Liang Dong1, Wenbing Jiang2, Wei Lu3, Jun Jiang1, Ya Zhao3, Xiangfen Song3, Xiaochang Leng3, Hang Zhao3, Jian'an Wang1, Changling Li1, Jianping Xiang4. 1. The Department of Cardiology, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, China. 2. The Department of Cardiology, Wenzhou People Hospital, Wenzhou, China. 3. ArteryFlow Technology Co., Ltd., Hangzhou, China. 4. ArteryFlow Technology Co., Ltd., Hangzhou, China. jianping.xiang@arteryflow.com.
Abstract
BACKGROUND: Intravascular 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. RESULTS: The 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. CONCLUSION: The 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.
BACKGROUND: Intravascular 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. RESULTS: The 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. CONCLUSION: The 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.