US 11,682,186 B2
Detection of annotated regions of interest in images
Thomas Fuchs, New York, NY (US); Peter J. Schüffler, New York, NY (US); Dig Vijay Kumar Yarlagadda, New York, NY (US); and Chad Vanderbilt, New York, NY (US)
Assigned to Memorial Sloan Kettering Cancer Center, New York, NY (US)
Filed by MEMORIAL SLOAN KETTERING CANCER CENTER, New York, NY (US)
Filed on Dec. 16, 2021, as Appl. No. 17/553,291.
Claims priority of provisional application 63/126,298, filed on Dec. 16, 2020.
Prior Publication US 2022/0189133 A1, Jun. 16, 2022
Int. Cl. G06V 10/25 (2022.01); G06V 30/18 (2022.01); G06V 30/19 (2022.01); G06T 5/00 (2006.01); G06T 7/194 (2017.01); G06T 3/40 (2006.01); G06V 30/14 (2022.01); G06T 7/00 (2017.01)
CPC G06V 10/25 (2022.01) [G06T 3/40 (2013.01); G06T 5/002 (2013.01); G06T 7/0012 (2013.01); G06T 7/194 (2017.01); G06V 30/1448 (2022.01); G06V 30/18105 (2022.01); G06V 30/19173 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/30024 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of identifying regions of interest (ROIs) in images, comprising:
identifying, by a computing system, an image of a tissue sample on a slide, the slide having an indicator manually labeled using a writing instrument on the tissue sample, the indicator at least partially surrounding a feature of the tissue sample, the image including an annotation corresponding to the indicator, the annotation identifying an ROI corresponding to the feature of the tissue sample, the image having a plurality of pixels in a first color space;
converting, by the computing system, the plurality of pixels from the first color space to a second color space to increase color differences between first color values associated with the annotation from second color values associated with the ROI;
selecting, by the computing system, from the plurality of pixels, a first subset of pixels corresponding to the annotation based at least on a color value of at least one of the first subset of pixels in the second color space;
identifying, by the computing system, a second subset of pixels included in the ROI from the image using the first subset of pixels; and
storing, by the computing system, in one or more data structures, an association between the second subset of pixels and the ROI identified by the annotation in the image.