Nonsmooth nonconvex LDCT image reconstruction via learned descent algorithm

Qingchao Zhang; Xiaojing Ye; Yunmei Chen

doi:10.1117/12.2597798

9 September 2021 Nonsmooth nonconvex LDCT image reconstruction via learned descent algorithm

Qingchao Zhang, Xiaojing Ye, Yunmei Chen

Proceedings Volume 11840, Developments in X-Ray Tomography XIII; 1184013 (2021) https://doi.org/10.1117/12.2597798
Event: SPIE Optical Engineering + Applications, 2021, San Diego, California, United States

Abstract

Deep neural network architectures based on unrolling optimization algorithms have been widely adopted in deep-learning based image reconstruction applications in recent years. However, these architectures only mimic the iterative schemes of the corresponding algorithms, but lack rigorous convergence guarantee; and the learned network layers are difficult to interpret. These issues have hindered their applications in clinical use. In this paper, we develop an efficient Learned Descent Algorithm with a Line Search strategy (LDA-LS) and apply it to the nonconvex nonsmooth optimization problem of low-dose CT (LDCT) reconstruction. We show that LDA-LS yields a highly interpretable neural network architecture, where the regularization parameterized as multilayer perception is explicitly integrated into the iterative scheme and learned during the training process. We demonstrate that LDA-LS retains convergence guarantee as classical optimization algorithms, while achieving improved efficiency and accuracy in LDCT image reconstruction problems.

Conference Presentation

Citation Download Citation

Qingchao Zhang, Xiaojing Ye, and Yunmei Chen "Nonsmooth nonconvex LDCT image reconstruction via learned descent algorithm", Proc. SPIE 11840, Developments in X-Ray Tomography XIII, 1184013 (9 September 2021); https://doi.org/10.1117/12.2597798

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