Systems and methods for processing images of slides for digital pathology
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 determine at least one characteristic of the target specimen and/or at least one characteristic of the target electronic image, the machine learning system having been generated by processing a plurality of training images to predict at least one characteristic, the training images comprising images of human tissue and/or images that are algorithmically generated, and outputting the target electronic image identifying an area of interest based on the at least one characteristic of the target specimen and/or the at least one characteristic of the target electronic image.
1 . A computer-implemented method for analyzing an electronic image corresponding to a specimen, the computer-implemented method comprising:
receiving a first 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 first target electronic image to determine at least one characteristic of the target specimen and/or at least one characteristic of the first target electronic image, the machine learning system having been generated by processing a plurality of training images to predict the at least one characteristic;
determining, by the machine learning system, a predicted likelihood that a location contains a biomarker;
outputting the first target electronic image identifying an area of interest based on the at least one characteristic of the target specimen and/or the at least one characteristic of the first target electronic image by displaying a heat map overlay on the first target electronic image based on the predicted likelihood determined by the machine learning system that the location contains the biomarker;
receiving a second target electronic image associated with the target specimen;
determining, by the machine learning system, a first portion of the target specimen associated with the first target electronic image;
determining, by the machine learning system, a second portion of the target specimen associated with the second target electronic image;
identifying, by the machine learning system, whether the first portion and the second portion are identical or overlapping; and
in response to identifying that the first portion and the second portion are identical or overlapping, simultaneously displaying a first representation of the first target electronic image and a second representation of the second target electronic image in predetermined proximity to each other.
2 . The computer-implemented method of claim 1 , wherein the heat map overlay comprises shading and/or coloration based on the predicted likelihood that the location contains a biomarker.
3 . The computer-implemented method of claim 1 , further comprising:
displaying a magnification window, wherein the magnification window comprises a selectable icon for toggling the heat map overlay onto a magnified image.
4 . The computer-implemented method of claim 1 , further comprising:
displaying a slide tray tool identifying an overview of the target specimen on the first target electronic image;
applying the machine learning system to the first target electronic image to determine whether a part of the target specimen contains a biomarker; and
in response to determining the part contains a biomarker, presenting an indicator of the biomarker in the slide tray tool.
5 . The computer-implemented method of claim 1 , further comprising: displaying an annotation log comprising an indicator identifying the area of interest and a consultation request related to the area of interest.
6 . The computer-implemented method of claim 1 , further comprising:
determining, by applying machine learning techniques, whether there exists an area of interest associated with the first target electronic image and/or an area of interest associated with the second target electronic image;
in response to determining the area of interest associated with the first target electronic image exists, displaying an indicator associated with the first representation of the first target electronic image; and
in response to determining the area of interest associated with the second target electronic image exists, displaying an indicator associated with the second representation of the second target electronic image.
7 . The computer-implemented method of claim 1 , further comprising:
displaying a magnification window over at least a portion that is being magnified of the first target electronic image; and
presenting, in the magnification window, a magnified image of the target specimen at a magnification level that is different than a magnification level of the first target electronic image,
wherein the magnification window comprises one or more selectable icons that change the magnification level in the magnification window.
8 . The computer-implemented method of claim 1 , further including:
receiving a plurality of target electronic images associated with the target specimen;
determining, by the machine learning system, one or more portions of the target specimen associated with the plurality of target electronic images;
determining, by the machine learning system, whether the one or more portions of the target specimen of the plurality of target electronic images are identical or overlapping; and
in response to determining that any of the one or more portions of the target specimen of the plurality of target electronic images are identical or overlapping, simultaneously displaying target electronic images which include identical or overlapping portions in predetermined proximity to each other.
9 . The computer-implemented method of claim 1 , further including:
the machine learning system may analyze all of the first target electronic image and all of the second target electronic image and determine whether any areas of either image overlap or are identical; and
upon determining one or more areas overlap or are identical, displaying the first target electronic image and second target electronic image in predetermined proximity to each other.
