Simultaneous vessel segmentation and unenhanced prediction using self-supervised dual-task learning in 3D CTA (SVSUP)

Wenjian Huang; Weizheng Gao; Chao Hou; Xiaodong Zhang; Xiaoying Wang; Jue Zhang

doi:10.1016/j.cmpb.2022.107001

Simultaneous vessel segmentation and unenhanced prediction using self-supervised dual-task learning in 3D CTA (SVSUP)

Comput Methods Programs Biomed. 2022 Sep:224:107001. doi: 10.1016/j.cmpb.2022.107001. Epub 2022 Jul 3.

Authors

Wenjian Huang¹, Weizheng Gao², Chao Hou³, Xiaodong Zhang³, Xiaoying Wang⁴, Jue Zhang⁵

Affiliations

¹ Academy for Advanced Interdisciplinary Studies, Peking University, No.5 Yiheyuan Rd., Beijing, 100871, China. Electronic address: wjhuang@pku.edu.cn.
² Academy for Advanced Interdisciplinary Studies, Peking University, No.5 Yiheyuan Rd., Beijing, 100871, China.
³ Department of Radiology, Peking University First Hospital, No.8 Xishiku Street, Beijing, 100034, China.
⁴ Academy for Advanced Interdisciplinary Studies, Peking University, No.5 Yiheyuan Rd., Beijing, 100871, China; Department of Radiology, Peking University First Hospital, No.8 Xishiku Street, Beijing, 100034, China. Electronic address: cjr.wangxiaoying@vip.163.com.
⁵ Academy for Advanced Interdisciplinary Studies, Peking University, No.5 Yiheyuan Rd., Beijing, 100871, China; College of Engineering, Peking University, No.5 Yiheyuan Rd., Beijing, 100871, China. Electronic address: zhangjue@pku.edu.cn.

PMID: 35810508
DOI: 10.1016/j.cmpb.2022.107001

Abstract

Background and objective: The vessel segmentation in CT angiography (CTA) provides an important basis for automatic diagnosis and hemodynamics analysis. Virtual unenhanced (VU) CT images obtained by dual-energy CT can assist clinical diagnosis and reduce radiation dose by obviating true unenhanced imaging (UECT). However, accurate segmentation of all vessels in the head-neck CTA (HNCTA) remains a challenge, and VU images are currently not available from conventional single-energy CT imaging.

Methods: In this paper, we proposed a self-supervised dual-task deep learning strategy to fully automatically segment all vessels and predict unenhanced CT images from single-energy HNCTA based on a developed iterative residual-sharing scheme. The underlying idea was to use the correlation between the two tasks to improve task performance while avoiding manual annotation for model training.

Results: The feasibility of the strategy was verified using the data of 24 patients. For vessel segmentation task, the proposed model achieves a significantly higher average Dice coefficient (84.83%, P-values 10^-3 in paired t-test) than the state-of-the-art segmentation model, vanilla VNet (78.94%), and several popular 3D vessel segmentation models, including Hessian-matrix based filter (62.59%), optically-oriented flux (66.33%), spherical flux model (66.91%), and deep vessel net (66.47%). For the unenhanced prediction task, the average ROI-based error compared to the UECT in the artery tissue is 6.1±4.5 HU, similar to previously reported 6.4±5.1 HU for VU reconstruction.

Conclusions: Results show that the proposed dual-task framework can effectively improve the accuracy of vessel segmentation in HNCTA, and it is feasible to predict the unenhanced image from single-energy CTA, providing a potential new approach for radiation dose saving. Moreover, to our best knowledge, this is the first reported annotation-free deep learning-based full-image vessel segmentation for HNCTA.

Keywords: All-vessel segmentation; Dual-task learning; Head-neck CTA; Self-supervised learning; Unenhanced prediction; Virtual unenhanced image.

MeSH terms

Angiography
Computed Tomography Angiography*
Humans
Image Processing, Computer-Assisted / methods
Tomography, X-Ray Computed* / methods