CN-114616590-B - System and method for processing slide images for digital pathology

Abstract

Systems and methods are disclosed for receiving a target electronic image corresponding to a target sample, the target sample 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 sample and/or at least one characteristic of the target electronic image, the machine learning system generated by processing a plurality of training images to predict the at least one characteristic, the training images comprising images of human tissue and/or algorithmically generated images, and outputting a target electronic image identifying a region of interest based on the at least one characteristic of the target sample and/or the at least one characteristic of the target electronic image.

Inventors

• J. Locke
• SUHY JULIANNE
• P. Schiffler
• J. S. izurita erera

Assignees

• 佩治人工智能公司

Dates

Publication Date

20260505

Application Date

20200908

Priority Date

20190909

Claims (20)

1. 1. A computer-implemented method for analyzing an electronic image corresponding to a sample, the method comprising: receiving a target electronic image corresponding to a target sample, the target sample 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 sample and/or at least one characteristic of the target electronic image, the machine learning system generated by processing a plurality of training images to predict the at least one characteristic, the training images including images of human tissue and/or algorithmically generated images, wherein the processing the plurality of training images processes the training images in a plurality of stages by using a first set of images having first-stage annotations in a first stage and using images having fewer annotations than the first set of images in at least a second stage; Outputting a target electronic image identifying a region of interest based on at least one characteristic of the target sample and/or at least one characteristic of the target electronic image; Displaying the target electronic image in a display; receiving a second target electronic image corresponding to the target sample; Determining a first portion of a target sample associated with a target electronic image; determining a second portion of the target sample associated with the second target electronic image; identifying 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, a first representation of a target electronic image and a second representation of a second target electronic image are displayed in a predetermined proximity to each other.
2. 2. The computer-implemented method of claim 1, wherein identifying the region of interest comprises displaying a heat map overlay on the target electronic image.
3. 3. The computer-implemented method of claim 1, wherein identifying a region of interest comprises displaying a heat map overlay on the target electronic image, the heat map overlay comprising shadows and/or shading based on a predicted likelihood of a location containing an anomaly.
4. 4. The computer-implemented method of claim 1, wherein identifying the region of interest comprises displaying a heat map overlay on the target electronic image, the heat map overlay comprising shadows and/or shading based on a predicted likelihood of the location containing an anomaly, Wherein the thermal map overlay is transparent or translucent.
5. 5. The computer-implemented method of claim 1, further comprising displaying a magnification window over at least a portion of the target electronic image, and The magnified image of the target specimen is presented in a magnification window at a magnification level different from the magnification level of the target electronic image.
6. 6. The computer-implemented method of claim 1, further comprising displaying a magnification window over at least a portion of the target electronic image, and A magnified image of the target specimen is presented in a magnification window at a magnification level different from the magnification level of the target electronic image, Wherein the magnification window includes selectable icons for overlay-shifting the heatmap onto the magnified image.
7. 7. The computer-implemented method of claim 1, further comprising: a slide tray tool that displays an overview identifying a target sample on the target electronic image; applying a machine learning system to the target electronic image to determine whether a portion of the target sample contains anomalies, and In response to determining that the portion contains an anomaly, an indicator of the anomaly is presented in the slide tray tool.
8. 8. The computer-implemented method of claim 1, further comprising: An annotation log is displayed that includes an indicator identifying a region of interest and a consultation request associated with the region of interest.
9. 9. The computer-implemented method of claim 1, further comprising: Determining whether there is a region of interest associated with the target electronic image and/or a region of interest associated with the second target electronic image; responsive to determining the region of interest associated with the target electronic image, displaying an indicator associated with the first representation of the target electronic image, and Responsive to determining the region of interest associated with the second target electronic image, an indicator associated with a second representation of the second target electronic image is displayed.
10. 10. A system for analyzing an electronic image corresponding to a sample, the system comprising: At least one memory storing instructions, and At least one processor executing instructions to perform a process comprising: receiving a target electronic image corresponding to a target sample, the target sample 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 sample and/or at least one characteristic of the target electronic image, the machine learning system generated by processing a plurality of training images to predict the at least one characteristic, the training images including images of human tissue and/or algorithmically generated images, wherein the processing the plurality of training images processes the training images in a plurality of stages by using a first set of images having first-stage annotations in a first stage and using images having fewer annotations than the first set of images in at least a second stage; Outputting a target electronic image identifying a region of interest based on at least one characteristic of the target sample and/or at least one characteristic of the target electronic image; Displaying the target electronic image in a display; receiving a second target electronic image corresponding to the target sample; Determining a first portion of a target sample associated with a target electronic image; determining a second portion of the target sample associated with the second target electronic image; identifying 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, a first representation of a target electronic image and a second representation of a second target electronic image are displayed in a predetermined proximity to each other.
11. 11. The system of claim 10, wherein identifying the region of interest comprises displaying a heat map overlay on the target electronic image.
12. 12. The system of claim 10, wherein identifying the region of interest comprises displaying a heat map overlay on the target electronic image, the heat map overlay comprising shadows and/or coloration based on a predicted likelihood of a location containing an anomaly.
13. 13. The system of claim 10, wherein identifying the region of interest comprises displaying a heat map overlay on the target electronic image, the heat map overlay comprising shadows and/or coloration based on a predicted likelihood of a location containing an anomaly, Wherein the thermal map overlay is transparent or translucent.
14. 14. The system of claim 10, further comprising displaying a magnification window over at least a portion of the target electronic image, and The magnified image of the target specimen is presented in a magnification window at a magnification level different from the magnification level of the target electronic image.
15. 15. The system of claim 10, further comprising displaying a magnification window over at least a portion of the target electronic image, and A magnified image of the target specimen is presented in a magnification window at a magnification level different from the magnification level of the target electronic image, Wherein the magnification window includes selectable icons for overlay-shifting the heatmap onto the magnified image.
16. 16. The system of claim 10, further comprising: a slide tray tool that displays an overview identifying a target sample on the target electronic image; applying a machine learning system to the target electronic image to determine whether a portion of the target sample contains anomalies, and In response to determining that the portion contains an anomaly, an indicator of the anomaly is presented in the slide tray tool.
17. 17. The system of claim 10, further comprising: An annotation log is displayed that includes an indicator identifying a region of interest and a consultation request associated with the region of interest.
18. 18. The system of claim 10, further comprising: Determining whether there is a region of interest associated with the target electronic image and/or a region of interest associated with the second target electronic image; responsive to determining the region of interest associated with the target electronic image, displaying an indicator associated with the first representation of the target electronic image, and Responsive to determining the region of interest associated with the second target electronic image, an indicator associated with a second representation of the second target electronic image is displayed.
19. 19. 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 sample, the method comprising: receiving a target electronic image corresponding to a target sample, the target sample 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 sample and/or at least one characteristic of the target electronic image, the machine learning system generated by processing a plurality of training images to predict the at least one characteristic, the training images including images of human tissue and/or algorithmically generated images, wherein the processing the plurality of training images processes the training images in a plurality of stages by using a first set of images having first-stage annotations in a first stage and using images having fewer annotations than the first set of images in at least a second stage; Outputting a target electronic image identifying a region of interest based on at least one characteristic of the target sample and/or at least one characteristic of the target electronic image; Displaying the target electronic image in a display; receiving a second target electronic image corresponding to the target sample; Determining a first portion of a target sample associated with a target electronic image; determining a second portion of the target sample associated with the second target electronic image; identifying 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, a first representation of a target electronic image and a second representation of a second target electronic image are displayed in a predetermined proximity to each other.
20. 20. The non-transitory computer-readable medium of claim 19, wherein identifying the region of interest comprises displaying a heat map overlay on the target electronic image, the heat map overlay comprising shadows and/or shading based on a predicted likelihood of a location-containing anomaly.

