DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 08/01/2024 is/are compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Office Action Summary
Claim(s) 11, 13-15, and 17-19 is/are interpreted under 35 USC 112(f).
Claim(s) 1-4, 6, 10-14, and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brozek et al (US 2021/0192722 A1) in view of Ho et al (US 2018/0024064 A1).
Claim(s) 7 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brozek et al (US 2021/0192722 A1) in view of Ho et al (US 2018/0024064 A1), further in view of Amat Roldan et al (US 2016/0042514 A1).
Claim(s) 8 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brozek et al (US 2021/0192722 A1) in view of Ho et al (US 2018/0024064 A1) and Amat Roldan et al (US 2016/0042514 A1), further in view of Smith (US 2015/0148658 A1).
Claim(s) 9 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brozek et al (US 2021/0192722 A1) in view of Ho et al (US 2018/0024064 A1) and Amat Roldan et al (US 2016/0042514 A1), further in view of Richter et al (US 2013/0060139 A1).
Claim(s) 5 and 15 is/are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are: “quantification module” in claim(s) 11 and 15, “selection module” in claim(s) 11 and 13, “construction module” in claim(s) 11 and 17-19, and “validation module” in claim(s) 11 and 14.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-4, 6, 10-14, and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brozek et al (US 2021/0192722 A1) in view of Ho et al (US 2018/0024064 A1).
Regarding claim(s) 1, Brozek teaches a method for assessing nonalcoholic steatohepatitis (NASH) cirrhosis in a liver biopsy sample, the method comprising:
extracting, from the liver biopsy sample, image data indicative of one or more histopathological features, wherein the one or more histopathological features comprise septa and/or nodules and/or fibrosis (Figure 1; Claim 1: “providing a liver biopsy slide from said subject”; Paragraph [0022]: “recognition of NASH specific fibrosis histological patterns would allow a more accurate quantification of collagen morphology (Septa) and proportionate area (CPA)”; and Paragraph [0060] – Paragraph [0061]: “Extraction of biomedical relevant images from WSI. Images representing either micro-patterns (cells) and macro-patterns(tissue regions) are extracted to be analyzed […] micro-patterns (ballooning and inflammation) and macro-patterns (NASH fibrosis, hepatic fibrosis) […]”); and
analysing the extracted image data, using a machine learning model trained to assess the one or more histopathological features, to determine a degree of NASH cirrhosis (Claim 8: “submitting said slide to a deep learning model to recognize patterns of liver fibrosis and/or to measure collagen proportion area (CPA), and score liver fibrosis […] as follows: F = 0, no liver fibrosis F = 0; F = 1, minimal liver fibrosis; F = 2, significant liver fibrosis; F = 3, moderate liver fibrosis; and F = 4, severe liver fibrosis”; and Paragraph [0022]: “Deep-Learning (DL) pattern recognition algorithms have recently shown to be able to capture accurately both micro and macro tissue patterns, furthermore mimicking the diagnostic workflow of the pathologist. Using such technologies, histological patterns can be automatically predicted”), wherein training the machine learning model comprises:
providing a plurality of training samples and a plurality of validation samples, each sample comprising a graded liver biopsy sample (Figure 10: “Select 75% of samples for training/testing of CNN network and 25% for independent validation”; and Paragraph [0028]: “Generalization properties of quantification pipelines for each NASH clinical component were assessed using independent cohorts for development, testing and validation. The final goal was to translate micro/macro predictions and quantifications (CPA/septa morphology) into clinically relevant information and to validate against the reference pathologist annotations”);
