuvant systemic therapy, or radiotherapy, or recommended for clinical trials” paragraph 0099).
Shah teaches when the users input the entries into the electronic medical record of the subject ("As a first step, we propose standardisation of the information model of problem and diagnosis records, and implementation of an application programming interface that will allow the retrieval of diagnosis and problem lists from the GP record or any other NHS EHR" page 5 col.2 lines 21-25 and "The fundamental principle is that clinicians curate a list of a patient's pertinent health problems or diagnoses, and link them to other entries related to the problem, such as prescriptions or clinical notes.1" page 2 col. 1 lines 9-13).
Shah is analogous art to the claimed invention, reasonably pertinent to the problem of medical record updating faced by the inventor. Shah is directed towards guidance for medical record recording for healthcare professionals ("As a first step, we propose standardisation of the information model of problem and diagnosis records, and implementation of an application programming interface that will allow the retrieval of diagnosis and problem lists from the GP record or any other NHS EHR" page 5 col.2 lines 21-25). A person of reasonable skill in the art, before the effective filing date of the claimed invention would have found it obvious to combine the teachings of Shah’s medical recording guidance with the combined system of Feng, Cook, Mahajan, and Takeda, with the expectation that doing so would result in "Detailed and accurate records of patient problems and diagnoses" (Shah page 1 col. 1 Background lines 1-2).
McRae teaches a system that comprises the database ("wherein the inventory management application is configured to process the medication data and to interface with the database of electronic medical records for updating the inventory of medications." Paragraph 0009 lines 5-9) automatically orders one or more therapies in view of the detected ocular pathology of the subject ("The inventory management application may be further configured to automatically order medications based at least in part on the projected patient medication needs." Paragraph 0009 lines 20-23).
McRae is analogous art to the claimed invention, pertinent to the problem of medical treatment ordering faced by the inventor. McCrae is directed towards a medicinal inventory system connected to a medical database ("wherein the inventory management application is configured to process the medication data and to interface with the database of electronic medical records for updating the inventory of medications." Paragraph 0009 lines 5-9). A person of ordinary skill in the art before the effective filing date of the claimed invention would have found it obvious to combine the teachings of Feng, Cook, Mahajan, Takeda, and McRae with the expectation that doing so would lead to improvements in inventory accuracy and decreases in processing time when it comes to dispensing patient treatments ("The inventory management system should be configured to process medication data, and to provide integration with the electronic medical records, thus improving the accuracy and decreasing the processing times associated with inventory management processes." McRae Paragraph 0007 lines 5-9).
Response to Arguments
Applicant’s arguments, see Remarks, filed 02/17/2026, have been fully considered.
With respect to applicant’s arguments regarding the previously made 112(d) rejection of claim 8, the examiner agrees and withdraws the previously held rejection.
With respect to applicant’s arguments concerning the combination of Feng, Cook, and Mahajan, the examiner respectfully disagrees with many of the assertions made. In response to applicant's argument that the examiner's conclusion of obviousness is based upon improper hindsight reasoning (see page 8(I)), it must be recognized that any judgment on obviousness is in a sense necessarily a reconstruction based upon hindsight reasoning. But so long as it takes into account only knowledge which was within the level of ordinary skill at the time the claimed invention was made, and does not include knowledge gleaned only from the applicant's disclosure, such a reconstruction is proper. See In re McLaughlin, 443 F.2d 1392, 170 USPQ 209 (CCPA 1971). Additionally, the examiner points out that according to MPEP 2145 (IV) “One cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., Inc., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).”. The combination cannot be broken down and viewed outside of its combined context. Individually, Feng broadly teaches imaging, Cook broadly teaches GEP classification and Mahajan broadly teaches administering therapy. It’s the obvious combination of these references that is being used to teach the claimed limitations. Each source, in isolation, does not teach and hasn’t been used to teach all claim limitations of the claimset in its entirety. The additional arguments made against the combination in page 8 (I) have been tackled below in regards to the source they correspond to.
With respect to applicant’s arguments regarding Feng, in section II, applicant argues that “Nothing in Feng teaches or suggests that image-derived properties are indicative of gene expression profiles, let alone the specific uveal melanoma GEP classes recited in claim 1” (See page 8 (II)(A)) and particularly that “Feng does not teach or suggest GEP Classifications from images…concerns visual cancer status, not …gene expression signatures…relies on histopathological image features…” (See page 8 (II)(A)). The examiner disagrees. Feng does teach inferring molecular class from images. See paragraph 0034, Feng follows Coudray “Classification and mutation prediction from non-small lung cancer histopathology image using deep learning, Nature Medicine (2018).”, meaning, Feng predicts molecular/genomic features (HRD, MSI, TMB) from H&E images, trained to obtain molecular ground truth. Additionally, Feng does not limit itself to visual cancer status. It, itself, teaches against this prospect “the molecular basis for the pathology frequently cannot be determined by human observation alone. However, the effectiveness of a particular cancer treatment often depends on the molecular biology of a particular cancer strain rather than macroscale phenotype” (see paragraph 0003). Furthermore, Feng has not been cited as explicitly teaching GEP class 1 and claim 2 and instead exists as part of a combination, that as a whole does. Additional support for the inclusion of Feng can be found in the provided updated 103 rejections, made in the interest of advancing prosecution and increasing clarity.