Description

System and method for processing slide images for digital pathology Related application(s) The present application claims priority from U.S. provisional application No. 62/897,745, filed on 9, 2019, the entire disclosure of which is hereby incorporated by reference in its entirety. Technical Field Various embodiments of the present disclosure relate generally to image-based sample analysis and related image processing methods. More particularly, certain embodiments of the present disclosure relate to systems and methods for identifying sample properties and providing a comprehensive pathology workflow based on processed images of tissue samples. Background In order to use digital pathology images in a hospital or research setting, it may be important to identify and classify the tissue type of the sample, the nature of the sample acquisition (e.g., prostatectomy, breast biopsy, mastectomy, etc.), and other relevant properties of the sample or image. It is desirable to have a way to provide a comprehensive pathology workflow based on processing tissue sample images. The following disclosure is directed to systems and methods for providing user interfaces and Artificial Intelligence (AI) tools that can be integrated into a workflow to accelerate and improve pathologist work solutions. The foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. The background description provided herein is for the purpose of generally presenting the context of the disclosure. Unless otherwise indicated herein, the materials described in this section are not prior art to the claims in this section and are not admitted to be prior art or prior art by inclusion in this section. Disclosure of Invention In accordance with certain aspects of the present disclosure, systems and methods for identifying sample properties and providing a comprehensive pathology workflow based on processed images of tissue samples are disclosed. A computer-implemented method for analyzing an electronic image corresponding to a sample includes receiving a target electronic image corresponding to a target sample, the target sample including 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 sample and/or at least one characteristic of the target electronic image, the machine learning system being generated by processing a plurality of training images to predict the at least one characteristic, the training images including images of a human and/or algorithmically generated images, and outputting a target electronic image identifying a region of interest based on the at least one characteristic of the target sample and/or the at least one characteristic of the target electronic image. A system for analyzing an electronic image corresponding to a sample includes a memory storing instructions and a processor executing the instructions to perform a process including receiving a target electronic image corresponding to a target sample, the target sample including 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 sample and/or at least one characteristic of the target electronic image, the machine learning system being generated by processing a plurality of training images to predict the at least one characteristic, the training images including images of human tissue and/or algorithmically generated images, and outputting a target electronic image identifying a region of interest based on the at least one characteristic of the target sample and/or the at least one characteristic of the target electronic image. A non-transitory computer readable medium storing instructions that, when executed by a processor, cause the processor to perform a method for analyzing an image corresponding to a sample, the method comprising receiving a target electronic image corresponding to a target sample, the target sample 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 sample and/or at least one characteristic of the target electronic image, the machine learning system generated by processing a plurality of training images to predict the at least one characteristic, the training images comprising images of a human and/or an algorithmically generated image, and outputting the target electronic image identifying a region of interest based on the at least one characteristic of the target sample and/or the at least one characteristic of the target electronic image. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosed embodiments, as claimed. Drawings The acco