selecting a subset of quantified parameters of the one or more histopathological features (Figure 10: “Training/testing set defined based on main NASH fibrosis histological patterns i.e., negative, peri-sinusoidal, peri-portal, bridging” and “Based on prediction percentages of each pattern above we define cut-off for generating a fibrosis score […]; Paragraph [0024] – Paragraph [0028]: “Given the different pathological and histological nature of each clinical parameter […] development process that was channeled into individual analysis pipelines: I. preprocess (Fields Of Views (FOVs) extraction, tissue segmentation, normalization); II. predict NASH pathological micro/macro pattern DL (Inflammatory, ballooned cells/hepatic fibrosis FOV type) and quantify steatosis area; III. data aggregation to the biopsy level; Generalization properties of quantification pipelines for each NASH clinical component were assessed using independent cohorts for development, testing and validation […]; and Paragraph [0672]: “Convolutional Neural Networks (CNN) were used to construct individual models to detect inflammatory cells, ballooned hepatocytes and, a third model, to recognize histological patterns of NASH fibrosis”);
constructing a model for assessing the one or more histopathological features from the subset of quantified parameters (Figure 10; Paragraph [0672]: “Convolutional Neural Networks (CNN) were used to construct individual models to detect inflammatory cells, ballooned hepatocytes and, a third model, to recognize histological patterns of NASH fibrosis”; Paragraph [0664]: “[…] fully automated CPA and septa analysis pipeline were applied independently to quantify collagen morphology and total expression”; and Paragraph [0681] – [0682]: “Development of Hepatic Fibrosis Morphometric Model”); and
validating the constructed model using the validation samples (Figure 10: “Select 75% of samples for training/testing of CNN network and 25% for independent validation”; Paragraph [0028]: “Generalization properties of quantification pipelines for each NASH clinical component were assessed using independent cohorts for development, testing and validation […]”; Paragraph [0680]: “The final model showed excellent accuracy at recognizing all fibrosis patterns in the independent validation set (Cohort III) […]”; Paragraph [0673]: “Cohen's Kappa was used to quantify the agreement between manual and fully automated fibrosis scores”; and Paragraph [0676]: “The most optimal network (best tradeoff between training-loss and validation-loss) was selected as the final model”).
Brozek fails to teach quantifying parameters of the one or more histopathological features from image data of each of the training samples. However, Ho teaches to quantifying parameters of the one or more histopathological features from image data of each of the training samples (Paragraph [0070]: “Unstained 4 μm sections tissue sections underwent 2PE/SHG using the Genesis® 200 […] A 20× objective was used to acquire multi-tiled images (600 μm2 total area) from each sample, resulting in a spatial resolution of approximately 0.2 μm […] Analysis parameters assessed included 2PE/SHG ratio, aggregated fiber percentage, total number, area, width, and length of fibers, and number of fiber cross-links”; Paragraph [0071]: “Fiber length density (FLD) was calculated using an approach adapted from stereology. To calculate FLD, the number of reticulin-stained fibers that crossed over a fixed line distance of 239.6 μm was manually counted (FIG. 6)”; and Paragraph [0068]: “[…] applicability of two-photon excitation/second harmonic generation laser scanning microscopy (2PE/SHG) for quantification of fibrosis in unstained bone marrow core biopsy samples and compared its performance to the EC scoring system and a stereology-based quantitative method”).
Therefore, it would have been obvious to one of ordinary skill in the art to combine Brozek and Ho before the effective filing date of the claimed invention. The motivation for this combination of references would have been to incorporate the quantitative fibrosis parameter analysis of Ho into the machine learning-based histopathological assessment of Brozek in order to allow a more accurate quantification of collagen morphology (Septa) and proportionate area (CPA). This motivation for the combination of Brozek and Ho is supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention. MPEP 2141 (III).