With respect to applicant’s arguments regarding Cook on pages 8-9 (II) (B), applicant argues that Cook teaches away from the combination of Feng, Cook, and Mahajan and provides examples where it does not suggest or mention that GEP classification can be derived from images. The examiner disagrees and points out that silence is not indicative of a source teaching away (see MPEP 2143.01, in particular, “The level of disclosure in the specification of the application under examination or in relevant references may also be informative of the knowledge and skills of a person of ordinary skill in the art. For example, if the specification is entirely silent on how a certain step or function is achieved, that silence may suggest that figuring out how to achieve that step or function is within the ordinary skill in the art, provided that the specification complies with 35 U.S.C. 112. Uber Techs., Inc. v. X One, Inc., 957 F.3d 1334, 1339, 2020 USPQ2d 10476 (Fed. Cir. 2020) ("The specification of the '593 patent is entirely silent on how to transmit user locations and maps from a server to a user's mobile device, suggesting that a person of ordinary skill in the art was more than capable of selecting between the known methods of accomplishing this. The '593 patent confirms that its invention, including any necessary plotting, ‘utilizes existing platforms and infrastructure’ and does not ‘require development of new cell phone or PDA technology, nor do[es it] require development of new cellular communication infrastructure.’")”).
With respect to applicant’s section II part C arguments on page 9, applicant argues that there is No Motivation to Replace Molecular Assays with Imaging. The examiner again disagrees and notes that the primary source, Feng, does provide a reasonable expectation of success that image data could replace gene expression measurements, in particular, as previously stated above, Feng follows Coudray “Classification and mutation prediction from non-small lung cancer histopathology image using deep learning, Nature Medicine (2018).”, meaning Feng predicts molecular/genomic features (HRD, MSI, TMB) from H&E images, trained to obtain molecular ground truth. Due to the above the examiner also again disagrees about the combination being “hindsight-driven substitution”. As previously stated above, it must be recognized that any judgment on obviousness is in a sense necessarily a reconstruction based upon hindsight reasoning. But so long as it takes into account only knowledge which was within the level of ordinary skill at the time the claimed invention was made, and does not include knowledge gleaned only from the applicant's disclosure, such a reconstruction is proper. See In re McLaughlin, 443 F.2d 1392, 170 USPQ 209 (CCPA 1971).
With respect to applicant’s section III page 9 argument that Mahajan does not cure deficiencies present in the claim 1 mapping, the examiner finds the argument moot and disagrees on the basis that there are no deficiencies caused by Feng (See above).
With respect to applicant’s page 10 section IV arguments, the examiner once again disagrees with the applicant’s assertion that Feng only teaches image based cancer characteristics, and that the combination of Feng and Cook is improper and relies on combining isolated unrelated content. As mentioned above Feng does mention that observation is not enough to determine pathology and that molecular biology is needed (“the molecular basis for the pathology frequently cannot be determined by human observation alone. However, the effectiveness of a particular cancer treatment often depends on the molecular biology of a particular cancer strain rather than macroscale phenotype” paragraph 0003) and to that end Feng teaches prediction molecular/genomic features like (HRD, MSI, and TMB) (see FIG. 9/ paragraph 0112: “ predicting or diagnosing the HR (e.g. HRD) status (or microsatellite (in)stability or tumor mutation burden) of a cancer from an image” and “the model is trained to learn a mapping from an input image of a cancer to an HR status (HRD probability) for the cancer” paragraph 0043). Once again, the examiner points out that Cook is being used to teach GEP classes and that Feng is being used to teach the imaging concepts and that they work together in combination, making the arguments in section IV (A) and (B) moot. Cook is not being used to teach image tilling and Feng is not being used to teach GEP classes explicitly.
Since the arguments against independent claims 1 and 2 are not persuasive, the examiner disagrees with applicant’s page 10 section V arguments that Claims 7-13 and 21 should be considered allowable. Additionally, the examiner disagrees with the relevance of applicant’s assertion that’s claims 11-13 recite limitations not taught or suggested in combination with image-based GEP inference and that claim 21 does not cure the deficiency of the absence of GEP inferred from imaging teachings. As stated above, when it comes to Feng there are no deficiencies or absences in teachings (see above responses and updated rejections) and all sources of the combination, individually, do not have to recite each and every limitation present in the claims, in fact, piecemeal analysis of them cannot show non-obviousness.
Claims 14-20, similarly, still remain rejected. Once again, as stated above, when it comes to Feng there are no deficiencies or absences in teachings (see above responses and updated rejections) and all sources of the combination, individually, do not have to recite each and every limitation present in the claims, in fact, piecemeal analysis of them cannot show non-obviousness.
Applicant’s arguments in section claim 23 are disagreed with, similarly, to the claim 1 (see above) and claim 2 arguments (see above), for largely the same reasons. As stated above, when it comes to Feng there are no deficiencies or absences in teachings (see above responses and updated rejections) and all sources of the combination, individually, do not have to recite each and every limitation present in the claims, in fact, piecemeal analysis of them cannot show non-obviousness.
Due to the above reasoning, the examiner finds that the claims in question still remain rejected under U.S.C. 103, however on pages 11 and 12 the applicant does present potential claim amendments and the examiner does agree that they appear to overcome the currently held claim rejections. With that being said, the examiner declines to comment on whether they would be allowable until after they have been officially filled and the examiner can review them in their full context.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to REBECCA C WILLIAMS whose telephone number is (571)272-7074. The examiner can normally be reached M-F 7:30am - 4:00pm.
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, Andrew W Bee can be reached at (571)270-5183. 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.
/REBECCA COLETTE WILLIAMS/Examiner, Art Unit 2677
/ANDREW W BEE/Supervisory Patent Examiner, Art Unit 2677
Prosecution Insights