Abstract
This paper reports on the feasibility of using a quasi-Newton optimization algorithm, limited-memory Broyden-Fletcher-Goldfarb-Shanno with boundary constraints (L-BFGS-B), for penalized image reconstruction problems in emission tomography (ET). For further acceleration, an additional preconditioning technique based on a diagonal approximation of the Hessian was introduced. The convergence rate of L-BFGS-B and the proposed preconditioned algorithm (L-BFGS-B-PC) was evaluated with simulated data with various factors, such as the noise level, penalty type, penalty strength and background level. Data of three 18F-FDG patient acquisitions were also reconstructed. Results showed that the proposed L-BFGS-B-PC outperforms L-BFGS-B in convergence rate for all simulated conditions and the patient data. Based on these results, L-BFGS-B-PC shows promise for clinical application.
Original language | English |
---|---|
Pages (from-to) | 1000-1010 |
Number of pages | 11 |
Journal | IEEE Transactions on Medical Imaging |
Volume | 37 |
Issue number | 4 |
Early online date | 25 Dec 2017 |
DOIs | |
Publication status | Published - 1 Apr 2018 |
Funding
Manuscript received September 25, 2017; revised December 11, 2017; accepted December 18, 2017. Date of publication December 25, 2017; date of current version April 2, 2018. This work was supported in part by GE Healthcare and in part by the NIHR-funded UCLH Biomedical Research Centre. The work of M. J. Ehrhardt was supported in part by the Leverhulme Trust Project—Breaking the non-convexity barrier, EPSRC, under Grant EP/M00483X/1 and Grant EP/N014588/1, in part by the Cantab Capital Institute for the Mathematics of Information, and in part by CHiPS (Horizon 2020 RISE Project Grant). (Corresponding author: Yu-Jung Tsai.) Y.-J. Tsai, A. Bousse, and K. Thielemans are with the Institute of Nuclear Medicine, University College London, London NW1 2BU, U.K. (e-mail: [email protected]).
Keywords
- Emission tomography
- L-BFGS-B
- penalized reconstruction
- preconditioning
ASJC Scopus subject areas
- Software
- Radiological and Ultrasound Technology
- Computer Science Applications
- Electrical and Electronic Engineering