US 2026/0301178 A1 · SYSTEMS AND METHODS TO PROCESS ELECTRONIC IMAGES TO CATEGORIZE INTRA-SLIDE SPECIMEN TISSUE TYPE

Abstract

Systems and methods are disclosed for identifying tissue specimen types present in digital whole slide images. In some aspects, tissue specimen types may be identified using unsupervised machine learning techniques for out-of-distribution detection. For example, a digital whole slide image of a tissue specimen and a recorded tissue specimen type for the digital whole slide image may be received. One or more feature vectors may be extracted from one or more foreground tiles of the digital whole slide image identified as including the tissue specimen, and a distribution learned by a machine learning system for the recorded tissue specimen type may be received. Using the distribution, a probability of the feature vectors corresponding to the recorded tissue specimen type may be computed and used as a basis for classifying the foreground tiles from which the feature vectors are extracted as an in-distribution foreground tile or an out-of-distribution foreground tile.

Claims20

Dependent claims

A method for processing digital images using a tissue classification platform, the method comprising:

receiving, by one or more processors, a digital image of a tissue specimen and a first tissue specimen type of the tissue specimen;
extracting, by the one or more processors, a feature vector from each of a plurality of foreground tiles of the digital image;
providing, by the one or more processors, the feature vector from each of the plurality of foreground tiles as input to a trained machine learning system;
outputting, by the trained machine learning system, a prediction associated with one or more tissue specimen types present in the plurality of foreground tiles;
comparing, by the one or more processors, the prediction to the first tissue specimen type;
classifying, by the one or more processors, at least one foreground tile of the plurality of foreground tiles as including an unexpected tissue specimen type based on the comparing;
and
providing, by the one or more processors, any remaining portion of the digital image of the tissue specimen to an image processing system specific to the first tissue specimen type.

5 more elements

A system comprising:

a memory storing instructions and one or more processors configured to execute the instructions to perform a method for processing digital images using a tissue classification platform, the method comprising:
receiving, by the one or more processors, a digital image of a tissue specimen and a first tissue specimen type of the tissue specimen;
extracting, by the one or more processors, a feature vector from each of a plurality of foreground tiles of the digital image;
providing, by the one or more processors, the feature vector from each of the plurality of foreground tiles as input to a trained machine learning system;
outputting, by the trained machine learning system, a prediction associated with one or more tissue specimen types present in the plurality of foreground tiles;
comparing, by the one or more processors, the prediction to the first tissue specimen type;
classifying, by the one or more processors, at least one foreground tile of the plurality of foreground tiles as including an unexpected tissue specimen type based on the comparing;
and
providing, by the one or more processors, any remaining portion of the digital image of the tissue specimen to an image processing system specific to the first tissue specimen type.

6 more elements

A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform a method for processing digital images using a tissue classification platform, the method comprising:

receiving, by the one or more processors, a digital image of a tissue specimen and a first tissue specimen type of the tissue specimen;
extracting, by the one or more processors, a feature vector from each of a plurality of foreground tiles of the digital image;
providing, by the one or more processors, the feature vector from each of the plurality of foreground tiles as input to a trained machine learning system;
outputting, by the trained machine learning system, a prediction associated with one or more tissue specimen types present in the plurality of foreground tiles;
comparing, by the one or more processors, the prediction to the first tissue specimen type;
classifying, by the one or more processors, at least one foreground tile of the plurality of foreground tiles as including an unexpected tissue specimen type based on the comparing;
and
providing, by the one or more processors, any remaining portion of the digital image of the tissue specimen to an image processing system specific to the first tissue specimen type.

5 more elements

Dependencies are inferred from the claim text.

Systems and methods to process electronic images to categorize intra-slide specimen tissue type

Life of this patent

Systems and methods to process electronic images to categorize intra-slide specimen tissue type

Life of this patent

Abstract

Claims20