US 12,340,506 B2
System and method for attention-based classification of high-resolution microscopy images
Saeed Hassanpour, Hanover, NH (US); and Naofumi Tomita, Hanover, NH (US)
Assigned to The Trustees of Dartmouth College, Hanover, NH (US)
Appl. No. 17/608,016
Filed by The Trustees of Dartmouth College, Hanover, NH (US)
PCT Filed Apr. 8, 2020, PCT No. PCT/US2020/027178
§ 371(c)(1), (2) Date Nov. 1, 2021,
PCT Pub. No. WO2020/222985, PCT Pub. Date Nov. 5, 2020.
Claims priority of provisional application 62/840,538, filed on Apr. 30, 2019.
Prior Publication US 2022/0309653 A1, Sep. 29, 2022
Int. Cl. G06T 7/11 (2017.01); G06T 7/00 (2017.01); G06V 10/82 (2022.01)
CPC G06T 7/0012 (2013.01) [G06T 7/11 (2017.01); G06V 10/82 (2022.01); G06T 2207/10056 (2013.01); G06T 2207/30004 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A system for analyzing and classifying images from whole slides of tissue comprising:
a source of image data including images of the tissue on the whole slides, each of the images divided into a plurality of adjacent non-overlapping tiles;
a computer processor executing a CNN-based feature extraction process by which the processor identifies regions of interest in each non-overlapping tile of the images thereby producing a grid-based feature map of the identified regions of interest; and
an attention network that, based upon training from an expert, when executed by the processor, configures the processor to identify trained characteristics in the regions of interest of the grid-based feature map and provide identification data for a least a portion of the identified regions of interest to a user,
wherein the attention network-configured processor performs attention-based weighting of features relative to the trained characteristics, and
wherein the attention network includes 3D convolutional filters of size N×d×d, where N is a depth of a filter kernel and d denotes a height and width of the kernel.