US 11,935,644 B2
Deep learning automated dermatopathology
Brian H. Jackson, Poquoson, VA (US); and Coleman C. Stavish, Havertown, PA (US)
Assigned to PROSCIA INC., Philadelphia, PA (US)
Filed by PROSCIA INC., Philadelphia, PA (US)
Filed on Jul. 29, 2022, as Appl. No. 17/877,611.
Application 17/877,611 is a continuation of application No. 16/656,033, filed on Oct. 17, 2019, granted, now 11,403,862.
Application 16/656,033 is a continuation of application No. 15/923,252, filed on Mar. 16, 2018, granted, now 11,641,124, issued on Oct. 29, 2019.
Prior Publication US 2022/0375242 A1, Nov. 24, 2022
Int. Cl. G16H 30/40 (2018.01); G06F 18/2413 (2023.01); G06N 3/08 (2023.01); G06T 7/00 (2017.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01); G06V 20/69 (2022.01)
CPC G16H 30/40 (2018.01) [G06F 18/2413 (2023.01); G06N 3/08 (2013.01); G06T 7/0014 (2013.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 20/695 (2022.01); G06V 20/698 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/30024 (2013.01); G06T 2207/30088 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method of classifying a human cutaneous tissue sample, the method comprising:
obtaining an image of the human cutaneous tissue sample;
applying a trained machine learning system to the image of the human cutaneous tissue sample, wherein the trained machine learning system is trained with a plurality of training images, the plurality of training images comprising a plurality of diagnostic goal dermatological images and a plurality of distractor dermatological images,
wherein the plurality of diagnostic goal dermatological images comprise at least a plurality of images of a first dermatological diagnostic goal and a plurality of images of a second dermatological diagnostic goal,
wherein the plurality of distractor dermatological images comprise a plurality of distractor images corresponding to the first dermatological diagnostic goal and a plurality of distractor images corresponding to the second dermatological diagnostic goal,
and wherein the trained machine learning system is trained using the plurality of training images by:
training a first deep learning neural network using the plurality of images of the first dermatological diagnostic goal and the plurality of distractor images corresponding to the first dermatological diagnostic goal, and
training a second deep learning neural network using the plurality of images of the second dermatological diagnostic goal and the plurality of distractor images corresponding to the second dermatological diagnostic goal;
obtaining a dermatological diagnosis from the trained machine learning system; and
outputting the dermatological diagnosis.