Regarding claim(s) 11, Brozek teaches a system for assessing nonalcoholic steatohepatitis (NASH) cirrhosis in a liver biopsy sample, the system comprising:
a processor (Paragraph [0672]: “Convolutional Neural Networks (CNN) were used to construct individual models to detect inflammatory cells, ballooned hepatocytes and, a third model, to recognize histological patterns of NASH fibrosis”); and
a computer-readable memory (Paragraph [0672]) coupled to the processor and having instructions stored thereon that are executable by the processor to:
receive image data of the liver biopsy sample indicative of one or more histopathological features, wherein the one or more histopathological features comprise septa and/or nodules and/or fibrosis (Figure 1; Claim 1: “providing a liver biopsy slide from said subject”; Paragraph [0022]: “recognition of NASH specific fibrosis histological patterns would allow a more accurate quantification of collagen morphology (Septa) and proportionate area (CPA)”; and Paragraph [0060] – Paragraph [0061]: “Extraction of biomedical relevant images from WSI. Images representing either micro-patterns (cells) and macro-patterns(tissue regions) are extracted to be analyzed […] micro-patterns (ballooning and inflammation) and macro-patterns (NASH fibrosis, hepatic fibrosis) […]”); and
analyse the image data, using a machine learning model trained to assess the one or more histopathological features, to determine a degree of NASH cirrhosis (Claim 8: “submitting said slide to a deep learning model to recognize patterns of liver fibrosis and/or to measure collagen proportion area (CPA), and score liver fibrosis […] as follows: F = 0, no liver fibrosis F = 0; F = 1, minimal liver fibrosis; F = 2, significant liver fibrosis; F = 3, moderate liver fibrosis; and F = 4, severe liver fibrosis”; and Paragraph [0022]: “Deep-Learning (DL) pattern recognition algorithms have recently shown to be able to capture accurately both micro and macro tissue patterns, furthermore mimicking the diagnostic workflow of the pathologist. Using such technologies, histological patterns can be automatically predicted”), wherein the machine learning model comprises:
a selection module for selecting a subset of quantified parameters of the one or more histopathological features (Figure 10: “Training/testing set defined based on main NASH fibrosis histological patterns i.e., negative, peri-sinusoidal, peri-portal, bridging” and “Based on prediction percentages of each pattern above we define cut-off for generating a fibrosis score […]; Paragraph [0024] – Paragraph [0028]: “Given the different pathological and histological nature of each clinical parameter […] development process that was channeled into individual analysis pipelines: I. preprocess (Fields Of Views (FOVs) extraction, tissue segmentation, normalization); II. predict NASH pathological micro/macro pattern DL (Inflammatory, ballooned cells/hepatic fibrosis FOV type) and quantify steatosis area; III. data aggregation to the biopsy level; Generalization properties of quantification pipelines for each NASH clinical component were assessed using independent cohorts for development, testing and validation […]; and Paragraph [0672]: “Convolutional Neural Networks (CNN) were used to construct individual models to detect inflammatory cells, ballooned hepatocytes and, a third model, to recognize histological patterns of NASH fibrosis”);
a construction module for constructing a model for assessing the one or more histopathological features from the subset of quantified parameters (Figure 10; Paragraph [0672]: “Convolutional Neural Networks (CNN) were used to construct individual models to detect inflammatory cells, ballooned hepatocytes and, a third model, to recognize histological patterns of NASH fibrosis”; Paragraph [0664]: “[…] fully automated CPA and septa analysis pipeline were applied independently to quantify collagen morphology and total expression”; and Paragraph [0681] – [0682]: “Development of Hepatic Fibrosis Morphometric Model”); and
a validation module for validating the constructed model using a plurality of validation samples, each validation sample comprises a graded liver biopsy sample (Figure 10: “Select 75% of samples for training/testing of CNN network and 25% for independent validation”; Paragraph [0028]: “Generalization properties of quantification pipelines for each NASH clinical component were assessed using independent cohorts for development, testing and validation […]”; Paragraph [0680]: “The final model showed excellent accuracy at recognizing all fibrosis patterns in the independent validation set (Cohort III) […]”; Paragraph [0673]: “Cohen's Kappa was used to quantify the agreement between manual and fully automated fibrosis scores”; and Paragraph [0676]: “The most optimal network (best tradeoff between training-loss and validation-loss) was selected as the final model”).
