ADSeg: A flap-attention-based deep learning approach for aortic dissection segmentation

Dongqiao Xiang; Jiyang Qi; Yiqing Wen; Hui Zhao; Xiaolin Zhang; Jia Qin; Xiaomeng Ma; Yaguang Ren; Hongyao Hu; Wenyu Liu; Fan Yang; Huangxuan Zhao; Xinggang Wang; Chuansheng Zheng

doi:10.1016/j.patter.2023.100727

ADSeg: A flap-attention-based deep learning approach for aortic dissection segmentation

Patterns (N Y). 2023 Apr 14;4(5):100727. doi: 10.1016/j.patter.2023.100727. eCollection 2023 May 12.

Authors

Dongqiao Xiang^{1

2}, Jiyang Qi³, Yiqing Wen³, Hui Zhao⁴, Xiaolin Zhang⁵, Jia Qin⁵, Xiaomeng Ma⁶, Yaguang Ren⁷, Hongyao Hu⁴, Wenyu Liu³, Fan Yang^{1

2}, Huangxuan Zhao^{1

2}, Xinggang Wang³, Chuansheng Zheng^{1

2}

Affiliations

¹ Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.
² Hubei Province Key Laboratory of Molecular Imaging, Wuhan 430022, China.
³ School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China.
⁴ Department of Interventional Radiology, Renmin Hospital of Wuhan University, Wuhan 430060, China.
⁵ Department of Radiology, Yichang Central People's Hospital, Yichang 443003, China.
⁶ Department of Radiology, Jingzhou First People's Hospital of Hubei province, Jingzhou 434000, China.
⁷ Research Laboratory for Biomedical Optics and Molecular Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China.

Abstract

Accurate and rapid segmentation of the lumen in an aortic dissection (AD) is an important prerequisite for risk evaluation and medical planning for patients with this serious condition. Although some recent studies have pioneered technical advances for the challenging AD segmentation task, they generally neglect the intimal flap structure that separates the true and false lumens. Identification and segmentation of the intimal flap may simplify AD segmentation, and the incorporation of long-distance z axis information interaction along the curved aorta may improve segmentation accuracy. This study proposes a flap attention module that focuses on key flap voxels and performs operations with long-distance attention. In addition, a pragmatic cascaded network structure with feature reuse and a two-step training strategy are presented to fully exploit network representation power. The proposed ADSeg method was evaluated on a multicenter dataset of 108 cases, with or without thrombus; ADSeg outperformed previous state-of-the-art methods by a significant margin and was robust against center variation.

Keywords: CT angiography; aortic dissection; deep learning; segmentation.