Invention Grant
- Patent Title: Method for unsupervised stain separation in pathological whole slide images
-
Application No.: US15359470Application Date: 2016-11-22
-
Publication No.: US10229495B2Publication Date: 2019-03-12
- Inventor: Amir Ben-Dor , Elad Arbel
- Applicant: Agilent Technologies, Inc.
- Applicant Address: US CA Santa Clara
- Assignee: Agilent Technologies, Inc.
- Current Assignee: Agilent Technologies, Inc.
- Current Assignee Address: US CA Santa Clara
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G06T7/00

Abstract:
A method of operating a data processing system to automatically process a color digital image of a specimen that has been stained with a first dye and a second different dye is disclosed. The method includes receiving a color image that includes a plurality of pixels, each pixel being characterized by a pixel vector having components determined by the intensity of light in each of a corresponding number of wavelength bands. A plurality of pixel vectors of the image are transformed to a hue space divided into a plurality of bins, each bin being characterized by a number of pixels that have been transformed into that bin. The data processing system automatically finds first and second color vectors characterizing the first and second dyes, respectively based on the number of pixels that were transformed into each of the bins.
Public/Granted literature
- US20180144464A1 Method for Unsupervised Stain Separation in Pathological Whole Slide Images Public/Granted day:2018-05-24
Information query