Affordable Access

Access to the full text

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

Authors
  • Dong, Liang1
  • Jiang, Wenbing2
  • Lu, Wei3
  • Jiang, Jun1
  • Zhao, Ya3
  • Song, Xiangfen3
  • Leng, Xiaochang3
  • Zhao, Hang3
  • Wang, Jian’an1
  • Li, Changling1
  • Xiang, Jianping3
  • 1 The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, China , Hangzhou (China)
  • 2 Wenzhou People Hospital, Wenzhou, China , Wenzhou (China)
  • 3 ArteryFlow Technology Co., Ltd., Hangzhou, China , Hangzhou (China)
Type
Published Article
Journal
BioMedical Engineering OnLine
Publisher
Springer (Biomed Central Ltd.)
Publication Date
Feb 06, 2021
Volume
20
Issue
1
Identifiers
DOI: 10.1186/s12938-021-00852-0
Source
Springer Nature
Keywords
License
Green

Abstract

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.

Report this publication

Statistics

Seen <100 times