Multiple instance learner for prognostic tissue pattern identification
AssigneeHoffmann-La Roche Inc.
InventorsEldad Klaiman, Jacob Gildenblat
Life of this patent
Estimating the term…
Abstract
The method includes receiving digital images of tissue samples of patients, the images having assigned a label indicating a patient-related attribute value; splitting each received image into a set of image tiles; computing a feature vector for each tile; training a Multiple-Instance-Learning program on all the tiles and respective feature vectors for computing for each of the tiles a numerical value being indicative of the predictive power of the feature vector associated with the tile in respect to the label of the tile's respective image; and outputting a report gallery including tiles sorted in accordance with their respectively computed numerical value and/or including a graphical representation of the numerical value.
Claims20
A method of identifying tissue patterns being indicative of a patient-related attribute value, the method comprising:
- receiving, by an image analysis system, for each patient in a group of patients, at least one digital image of a tissue sample of the patient, the at least one image having assigned one out of at least two different predefined labels, each label indicating a patient-related attribute value of the patient whose tissue is depicted in the labeled image;
- splitting, by the image analysis system, each received image into a set of image tiles, each tile having assigned the label assigned to the image used for creating the tile;
- for each of the tiles, computing by the image analysis system, a feature vector comprising image features extracted selectively from a tissue pattern depicted in the said tile;
- training a Multiple-Instance-Learning program on the tiles and respective feature vectors of the images received for all patients in the group, each set of tiles being treated by the MIL program as a bag of tiles having the same label, the training comprising analyzing the feature vectors for computing for each of the tiles a numerical value being indicative of the predictive power of the feature vector associated with the tile in respect to the label assigned to the image from which the tile was derived;
- and
- outputting, via a GUI of the image analysis system, an image tile report gallery, the report gallery comprising a subset of the tiles, the subset of tiles being sorted in accordance with their respectively computed numerical value.
An image analysis system for identifying tissue patterns being indicative of a patient-related attribute value, the image analysis system comprising:
- at least one processor;
- a volatile or non-volatile storage medium comprising digital tissue images of tissues of a group of patients, wherein for each patient in the group of patients, at least one digital image of a tissue sample of the patient is stored in the storage medium, the at least one image having assigned one out of at least two different predefined labels, each label indicating a patient-related attribute value of the patient whose tissue is depicted in the labeled image;
- an image splitting module being executable by the at least one processor and being configured to split each of the images into a set of image tiles, each tile having assigned the label assigned to the image used for creating the tile;
- a feature extraction module being executable by the at least one processor and being configured to compute, for each of the tiles, a feature vector comprising image features extracted selectively from a tissue pattern depicted in the said tile;
- a Multiple-Instance-Learning program being executable by the at least one processor and being configured to receive, in a training phase of the MIL program, all the tiles and respective feature vectors of all images of all patients in the group, the MIL program being configured to treat each set of tiles as a bag of tiles having the same label during the training phase, the training comprising analyzing the feature vectors for computing for each of the tiles a numerical value being indicative of the predictive power of the feature vector associated with the tile in respect to the label assigned to the image from which the tile was derived;
- and
- a GUI generation module being executable by the at least one processor and being configured to generate and output a GUI comprising an image tile report gallery, the report gallery comprising a subset of the tiles, the subset of tiles being sorted in accordance with their respectively computed numerical value;
- and
- a display adapted for displaying the GUI with the image tile report gallery.
Dependencies are inferred from the claim text.