Towards a relation extractor U-shaped network for accurate pulmonary vessel segmentation in CT images

Jiabao Jin; Yu Wu; Gang Ding; Ying Ma; Hui-Qing Zeng; Sunkui Ke; Xiangxing Chen; Miao Wang; Yinran Chen; Xiongbiao Luo

doi:10.1117/12.2653850

7 April 2023 Towards a relation extractor U-shaped network for accurate pulmonary vessel segmentation in CT images

Jiabao Jin, Yu Wu, Gang Ding, Ying Ma, Hui-Qing Zeng, Sunkui Ke, Xiangxing Chen, Miao Wang, Yinran Chen, Xiongbiao Luo

Proceedings Volume 12465, Medical Imaging 2023: Computer-Aided Diagnosis; 124653B (2023) https://doi.org/10.1117/12.2653850
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Conference Poster

Abstract

Pulmonary vessel segmentation from CT images is essential to diagnosis and treatment of lung diseases, particularly in treatment planning and clinical outcome evaluation. The main challenge for pulmonary vessel segmentation is complicated structures of the vascular trees and their similar intensity values with other tissues like the tracheal wall and lung nodules. This paper presents a novel relation extractor U-shaped network combining convolution and self-attention mechanism in an encoder-decoder mode. Particularly, we employ convolution in the shallow layers to extract local information of vessels in a short range and apply self-attention in the deep layers to capture long-range contextual relationship between ancestors and descendants of the vascular tree. We evaluate our proposed method on 50 computer tomography volumes, with the experimental results showing that our method can improve the average coefficient dice and recall to 85.60 and 86.04 respectively.

Citation Download Citation

Jiabao Jin, Yu Wu, Gang Ding, Ying Ma, Hui-Qing Zeng, Sunkui Ke, Xiangxing Chen, Miao Wang, Yinran Chen, and Xiongbiao Luo "Towards a relation extractor U-shaped network for accurate pulmonary vessel segmentation in CT images", Proc. SPIE 12465, Medical Imaging 2023: Computer-Aided Diagnosis, 124653B (7 April 2023); https://doi.org/10.1117/12.2653850

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available