US 11,885,732 B2
Morphometric genotyping of cells in liquid biopsy using optical tomography
Michael G. Meyer, Phoenix, AZ (US); Daniel J. Sussman, Auburn, CA (US); Rahul Katdare, Bothell, WA (US); Laimonas Kelbauskas, Chandler, AZ (US); Alan C. Nelson, Gig Harbor, WA (US); and Randall Mastrangelo, Gaithersburg, MD (US)
Assigned to VisionGate, Inc., Woodinville, WA (US)
Filed by VisionGate, Inc., Woodinville, WA (US)
Filed on Oct. 18, 2022, as Appl. No. 17/968,668.
Application 17/968,668 is a continuation of application No. 16/650,304, granted, now 11,545,237, previously published as PCT/US2018/052880, filed on Sep. 26, 2018.
Claims priority of provisional application 62/563,542, filed on Sep. 26, 2017.
Prior Publication US 2023/0050322 A1, Feb. 16, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/00 (2017.01); G01N 15/14 (2006.01); G06T 7/194 (2017.01); G06T 7/11 (2017.01); G16B 40/20 (2019.01); G06V 20/64 (2022.01); G06V 20/69 (2022.01); G06F 18/214 (2023.01); G06V 10/40 (2022.01); G01N 15/10 (2006.01)
CPC G01N 15/1434 (2013.01) [G01N 15/147 (2013.01); G01N 15/1429 (2013.01); G01N 15/1475 (2013.01); G06F 18/214 (2023.01); G06T 7/0012 (2013.01); G06T 7/11 (2017.01); G06T 7/194 (2017.01); G06V 10/40 (2022.01); G06V 20/64 (2022.01); G06V 20/695 (2022.01); G06V 20/698 (2022.01); G16B 40/20 (2019.02); G01N 2015/1006 (2013.01); G01N 2015/1445 (2013.01); G06T 2207/10101 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30024 (2013.01); G06V 2201/03 (2022.01)] 29 Claims
OG exemplary drawing
 
1. A classification training method for training classifiers adapted to identify specific mutations associated with cancer, the method comprising:
identifying 3D image feature data from a plurality of first cells;
generating a first set of 3D cell imaging data from the plurality of first cells with a plurality of known driver mutations and from a plurality of other malignant cells where the plurality of driver mutations is expected to occur, where the first set of cell imaging data includes a plurality of first individual cell images;
generating a second set of 3D cell imaging data from a set of normal cells where the plurality of driver mutations is not expected to occur, where the second set of cell imaging data includes a plurality of second individual cell images;
operating supervised learning based on cell line status as ground truth; and
generating a classifier from the supervised learning.