Author/Authors :
Jiang, Xiaolu Jimei University - Xiamen, China , Zeng, Yanqiu Jimei University - Xiamen, China , Xiao, Shixiao Jimei University - Xiamen, China , He, Shaojie School of Informatics - Xiamen University - Xiamen, China , Ye, Caizhi School of Management - Xiamen University - Xiamen, China , Qi, Yu , Zhao, Jiangsheng School of Informatics - Xiamen University - Xiamen, China , Wei, Dezhi Jimei University - Xiamen, China , Hu, Muhua Jimei University - Xiamen, China , Chen, Fei Department of Cardiology - Tongji Hospital of Tongji University - Shanghai, China
Abstract :
An artificial stent implantation is one of the most effective ways to treat coronary artery diseases. It is vital in vascular medical
imaging, such as intravascular optical coherence tomography (IVOCT), to be able to track the position of stents in blood vessels
effectively. We trained two models, the “You Only Look Once” version 3 (YOLOv3) and the Region-based Fully Convolutional
Network (R-FCN), to detect metal support struts in IVOCT, respectively. After rotating the original images in the training set
for data augmentation, and modifying the scale of the conventional anchor box in both two algorithms to fit the size of the
target strut, YOLOv3 and R-FCN achieved precision, recall, and AP all above 95% in 0.4 IoU threshold. and R-FCN performs
better than YOLOv3 in all relevant indicators.
Keywords :
R-FCN , YOLOv3 , Automatic , IVOCT
