Title:
FRACTURE DIAGNOSIS MODEL TRAINING METHOD AND DEVICE
Document Type and Number:
WIPO Patent Application WO/2021/071288
Kind Code:
A1
Abstract:
Provided according to the present invention is a fracture diagnosis model training method. The fracture diagnosis model training method is a method for training a learning model for fracture diagnosis by using medical images, the method comprising the steps of: training a typical fracture learning model by using medical fracture images corresponding to various body regions, the medical fracture images being obtained on the basis of imaging of the body regions in which fractures occur; fixing the weight of an artificial neural network provided in the typical fracture learning model to a fixed value, and configuring a region-by-region fracture learning model having a structure in which a value output from the typical fracture learning model is input into a feature learning model; and inputting a region-by-region medical fracture image corresponding to a specified region among the body regions into the typical fracture learning model and setting a fracture diagnosis result corresponding thereto as a target variable of the feature learning model to train the region-by-region fracture learning model.
Inventors:
KIM WON TAE (KR)
KANG SHIN UK (KR)
LEE MYUNG JAE (KR)
KIM DONG MIN (KR)
NAM DONG YEON (KR)
KANG SHIN UK (KR)
LEE MYUNG JAE (KR)
KIM DONG MIN (KR)
NAM DONG YEON (KR)
Application Number:
PCT/KR2020/013741
Publication Date:
April 15, 2021
Filing Date:
October 08, 2020
Export Citation:
Assignee:
JLK INC (KR)
International Classes:
G16H50/50; A61B6/00; G06N20/00; G16H30/40; G16H50/20; G16H50/70
Foreign References:
| KR101854567B1 | 2018-05-04 | |||
| KR20180040287A | 2018-04-20 | |||
| JP2015208385A | 2015-11-24 | |||
| KR102119057B1 | 2020-06-29 |
Other References:
CHENG CHI-TUNG; HO TSUNG-YING; LEE TAO-YI; CHANG CHIH-CHEN; CHOU CHING-CHENG; CHEN CHIH-CHI; CHUNG I-FANG; LIAO CHIEN-HUNG: "Application of a deep learning algorithm for detection and visualization of hip fractures on plain pelvic radiographs", EUROPEAN RADIOLOGY, SPRINGER INTERNATIONAL, BERLIN, DE, vol. 29, no. 10, 1 April 2019 (2019-04-01), DE, pages 5469 - 5477, XP036875428, ISSN: 0938-7994, DOI: 10.1007/s00330-019-06167-y
NISSINEN TOMI: "Convolutional neural networks in osteoporotic fracture risk prediction using spine DXA images", MASTER'S THESIS, UNIVERSITY OF EASTERN FINLAND, 1 March 2019 (2019-03-01), XP055800444
NISSINEN TOMI: "Convolutional neural networks in osteoporotic fracture risk prediction using spine DXA images", MASTER'S THESIS, UNIVERSITY OF EASTERN FINLAND, 1 March 2019 (2019-03-01), XP055800444
Attorney, Agent or Firm:
SUNG, Byung Kee (KR)
Download PDF:
Previous Patent: TRANSFORM-BASED IMAGE CODING METHOD AND DEVICE FOR SAME
Next Patent: COMPOSITION FOR AUGMENTING STEMNESS AND USE THEREOF
Next Patent: COMPOSITION FOR AUGMENTING STEMNESS AND USE THEREOF