Your browser doesn't support javascript.
loading
Automatic Detection of Coronary Metallic Stent Struts Based on YOLOv3 and R-FCN.
Jiang, Xiaolu; Zeng, Yanqiu; Xiao, Shixiao; He, Shaojie; Ye, Caizhi; Qi, Yu; Zhao, Jiangsheng; Wei, Dezhi; Hu, Muhua; Chen, Fei.
Afiliación
  • Jiang X; Chengyi University College, Jimei University, Xiamen 361021, China.
  • Zeng Y; Chengyi University College, Jimei University, Xiamen 361021, China.
  • Xiao S; Chengyi University College, Jimei University, Xiamen 361021, China.
  • He S; School of Informatics, Xiamen University, Xiamen 361021, China.
  • Ye C; School of Management, Xiamen University, Xiamen 361021, China.
  • Qi Y; School of Mathematical Sciences, Xiamen University, Xiamen 361021, China.
  • Zhao J; School of Informatics, Xiamen University, Xiamen 361021, China.
  • Wei D; Chengyi University College, Jimei University, Xiamen 361021, China.
  • Hu M; Chengyi University College, Jimei University, Xiamen 361021, China.
  • Chen F; Department of Cardiology, Tongji Hospital of Tongji University, Shanghai 200065, China.
Comput Math Methods Med ; 2020: 1793517, 2020.
Article en En | MEDLINE | ID: mdl-32952597
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.
Asunto(s)

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Enfermedad de la Arteria Coronaria / Stents / Tomografía de Coherencia Óptica Tipo de estudio: Diagnostic_studies Límite: Humans Idioma: En Revista: Comput Math Methods Med Asunto de la revista: INFORMATICA MEDICA Año: 2020 Tipo del documento: Article País de afiliación: China Pais de publicación: Estados Unidos

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Enfermedad de la Arteria Coronaria / Stents / Tomografía de Coherencia Óptica Tipo de estudio: Diagnostic_studies Límite: Humans Idioma: En Revista: Comput Math Methods Med Asunto de la revista: INFORMATICA MEDICA Año: 2020 Tipo del documento: Article País de afiliación: China Pais de publicación: Estados Unidos