Systems and methods for processing electronic images to infer biomarkers
Systems and methods are disclosed for receiving a target electronic image corresponding to a target specimen, the target specimen comprising a tissue sample of a patient, applying a machine learning system to the target electronic image to identify a region of interest of the target specimen and determine an expression level of, category of, and/or presence of a biomarker in the region of interest, the biomarker comprising at least one from among an epithelial growth factor receptor (EGFR) biomarker and/or a DNA mismatch repair (MMR) deficiency biomarker, the machine learning system having been generated by processing a plurality of training images to predict whether a region of interest is present in the target electronic image, the training images comprising images of human tissue and/or images that are algorithmically generated, and outputting the determined expression level of, category of, and/or presence of the biomarker in the region of interest.
1. A computer-implemented method for analyzing a plurality of digital images corresponding to a pathology specimen, comprising:
receiving the plurality of digital images of the pathology specimen;
dividing each of the plurality of digital images into a plurality of sub-regions;
generating a plurality of tiles from the plurality of sub-regions;
determining, by a machine learning system, a human epidermal growth factor receptor 2 (HER2) biomarker expression level prediction value for each of the plurality of digital images, the machine learning system having been trained by processing a plurality of training images, the determining of the HER2 biomarker expression level prediction value further comprising:
determining, by the machine learning system, tile-level HER2 biomarker expression level prediction values for the plurality of tiles;
aggregating the tile-level HER2 biomarker expression level prediction values into at least one part-level HER2 prediction; and
determining the HER2 biomarker expression prediction value based on the at least one part-level HER2 prediction;
determining, for each of the plurality of digital images, based on the HER2 biomarker expression level prediction values, a HER2 score; and
determining, for each of the plurality of digital images, whether gastric cancer is present based on the HER2 score value exceeding a predetermined threshold value.
2. The method of claim 1 , wherein determining, by the machine learning system, the HER2 biomarker expression level prediction further comprises:
analyzing histologic and immunohistochemistry (IHC) patient samples to characterize one or more constellations of morphologic features that distinguish HER2 biomarker levels.
3. The method of claim 1 , further comprising:
determining an immune response biomarker expression level, comprising IHC for markers including PDL1 and/or PD1; and
outputting, based on whether the immune response biomarker expression exceeds a threshold value, whether the pathology specimen is PDL1 and/or PD1 positive.
4. The method of claim 1 , further comprising:
determining, an epithelial growth factor receptor (EGFR) biomarker expression level; and
outputting, based on the EGFR biomarker expression level exceeding a threshold value, whether an EGFR mutation is present in the pathology specimen.
5. The method of claim 1 , wherein determining the HER2 biomarker expression level prediction comprises:
predicting, for each of the plurality of tiles, by the machine learning system, a tile-level probability of a presence of HER2 biomarkers at a level of HER2-low, HER2-high, 0, 1, 2, or 3;
predicting, for the at least one part-level HER2 prediction, a part-level probability of a presence of HER2 biomarkers at a level of HER2-low, HER2-high, 0, 1, 2, or 3;
classifying, based on the tile-level probability and part-level probability, HER2 biomarkers as positive at levels of approximately 1 to 2, the HER2 biomarkers being configured to facilitate a recommended treatment decision whether to administer one or more anti-HER2 antibodies.
6. The method of claim 5 , further comprising:
upon determining that the probability is greater than the predetermined threshold, outputting that one or more tiles that identify an invasive cancer.
7. The method of claim 1 , wherein determining the HER2 biomarker expression level prediction comprises using classifier training with a convolutional neural network (CNN).