Brozek fails to teach a quantification module for quantifying parameters of the one or more histopathological features from image data of each of a plurality of training samples, each training sample comprising a graded liver biopsy sample. However, Ho teaches a quantification module for quantifying parameters of the one or more histopathological features from image data of each of a plurality of training samples, each training sample comprising a graded liver biopsy sample (Paragraph [0070]: “Unstained 4 μm sections tissue sections underwent 2PE/SHG using the Genesis® 200 […] A 20× objective was used to acquire multi-tiled images (600 μm2 total area) from each sample, resulting in a spatial resolution of approximately 0.2 μm […] Analysis parameters assessed included 2PE/SHG ratio, aggregated fiber percentage, total number, area, width, and length of fibers, and number of fiber cross-links”; Paragraph [0071]: “Fiber length density (FLD) was calculated using an approach adapted from stereology. To calculate FLD, the number of reticulin-stained fibers that crossed over a fixed line distance of 239.6 μm was manually counted (FIG. 6)”; and Paragraph [0068]: “[…] applicability of two-photon excitation/second harmonic generation laser scanning microscopy (2PE/SHG) for quantification of fibrosis in unstained bone marrow core biopsy samples and compared its performance to the EC scoring system and a stereology-based quantitative method”).
Therefore, it would have been obvious to one of ordinary skill in the art to combine Brozek and Ho before the effective filing date of the claimed invention. The motivation for this combination of references would have been to incorporate the quantitative fibrosis parameter analysis of Ho into the machine learning-based histopathological assessment of Brozek in order to allow a more accurate quantification of collagen morphology (Septa) and proportionate area (CPA). This motivation for the combination of Brozek and Ho is supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention. MPEP 2141 (III).
Regarding claim(s) 2 and 12, Brozek as modified by Ho teaches the method as claimed in claim 1, where Ho teaches wherein the image data is extracted by second harmonic generation (SHG) microscopy and/or two photon excitation fluorescence (TPEF) microscopy (Paragraph [0068]: “[…] applicability of two-photon excitation/second harmonic generation laser scanning microscopy (2PE/SHG) for quantification of fibrosis in unstained bone marrow core biopsy samples”; and Paragraph [0070]: “Unstained 4 μm sections tissue sections underwent 2PE/SHG using the Genesis® 200 […] A 20× objective was used to acquire multi-tiled images (600 μm2 total area) from each sample).
Regarding claim(s) 3 and 13, Brozek as modified by Ho teaches the method as claimed in claim 1, where Brozek teaches wherein selecting the subset of quantified parameters comprises a sequential feature selection (Figure 10: “Training/testing set defined based on main NASH fibrosis histological patterns i.e., negative, peri-sinusoidal, peri-portal, bridging” and “Based on prediction percentages of each pattern above we define cut-off for generating a fibrosis score […]; Paragraph [0024] – Paragraph [0028]: “Given the different pathological and histological nature of each clinical parameter […] development process that was channeled into individual analysis pipelines: I. preprocess (Fields Of Views (FOVs) extraction, tissue segmentation, normalization); II. predict NASH pathological micro/macro pattern DL (Inflammatory, ballooned cells/hepatic fibrosis FOV type) and quantify steatosis area; III. data aggregation to the biopsy level; Generalization properties of quantification pipelines for each NASH clinical component were assessed using independent cohorts for development, testing and validation […]; and Paragraph [0672]: “Convolutional Neural Networks (CNN) were used to construct individual models to detect inflammatory cells, ballooned hepatocytes and, a third model, to recognize histological patterns of NASH fibrosis”).
Regarding claim(s) 4 and 14, Brozek as modified by Ho teaches the method as claimed in claim 1, where Brozek teaches wherein validating the constructed model comprises a leave-one-out validation (Figure 10: “Select 75% of samples for training/testing of CNN network and 25% for independent validation”; Paragraph [0028]: “Generalization properties of quantification pipelines for each NASH clinical component were assessed using independent cohorts for development, testing and validation […]”; Paragraph [0680]: “The final model showed excellent accuracy at recognizing all fibrosis patterns in the independent validation set (Cohort III) […]”; Paragraph [0673]: “Cohen's Kappa was used to quantify the agreement between manual and fully automated fibrosis scores”; and Paragraph [0676]: “The most optimal network (best tradeoff between training-loss and validation-loss) was selected as the final model”).
