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 |
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
Cite this
Fast Quasi-Newton Algorithms for Penalized Reconstruction in Emission Tomography and Further Improvements via Preconditioning. / Tsai, Yu Jung; Bousse, Alexandre; Ehrhardt, Matthias J.; Stearns, Charles W.; Ahn, Sangtae; Hutton, Brian F.; Arridge, Simon; Thielemans, Kris.
In: IEEE Transactions on Medical Imaging, Vol. 37, No. 4, 01.04.2018, p. 1000-1010.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Fast Quasi-Newton Algorithms for Penalized Reconstruction in Emission Tomography and Further Improvements via Preconditioning
AU - Tsai, Yu Jung
AU - Bousse, Alexandre
AU - Ehrhardt, Matthias J.
AU - Stearns, Charles W.
AU - Ahn, Sangtae
AU - Hutton, Brian F.
AU - Arridge, Simon
AU - Thielemans, Kris
PY - 2018/4/1
Y1 - 2018/4/1
N2 - 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.
AB - 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.
KW - Emission tomography
KW - L-BFGS-B
KW - penalized reconstruction
KW - preconditioning
UR - http://www.scopus.com/inward/record.url?scp=85039799233&partnerID=8YFLogxK
U2 - 10.1109/TMI.2017.2786865
DO - 10.1109/TMI.2017.2786865
M3 - Article
AN - SCOPUS:85039799233
VL - 37
SP - 1000
EP - 1010
JO - IEEE Transactions on Medical Imaging
JF - IEEE Transactions on Medical Imaging
SN - 0278-0062
IS - 4
ER -