Invention Grant
- Patent Title: Machine learning classification and training for digital microscopy images
-
Application No.: US15585045Application Date: 2017-05-02
-
Publication No.: US10255693B2Publication Date: 2019-04-09
- Inventor: Richard Boyd Smith
- Applicant: TechCyte, Inc.
- Applicant Address: US UT Orem
- Assignee: Techcyte, Inc.
- Current Assignee: Techcyte, Inc.
- Current Assignee Address: US UT Orem
- Agency: TechLaw Ventures, PLLC
- Agent Terrence J. Edwards
- Main IPC: G06T7/00
- IPC: G06T7/00 ; G06K9/62

Abstract:
Systems, methods, and devices for training models or algorithms for classifying or detecting particles or materials in microscopy images are disclosed. A method includes receiving a plurality of microscopy images of a specimen and a classification for the specimen. The plurality of microscopy images includes a first image captured at a first magnification and a second image captured at the first magnification with a different focus than the first image. The method includes training a machine learning model or algorithm using the plurality of images, wherein the first image and the second image are provided with one or more labels indicating the classification.
Public/Granted literature
- US20180322660A1 MACHINE LEARNING CLASSIFICATION AND TRAINING FOR DIGITAL MICROSCOPY IMAGES Public/Granted day:2018-11-08
Information query