US 12,243,231 B2
Computer supported review of tumors in histology images and post operative tumor margin assessment
Walter Georgescu, Vista, CA (US)
Assigned to Leica Biosystems Imaging, Inc., Vista, CA (US)
Filed by Leica Biosystems Imaging, Inc., Vista, CA (US)
Filed on Dec. 18, 2023, as Appl. No. 18/543,461.
Application 18/543,461 is a continuation of application No. 17/415,396, granted, now 11,893,732, previously published as PCT/US2020/035286, filed on May 29, 2020.
Claims priority of provisional application 62/854,055, filed on May 29, 2019.
Claims priority of provisional application 62/854,014, filed on May 29, 2019.
Prior Publication US 2024/0119595 A1, Apr. 11, 2024
Int. Cl. G06T 7/00 (2017.01); G06F 18/214 (2023.01); G06F 18/24 (2023.01); G06N 3/08 (2023.01); G06V 10/94 (2022.01); G06V 20/69 (2022.01); G16H 30/40 (2018.01); G06F 3/04842 (2022.01)
CPC G06T 7/0012 (2013.01) [G06F 18/2148 (2023.01); G06F 18/24 (2023.01); G06N 3/08 (2013.01); G06V 10/95 (2022.01); G06V 20/693 (2022.01); G06V 20/695 (2022.01); G06V 20/698 (2022.01); G16H 30/40 (2018.01); G06F 3/04842 (2013.01); G06T 2200/24 (2013.01); G06T 2207/10056 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30024 (2013.01); G06T 2207/30096 (2013.01); G06V 2201/03 (2022.01)] 12 Claims
OG exemplary drawing
 
1. A computer apparatus for identifying tumors in a histological image, comprising:
a memory configured to store computer-executable instructions; and
a hardware processor in communication with the memory, wherein the computer-executable instructions, when executed by the processor, configure the processor to perform a method comprising:
generating, from an output image, a segmentation mask having areas occupied by individual tumors in the output image marked in the segmentation mask;
computing statistics for each tumor marked in the segmentation mask; and
applying a filter to the statistics of the tumors to edit the segmentation mask, wherein application of the filter selects and deselects tumors according to the filter to edit the segmentation mask to remove insignificant tumors; wherein:
the output image comprises an array of pixels, each pixel in the output image being assigned to one of a plurality of tissue classes;
the output image is generated by a convolutional neural network based on the histological image by performing acts comprising:
extracting image patches from the histological image, the image patches being area portions of the histological image having a size defined by numbers of pixels in width and height;
providing the convolutional neural network with a set of weights and a plurality of channels, each channel corresponding to one of the plurality of tissue classes;
inputting each image patch as an input image patch into the convolutional neural network;
performing multi-stage convolution to generate convolution layers of ever decreasing dimensions up to and including a final convolution layer of minimum dimensions, followed by multi-stage transpose convolution to reverse the convolutions by generating deconvolution layers of ever increasing dimensions until a layer is recovered matched in size to the input image patch, each pixel in the recovered layer containing a probability of belonging to each of the tissue classes; and
assigning the tissue class to each pixel of the recovered layer based on said probabilities to arrive at an output image patch.