SYSTEMS AND METHODS FOR ASSESSING LIVER PATHOLOGY
In some aspects, the described systems and methods provide for a method for training a deep learning model to assess liver pathology, including accessing annotated liver pathology images associated with a group of patients in one or more randomized controlled clinical trials of nonalcoholic steatohepatitis therapy, each of the annotated liver pathology images including at least one annotation describing one or more tissue characteristic categories for a portion of the image, and training the deep learning model based on the annotated liver pathology images to predict the tissue characteristic categories, selected from a group comprising steatosis, lobular inflammation, hepatocyte ballooning, and fibrosis stage.
1 . A system for using a deep learning model to assess liver pathology, the system comprising:
at least one computer hardware processor; and
at least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by the at least one computer hardware processor, cause the at least one computer hardware processor to perform:
accessing a liver pathology image associated with a patient from a group of patients in one or more randomized controlled clinical trials of nonalcoholic steatohepatitis therapy; and
processing, using a deep learning model, the liver pathology image to predict one or more tissue characteristic categories for at least a portion of the liver pathology image, wherein the deep learning model is trained on a plurality of annotated liver pathology images including at least one annotation describing the one or more tissue characteristic categories for a portion of each image, wherein the deep learning model selects the one or more tissue characteristic categories from a group comprising steatosis, lobular inflammation, hepatocyte ballooning, and fibrosis stage.
2 . The system of claim 1 , wherein the processor-executable instructions cause the at least one computer hardware processor to further perform:
measuring a feature at or prior to the therapy of a patient, and measuring the same feature at a time point following therapy of the same patient and calculating differences in feature values to determine treatment-dependent effects.
3 . The system of claim 1 , wherein the processor-executable instructions cause the at least one computer hardware processor to further perform:
generating, for the liver pathology image, based on the predicted one or more tissue characteristic categories, a slide-level continuous score that corresponds to an underlying heterogeneous pattern of fibrosis observed in the liver pathology image.
4 . The system of claim 3 , wherein the one or more tissue characteristic categories are predicted on a pixel-level basis.
5 . The system of claim 3 , wherein the slide-level continuous score represents a continuum of severity of cellular and stromal injury to capture disease heterogeneity among different patients, wherein an ordinal classification system does not capture the disease heterogeneity among the different patients.
6 . The system of claim 1 , wherein the processor-executable instructions cause the at least one computer hardware processor to further perform:
for a liver pathology image, evaluating a performance of the deep learning model by comparing a fraction of tissue area in the liver pathology image assigned to each NAS component with an ordinal score determined by a pathologist, wherein the ordinal score is determined based on the NAS components.
7 . The system of claim 6 , wherein intra-observer reproducibility of the ordinal score of the liver pathology image by multiple pathologists is lower than reproducibility of predictions from multiple iterations of the trained deep learning model processing the liver pathology image.
8 . The system of claim 7 , wherein a group comprising steatosis, lobular inflammation, and hepatocyte ballooning corresponds to components of a nonalcoholic fatty liver disease activity score (NAS).
9 . A method for assessing liver pathology, the method comprising:
using at least one computer hardware processor to perform:
accessing a liver pathology image associated with a patient from a group of patients in one or more randomized controlled clinical trials of nonalcoholic steatohepatitis therapy; and
processing, using a deep learning model, the liver pathology image to predict one or more tissue characteristic categories for at least a portion of the liver pathology image, wherein the deep learning model is trained on a plurality of annotated liver pathology images including at least one annotation describing the one or more tissue characteristic categories for a portion of each image, wherein the deep learning model selects the one or more tissue characteristic categories from a group comprising steatosis, lobular inflammation, hepatocyte ballooning, and fibrosis stage.
10 . The method of claim 9 , further comprising, using the at least one computer hardware processor to perform:
measuring a feature at or prior to the therapy of a patient, and measuring the same feature at a time point following therapy of the same patient and calculating differences in feature values to determine treatment-dependent effects.
11 . The method of claim 9 , further comprising, using the at least one computer hardware processor to perform:
generating, for the liver pathology image, based on the predicted one or more tissue characteristic categories, a slide-level continuous score that corresponds to an underlying heterogeneous pattern of fibrosis observed in the liver pathology image.
12 . The method of claim 11 , wherein the one or more tissue characteristic categories are predicted on a pixel-level basis.
13 . The method of claim 11 , wherein the slide-level continuous score represents a continuum of severity of cellular and stromal injury to capture disease heterogeneity among different patients, wherein an ordinal classification system does not capture the disease heterogeneity among the different patients.
14 . The method of claim 9 , further comprising, using the at least one computer hardware processor to perform:
for a liver pathology image, evaluating a performance of the deep learning model by comparing a fraction of tissue area in the liver pathology image assigned to each NAS component with an ordinal score determined by a pathologist, wherein the ordinal score is determined based on the NAS components.
15 . The method of claim 14 , wherein intra-observer reproducibility of the ordinal score of the liver pathology image by multiple pathologists is lower than reproducibility of predictions from multiple iterations of the trained deep learning model processing the liver pathology image.
16 . The method of claim 15 , wherein a group comprising steatosis, lobular inflammation, and hepatocyte ballooning corresponds to components of a nonalcoholic fatty liver disease activity score (NAS).
17 . At least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by at least one processor, cause the at least one processor to perform a method for assessing liver pathology, the method comprising:
using at least one computer hardware processor to perform:
accessing a liver pathology image associated with a patient from a group of patients in one or more randomized controlled clinical trials of nonalcoholic steatohepatitis therapy; and
processing, using a deep learning model, the liver pathology image to predict one or more tissue characteristic categories for at least a portion of the liver pathology image, wherein the deep learning model is trained on a plurality of annotated liver pathology images including at least one annotation describing the one or more tissue characteristic categories for a portion of each image, wherein the deep learning model selects the one or more tissue characteristic categories from a group comprising steatosis, lobular inflammation, hepatocyte ballooning, and fibrosis stage.
18 . The at least one non-transitory computer-readable storage medium of claim 17 , wherein the at least one computer hardware processor is further configured to perform:
measuring a feature at or prior to the therapy of a patient, and measuring the same feature at a time point following therapy of the same patient and calculating differences in feature values to determine treatment-dependent effects.
19 . The at least one non-transitory computer-readable storage medium of claim 17 , wherein the at least one computer hardware processor is further configured to perform:
generating, for the liver pathology image, based on the predicted one or more tissue characteristic categories, a slide-level continuous score that corresponds to an underlying heterogeneous pattern of fibrosis observed in the liver pathology image.
20 . at least one non-transitory computer-readable storage medium of claim 19 , wherein the one or more tissue characteristic categories are predicted on a pixel-level basis.