Detection of coronary lesions in Kawasaki disease by Scaled-YOLOv4 with HarDNet backbone

Kawasaki disease (KD) may increase the risk of myocardial infarction or sudden death. In children, delayed KD diagnosis and treatment can increase coronary lesions (CLs) incidence by 25% and mortality by approximately 1%. This study focuses on the use of deep learning algorithm-based KD detection fr...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in cardiovascular medicine 2023-01, Vol.9, p.1000374-1000374
Main Authors: Kuo, Ho-Chang, Chen, Shih-Hsin, Chen, Yi-Hui, Lin, Yu-Chi, Chang, Chih-Yung, Wu, Yun-Cheng, Wang, Tzai-Der, Chang, Ling-Sai, Tai, I-Hsin, Hsieh, Kai-Sheng
Format: Article
Language:English
Subjects:
Cardiovascular Medicine
deep learning
echocardiography
HarDNet
Kawasaki disease
object detection
Scaled-YOLOv4
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Kawasaki disease (KD) may increase the risk of myocardial infarction or sudden death. In children, delayed KD diagnosis and treatment can increase coronary lesions (CLs) incidence by 25% and mortality by approximately 1%. This study focuses on the use of deep learning algorithm-based KD detection from cardiac ultrasound images. Specifically, object detection for the identification of coronary artery dilatation and brightness of left and right coronary artery is proposed and different AI algorithms were compared. In infants and young children, a dilated coronary artery is only 1-2 mm in diameter than a normal one, and its ultrasound images demonstrate a large amount of noise background-this can be a considerable challenge for image recognition. This study proposes a framework, named Scaled-YOLOv4-HarDNet, integrating the recent Scaled-YOLOv4 but with the CSPDarkNet backbone replaced by the CSPHarDNet framework. The experimental result demonstrated that the mean average precision (mAP) of Scaled-YOLOv4-HarDNet was 72.63%, higher than that of Scaled YOLOv4 and YOLOv5 (70.05% and 69.79% respectively). In addition, it could detect small objects significantly better than Scaled-YOLOv4 and YOLOv5. Scaled-YOLOv4-HarDNet may aid physicians in detecting KD and determining the treatment approach. Because relatively few artificial intelligence solutions about images for KD detection have been reported thus far, this paper is expected to make a substantial academic and clinical contribution.
ISSN:2297-055X
2297-055X
DOI:10.3389/fcvm.2022.1000374