Title:
CORONARY ANGIOGRAM QUANTITATIVE ANALYSIS METHOD AND APPARATUS BASED ON ANGIOGRAM VIDEO
Document Type and Number:
WIPO Patent Application WO/2023/130663
Kind Code:
A1
Abstract:
The embodiments of the present invention relate to a coronary angiogram quantitative analysis method and apparatus based on an angiogram video. The method comprises: acquiring an angiogram video; performing video frame image extraction to generate a first image sequence; on the basis of an image object detection and semantic segmentation model, performing object detection and semantic segmentation processing of a stenosis-section blood vessel on each first image in the first image sequence so as to obtain from each first image one or more object detection boxes used for marking the stenosis-section blood vessel, and a stenosis-section blood vessel mask image in each object detection box; performing image preference processing on the first image sequence to obtain a specified number of preferred images; and in respect of each preferred image, performing coronary angiogram quantitative analysis on the stenosis-section blood vessel mask image in each object detection box so as to generate a corresponding blood vessel stenosis rate. The present invention may eliminate excessive dependence on human experience in a traditional method, and improve image extraction accuracy and computational accuracy of the stenosis rate.
Inventors:
ZHANG BIYING (CN)
WU ZEJIAN (CN)
CAO JUN (CN)
WU ZEJIAN (CN)
CAO JUN (CN)
Application Number:
PCT/CN2022/097245
Publication Date:
July 13, 2023
Filing Date:
June 07, 2022
Export Citation:
Assignee:
LEPU MED TECH BEIJING CO LTD (CN)
International Classes:
G06V10/26; G06T7/00
Foreign References:
| CN114418977A | 2022-04-29 | |||
| CN109222980A | 2019-01-18 | |||
| CN111657883A | 2020-09-15 | |||
| US20190159683A1 | 2019-05-30 |
Other References:
KAI SHAO, ZHANG YUNFENG; BAO FANGXUN, ZHENG YONG, QIN CHAO: "A Coronary Artery Segmentation Method Based on Mask RCNN Integrated with Geometric Features", JOURNAL OF TAIYUAN UNIVERSITY OF TECHNOLOGY, vol. 52, no. 1, 22 December 2020 (2020-12-22), pages 83 - 90, XP093077190
Attorney, Agent or Firm:
HECHWISE PATENT & TRADEMARK FIRM (CN)
Download PDF: