METHOD AND SYSTEM FOR TRAINING A SEPARATION OF OVERLAPPING CHROMOSOME RECOGNITION MODEL BASED ON SIMULATION
Patent №
US 11,348,238
Granted
2022-05-31
Filed 2020
Owner
EVER FORTUNE.AI CO., LTD.
Lab
—
AI components
4
ml · vision · planning · hardware
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
16908232
A method for training a chromosome recognition model includes: identifying objects on a karyotype image, obtaining a mask and a minimal bounding box of each of the chromosome objects, and obtaining an organized image that includes a set of organized chromosome objects; generating a simulated metaphase image in which the chromosome objects are randomly reorganized; detecting the plurality of chromosome objects on the simulated metaphase image; obtaining a recalibrated image in which the chromosome objects are separated from one another, so as to train the chromosome recognition model for identifying feature of chromosome objects included in an image.
AI classification
Ownership
EVER FORTUNE.AI CO., LTD.
assignment · 530060538
Assignors
TCHOU, CHRISTIAN PASCAL, TSAI, FUU-JEN, LIAO, KEN YING-KAI, HUANG, TZUNG-CHI
On an employer assignment, the assignors are typically the inventors.