10 . The computer-implemented method of claim 1 , the biomarker comprising an indication of an over-expression of a protein and/or gene product, amplification, or mutations of specific genes.
11 . A system for analyzing an electronic image corresponding to a specimen, the system comprising:
at least one memory storing instructions; and
at least one processor executing the instructions to perform operations comprising:
receiving a first 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 first target electronic image to determine at least one characteristic of the target specimen and/or at least one characteristic of the first target electronic image, the machine learning system having been generated by processing a plurality of training images to predict the at least one characteristic;
determining, by the machine learning system, a predicted likelihood, that a location contains a biomarker;
outputting the first target electronic image identifying an area of interest based on the at least one characteristic of the target specimen and/or the at least one characteristic of the first target electronic image by displaying a heat map overlay on the first target electronic image based on the predicted likelihood determined by the machine learning system that the location contains the biomarker;
receiving a second target electronic image associated with the target specimen;
determining, by the machine learning system, a first portion of the target specimen associated with the first target electronic image;
determining, by the machine learning system, a second portion of the target specimen associated with the second target electronic image;
identifying, by the machine learning system, whether the first portion and the second portion are identical or overlapping; and
in response to identifying that the first portion and the second portion are identical or overlapping, simultaneously displaying a first representation of the first target electronic image and a second representation of the second target electronic image in predetermined proximity to each other.
12 . The system of claim 11 , wherein the heat map overlay comprises shading and/or coloration based on the predicted likelihood that the location contains the biomarker.
13 . The system of claim 11 , further comprising:
displaying a magnification window, wherein the magnification window comprises a selectable icon for toggling the heat map overlay onto a magnified image.
14 . The system of claim 11 , the operations further comprising:
displaying a slide tray tool identifying an overview of the target specimen on the first target electronic image;
applying the machine learning system to the first target electronic image to determine whether a part of the target specimen contains the biomarker; and
in response to determining the part contains a biomarker, presenting an indicator of the biomarker in the slide tray tool.
15 . The system of claim 11 , the operations further comprising: displaying an annotation log comprising an indicator identifying the area of interest and a consultation request related to the area of interest.
16 . The system of claim 11 , the operations further comprising:
determining, by applying machine learning techniques, whether there exists an area of interest associated with the first target electronic image and/or an area of interest associated with the second target electronic image;
in response to determining the area of interest associated with the first target electronic image, displaying an indicator associated with the first representation of the first target electronic image; and
in response to determining the area of interest associated with the second target electronic image, displaying an indicator associated with the second representation of the second target electronic image.
17 . The system of claim 11 , the operations further comprising displaying a magnification window moving over the first target electronic image in response to a user input.
18 . A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform a method for analyzing an electronic image corresponding to a specimen, the method comprising:
receiving a first 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 first target electronic image to determine at least one characteristic of the target specimen and/or at least one characteristic of the first target electronic image the machine learning system having been generated by processing a plurality of training images to predict the at least one characteristic;
determining, by the machine learning system, a predicted likelihood, that a location contains a biomarker;
outputting the first target electronic image identifying an area of interest based on the at least one characteristic of the target specimen and/or the at least one characteristic of the first target electronic image by displaying a heat map overlay on the first target electronic image based on the predicted likelihood determined by the machine learning system that the location contains the biomarker;
receiving a second target electronic image associated with the target specimen;
determining, by the machine learning system, a first portion of the target specimen associated with the first target electronic image;
determining, by the machine learning system, a second portion of the target specimen associated with the second target electronic image;
identifying, by the machine learning system, whether the first portion and the second portion are identical or overlapping; and
in response to identifying that the first portion and the second portion are identical or overlapping, simultaneously displaying a first representation of the first target electronic image and a second representation of the second target electronic image in predetermined proximity to each other.
19 . The non-transitory computer-readable medium of claim 18 , wherein the heat map overlay comprises shading and/or coloration based on the predicted likelihood that the location contains a biomarker.
20 . The non-transitory computer-readable medium of claim 18 , wherein the method further comprises displaying a magnification window moving over the first target electronic image in response to a user input.