Regarding claim(s) 6 and 16, Brozek as modified by Ho teaches the method as claimed in claim 1, where Brozek teaches wherein the one or more histopathological features comprises a combination of all of septa, nodules and fibrosis (Figure 1; Claim 1: “providing a liver biopsy slide from said subject”; Paragraph [0022]: “recognition of NASH specific fibrosis histological patterns would allow a more accurate quantification of collagen morphology (Septa) and proportionate area (CPA)”; and Paragraph [0060] – Paragraph [0061]: “Extraction of biomedical relevant images from WSI. Images representing either micro-patterns (cells) and macro-patterns(tissue regions) are extracted to be analyzed […] micro-patterns (ballooning and inflammation) and macro-patterns (NASH fibrosis, hepatic fibrosis) […]”).
Regarding claim(s) 10, Brozek as modified by Ho teaches a method for evaluating efficacy of a therapeutic intervention, where Brozek teaches the method comprising:
determining, from a first liver biopsy sample of a subject before the therapeutic intervention, a first degree of NASH cirrhosis using the method as claimed in claim 1 (Claim 8: “submitting said slide to a deep learning model to recognize patterns of liver fibrosis and/or to measure collagen proportion area (CPA), and score liver fibrosis […] as follows: F = 0, no liver fibrosis F = 0; F = 1, minimal liver fibrosis; F = 2, significant liver fibrosis; F = 3, moderate liver fibrosis; and F = 4, severe liver fibrosis”; Paragraph [0221]: “assess the efficacy of a medical treatment based on a drug administration to treat NASH disease”; Paragraph [0255]: “the subject is suffering from NASH, the method of the invention thereby allowing determining the efficacy of a drug for the treatment of the NASH disease, classifying the subject as responder/non-responder to a treatment for NASH, or monitoring the evolution of the NASH state of the subject”);
determining, from a second liver biopsy sample of the subject after the therapeutic intervention, a second degree of NASH cirrhosis using the method as claimed in any one of the preceding claims (Claim 8: “submitting said slide to a deep learning model to recognize patterns of liver fibrosis and/or to measure collagen proportion area (CPA), and score liver fibrosis […] as follows: F = 0, no liver fibrosis F = 0; F = 1, minimal liver fibrosis; F = 2, significant liver fibrosis; F = 3, moderate liver fibrosis; and F = 4, severe liver fibrosis”; Paragraph [0221]: “assess the efficacy of a medical treatment based on a drug administration to treat NASH disease”; Paragraph [0255]: “the subject is suffering from NASH, the method of the invention thereby allowing determining the efficacy of a drug for the treatment of the NASH disease, classifying the subject as responder/non-responder to a treatment for NASH, or monitoring the evolution of the NASH state of the subject”); and
comparing the first degree and second degree to determine efficacy of the therapeutic intervention (Claim 8: “submitting said slide to a deep learning model to recognize patterns of liver fibrosis and/or to measure collagen proportion area (CPA), and score liver fibrosis […] as follows: F = 0, no liver fibrosis F = 0; F = 1, minimal liver fibrosis; F = 2, significant liver fibrosis; F = 3, moderate liver fibrosis; and F = 4, severe liver fibrosis”; Paragraph [0221]: “assess the efficacy of a medical treatment based on a drug administration to treat NASH disease”; Paragraph [0255]: “the subject is suffering from NASH, the method of the invention thereby allowing determining the efficacy of a drug for the treatment of the NASH disease, classifying the subject as responder/non-responder to a treatment for NASH, or monitoring the evolution of the NASH state of the subject”).
