Automatic segmentation of coronary lumen and external elastic membrane in intravascular ultrasound images using 8-layer U-Net

BioMedical Engineering OnLine

Jianping Xiang¹  Ya Zhao¹  Wei Lu¹  Hang Zhao¹  Xiangfen Song¹  Xiaochang Leng¹  Jian’an Wang²  Liang Dong²  Jun Jiang²  Changling Li²  Wenbing Jiang³ 

[1] ArteryFlow Technology Co., Ltd., Hangzhou, China;The Department of Cardiology, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, China;The Department of Cardiology, Wenzhou People Hospital, Wenzhou, China;

关键词: IVUS;    Coronary;    Segmentation;    Lumen;    EEM;    MeshGrid;    U-Net;   

DOI  :  10.1186/s12938-021-00852-0

来源: Springer

【 摘 要 】

BackgroundIntravascular ultrasound (IVUS) is the golden standard in accessing the coronary lesions, stenosis, and atherosclerosis plaques. In this paper, a fully automatic approach by an 8-layer U-Net is developed to segment the coronary artery lumen and the area bounded by external elastic membrane (EEM), i.e., cross-sectional area (EEM-CSA). The database comprises single-vendor and single-frequency IVUS data. Particularly, the proposed data augmentation of MeshGrid combined with flip and rotation operations is implemented, improving the model performance without pre- or post-processing of the raw IVUS images.ResultsThe mean intersection of union (MIoU) of 0.937 and 0.804 for the lumen and EEM-CSA, respectively, were achieved, which exceeded the manual labeling accuracy of the clinician.ConclusionThe accuracy shown by the proposed method is sufficient for subsequent reconstruction of 3D-IVUS images, which is essential for doctors’ diagnosis in the tissue characterization of coronary artery walls and plaque compositions, qualitatively and quantitatively.

【 授权许可】

CC BY