8. The method of claim 1 , wherein the plurality of digital images are stained using Hematoxylin and Eosin (H&E).
9. The method of claim 1 , wherein the pathology specimen is a stomach tissue.
10. A system for analyzing a plurality of digital images corresponding to a pathology specimen, comprising:
at least one memory storing instructions; and
at least one processor configured to execute instructions to perform operations comprising:
receiving the plurality of digital images of the pathology specimen;
dividing each of the plurality of digital images into a plurality of sub-regions;
generating a plurality of tiles from the plurality of sub-regions;
determining, by a machine learning system, a human epidermal growth factor receptor 2 (HER2) biomarker expression level prediction value for each of the plurality of digital images, the machine learning system having been trained by processing a plurality of training images, the determining of the HER2 biomarker expression level prediction value further comprising:
determining, by the machine learning system, tile-level HER2 biomarker expression level prediction values for the plurality of tiles;
aggregating the tile-level HER2 biomarker expression level prediction values into at least one part-level HER2 prediction; and
determining the HER2 biomarker expression prediction value based on the at least one part-level HER2 prediction;
determining, for each of the plurality of digital images, based on the HER2 biomarker expression level prediction values, a HER2 score; and
determining, for each of the plurality of digital images, whether gastric cancer is present based on the HER2 score value exceeding a predetermined threshold value.
11. The system of claim 10 , further comprising:
determining, an immune response biomarker expression level comprising IHC for markers including PDL1 and/or PD1; and
outputting, based on whether the immune response biomarker expression exceeds a threshold value, whether the pathology specimen is PDL1 and/or PD1 positive.
12. The system of claim 10 , wherein determining, by the machine learning system, the HER2 biomarker expression level prediction comprises analyzing histologic and immunohistochemistry (IHC) patient samples data to characterize one or more constellations of morphologic features that distinguish HER2 biomarker levels.
13. The system of claim 10 , further comprising:
determining, an epithelial growth factor receptor (EGFR) biomarker expression level; and
outputting, based on the EGFR biomarker expression level exceeding a threshold value, whether an EGFR mutation is present in the pathology specimen.
14. The system of claim 10 , wherein the pathology specimen is a gastric cancer specimen.
15. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations for analyzing a plurality of digital images corresponding to a pathology specimen, the operations comprising:
receiving the plurality of digital images of the pathology specimen;
dividing each of the plurality of digital images into a plurality of sub-regions;
generating a plurality of tiles from the plurality of sub-regions;
determining, by a machine learning system, a human epidermal growth factor receptor 2 (HER2) biomarker expression level prediction value for each of the plurality of digital images, the machine learning system having been trained by processing a plurality of training images; the determining of the HER2 biomarker expression level prediction value further comprising:
determining, by the machine learning system, tile-level HER2 biomarker expression level prediction values for the plurality of tiles;
aggregating the tile-level HER2 biomarker expression level prediction values into at least one part-level HER2 prediction; and
determining the HER2 biomarker expression prediction value based on the at least one part-level HER2 prediction;
determining, for each of the plurality of digital images, based on the HER2 biomarker expression level prediction values, a HER2 score; and
determining, for each of the plurality of digital images, whether gastric cancer is present based on the HER2 score value exceeding a predetermined threshold value.
16. The computer-readable medium of claim 15 , further comprising:
determining, an epithelial growth factor receptor (EGFR) biomarker expression level; and
outputting, based on the EGFR biomarker expression level exceeding a threshold value, whether an EGFR mutation is present in the pathology specimen.
17. The computer-readable medium of claim 15 , wherein determining the HER2 biomarker expression level prediction comprises:
predicting for each of the plurality of tiles, by the machine learning system, a tile level probability of a presence of HER2 biomarkers at a level of HER2-low, HER2-high, 0, 1, 2, or 3;
predicting, for the at least one part-level HER2 prediction, a part-level probability of a presence of HER2 biomarkers at a level of HER2-low, HER2-high, 0, 1, 2, or 3;
classifying, based on the tile-level probability and part-level probability, HER2 biomarkers as positive at levels of approximately 1 to 2, the HER2 biomarkers being configured to facilitate a recommended treatment decision whether to administer one or more anti-HER2 antibodies.
18. The computer-readable medium of claim 17 , further comprising:
determining an immune response biomarker expression level, comprising IHC for markers including PDL1 and/or PD1; and
outputting, based on whether the immune response biomarker expression exceeds a threshold value, whether the pathology specimen is PDL1 and/or PD1 positive.
19. The computer-readable medium of claim 15 , wherein determining the HER2 biomarker expression level prediction comprises using classifier training with a convolutional neural network (CNN) to predict a probability that gastric cancer is present in tiles created from the plurality of digital images.
20. The computer-readable medium of claim 15 , wherein the pathology specimen is a gastric cancer specimen.