US 11,756,675 B2
Systems and methods for analysis and remote interpretation of optical histologic images
Daniel Orringer, Ann Arbor, MI (US); Balaji Pandian, Farmington Hills, MI (US); Christian Freudiger, San Carlos, CA (US); and Todd Hollon, Ann Arbor, MI (US)
Assigned to THE REGENTS OF THE UNIVERSITY OF MICHIGAN, Ann Arbor, MI (US); and INVENIO IMAGING, INC., Santa Clara, CA (US)
Appl. No. 16/967,052
Filed by THE REGENTS OF THE UNIVERSITY OF MICHIGAN, Ann Arbor, MI (US); and INVENIO IMAGING, INC., Santa Clara, CA (US)
PCT Filed Feb. 6, 2019, PCT No. PCT/US2019/016886
§ 371(c)(1), (2) Date Aug. 3, 2020,
PCT Pub. No. WO2019/157078, PCT Pub. Date Aug. 15, 2019.
Claims priority of provisional application 62/627,033, filed on Feb. 6, 2018.
Prior Publication US 2021/0050094 A1, Feb. 18, 2021
Int. Cl. G06K 9/00 (2022.01); G16H 30/40 (2018.01); G01N 21/65 (2006.01); G06N 3/08 (2023.01); G06T 7/00 (2017.01)
CPC G16H 30/40 (2018.01) [G01N 21/65 (2013.01); G06N 3/08 (2013.01); G06T 7/0012 (2013.01); G01N 2021/655 (2013.01); G06T 2207/10061 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30016 (2013.01); G06T 2207/30096 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A system, comprising:
an imaging device that captures an image of a tissue sample at an optical section of the tissue sample using Stimulated Raman Scattering, where the tissue sample has a thickness larger than the optical section; and
a diagnostic module configured to receive the image for the tissue sample from the imaging device and generate a diagnosis for the tissue sample by classifying the tissue sample into categories using a convolutional neural network including a tumoral tissue category or a nontumoral tissue category, where the tumoral tissue category is a tissue sample with a tumor and the nontumoral tissue category is a tissue sample without a tumor;
wherein the diagnostic module generates a secondary diagnosis for the tissue sample by determining a quantitative measure of cellularity for the tissue sample and outputs the diagnosis when the secondary diagnosis matches the diagnosis for the tissue sample using the convolutional neural network.