Claim(s) 7 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brozek et al (US 2021/0192722 A1) in view of Ho et al (US 2018/0024064 A1), further in view of Amat Roldan et al (US 2016/0042514 A1).
Regarding claim(s) 7 and 17, Brozek as modified by Ho teaches the method as claimed in claim 1, but do not specifically teach wherein constructing the model comprises determining whether the model correlates with hepatic venous pressure gradient (HVPG) measurements. However, Amat Roldan teaches wherein constructing the model comprises determining whether the model correlates with hepatic venous pressure gradient (HVPG) measurements (Figure 4; Paragraph [0060]: “The computational model is trained according to data by principal components decomposition where three first components are kept and a random forest of the regression trees fits the data to the HVPG, measured values”; and Paragraph [0048]: “[…] the cross validation of the HVPG measured invasively versus the predicted HVPG […]”).
Therefore, it would have been obvious to one of ordinary skill in the art to combine Brozek, Ho and Amat Roldan before the effective filing date of the claimed invention. The motivation for this combination of references would have been to improve the clinical relevance and predictive accuracy of machine learning models for liver disease assessment by correlating imaging- or histology-derived features with established hemodynamic clinical indicators such as HVPG, as taught by Amat Roldan, which identifies HVPG as a gold-standard measurement for assessing portal hypertension and validating predictive models against measured HVPG values. This motivation for the combination of Brozek, Ho and Amat Roldan is supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention. MPEP 2141 (III).
Claim(s) 8 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brozek et al (US 2021/0192722 A1) in view of Ho et al (US 2018/0024064 A1) and Amat Roldan et al (US 2016/0042514 A1), further in view of Smith (US 2015/0148658 A1).
Regarding claim(s) 8 and 18, Brozek as modified by Ho and Amat Roldan teaches the method as claimed in claim 7, where Brozek teaches wherein constructing the model (Figure 10; Paragraph [0672]: “Convolutional Neural Networks (CNN) were used to construct individual models to detect inflammatory cells, ballooned hepatocytes and, a third model, to recognize histological patterns of NASH fibrosis”; Paragraph [0664]: “[…] fully automated CPA and septa analysis pipeline were applied independently to quantify collagen morphology and total expression”; and Paragraph [0681] – [0682]: “Development of Hepatic Fibrosis Morphometric Model”). However, Smith teaches (Paragraph [0005]: “Patients with decompensated cirrhosis present with symptoms of jaundice, ascites, bleeding varices, and/or hepatic encephalopathy […]”; Paragraph [0010]: “The current role of medical imaging is for the detection of complications of cirrhosis including detection of varices, ascites, hepatocellular carcinoma […]”; and Paragraph [0024]: “the step of identifying varices on medical images or by endoscopy report and using the presence of varices to diagnose cirrhosis with portal hypertension”).
Therefore, it would have been obvious to one of ordinary skill in the art to combine Brozek, Ho, Amat Roldan, and Smith before the effective filing date of the claimed invention. The motivation for this combination of references would have been to apply known machine learning models to predict clinically meaningful outcomes, such as the presence or absence of varices, because Smith teaches that varices are clinically detectable signs of portal hypertension and that the presence or absence of varices is used to diagnose cirrhosis with portal hypertension, thereby providing a well-established diagnostic target for predictive modeling. This motivation for the combination of Brozek, Ho, Amat Roldan, and Smith is supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention. MPEP 2141 (III).
Claim(s) 9 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brozek et al (US 2021/0192722 A1) in view of Ho et al (US 2018/0024064 A1) and Amat Roldan et al (US 2016/0042514 A1), further in view of Richter et al (US 2013/0060139 A1).
Regarding claim(s) 9 and 19, Brozek as modified by Ho and Amat Roldan teaches the method as claimed in claim 7, where Brozek teaches wherein constructing the model (Figure 10; Paragraph [0672]: “Convolutional Neural Networks (CNN) were used to construct individual models to detect inflammatory cells, ballooned hepatocytes and, a third model, to recognize histological patterns of NASH fibrosis”; Paragraph [0664]: “[…] fully automated CPA and septa analysis pipeline were applied independently to quantify collagen morphology and total expression”; and Paragraph [0681] – [0682]: “Development of Hepatic Fibrosis Morphometric Model”) comprises where Amat Roldan teaches determining whether the model identifies hepatic venous pressure gradient (HVPG) (Figure 4; Paragraph [0060]: “The computational model is trained according to data by principal components decomposition where three first components are kept and a random forest of the regression trees fits the data to the HVPG, measured values”; and Paragraph [0048]: “[…] the cross validation of the HVPG measured invasively versus the predicted HVPG […]”).
Brozek, Ho, and Amat Roldan fails to teaches wherein (Paragraph [0003]: “PHT is defined according to a "portal pressure gradient," or, the difference in pressure between the portal vein and the hepatic veins, for example of 10 mmHg or greater. A typical portal venous pressure under normal physiological conditions is less than or equal to approximately 10 mmHg, and the hepatic venous pressure gradient (HVPG) is less than approximately 5 mmHg […]”; and Paragraph [0046]: “ In the portal venous system, "normal" conditions are a pressure approximately 5 mmHg or less, and a pressure gradient between the portal and the hepatic vein of approximately 10 mmHg or less”).
Therefore, it would have been obvious to one of ordinary skill in the art to combine Brozek, Ho, Amat Roldan, and Richter before the effective filing date of the claimed invention. The motivation for this combination of references would have been to evaluate whether predicted HVPG values fall outside clinically established ranges, since Richter teaches that HVPG values correspond to defined thresholds indicative of portal hypertension, including normal values below approximately 5 mmHg and elevated values of 10 mmHg or greater, and Amat teaches constructing predictive models that fit data to measured HVPG values, thereby making it desirable to apply such models to identify whether HVPG values fall outside clinically relevant ranges. This motivation for the combination of Brozek, Ho, Amat Roldan, and Richter is supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention. MPEP 2141 (III).
Allowable Subject Matter
Claim(s) 5 and 15 is/are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Relevant Prior Art Directed to State of Art
Cales et al (US 2018/0075600 A1) are relevant prior art not applied in the rejection(s) above. Cales discloses a method for assessing the presence and/or the severity of a lesion in an organ or tissue of a subject through automated analysis of at least one image of said organ or tissue, comprising the calculation of a score combining descriptors of said image, wherein said method comprises the steps of: a. measuring on said at least one image at least two descriptors of said at least one image; b. mathematically combining said at least two descriptors in a score, wherein said mathematical combination does not consist in a division of two descriptors; and c. assessing the presence and/or the severity of a lesion in the organ or tissue, based on the value of the score calculated at step (b).
Yu et al (US 2015/0339816 A1) are relevant prior art not applied in the rejection(s) above. Yu discloses a method for assessing fibrosis in a tissue using a test image which is an image of the tissue, wherein the test image comprises a plurality of pixels having respective intensity values and wherein the method comprises: (1a) automatically identifying, from the test image, a portal collagen area, a septal collagen area and a fibrillar collagen area respectively comprising pixels representing portal collagen, septal collagen and fibrillar collagen of the tissue, the fibrillar collage including collagen in both peri-cellular and peri-sinusoidal spaces; (1b) obtaining quantitative values of one or more features for each identified area based on characteristics of the identified area in the test image; and (1c) assessing fibrosis using the quantitative values obtained for all the identified areas.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JONGBONG NAH whose telephone number is (571) 272-1361. The examiner can normally be reached M - F: 9:00 AM - 5:30 PM.
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, ONEAL MISTRY can be reached on 313-446-4912. 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.
/JONGBONG NAH/Examiner, Art Unit 2674
/ONEAL R MISTRY/Supervisory Patent Examiner, Art Unit 2674
Prosecution Insights