DocumentCode :
686865
Title :
Ordered subsets acceleration using relaxed momentum for X-ray CT image reconstruction
Author :
Donghwan Kim ; Fessler, Jeffrey A.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Univ. of Michigan, Ann Arbor, MI, USA
fYear :
2013
fDate :
Oct. 27 2013-Nov. 2 2013
Firstpage :
1
Lastpage :
5
Abstract :
Statistical image reconstruction in X-ray CT can provide decent images even with low dose, but requires substantial computation time. Recently, we have proposed combining ordered subsets (OS) methods and Nesterov´s momentum technique for accelerated X-ray CT image reconstruction. We have observed rapid convergence speed of the proposed algorithms in our experiments, but sometimes encountered unstable behavior. Therefore, we introduce a diminishing step size rule, called a relaxed momentum approach, to stabilize the algorithm, while preserving the fast convergence rate. We use a real 3D CT scan to show that the proposed approach can achieve both fast convergence rate and stability.
Keywords :
computerised tomography; image reconstruction; medical image processing; statistical analysis; Nesterov´s momentum technique; accelerated X-ray CT image reconstruction; diminishing step size rule; fast convergence rate; ordered subset acceleration; ordered subset methods; rapid convergence speed; real 3D CT scan; relaxed momentum approach; stability; statistical image reconstruction; substantial computation time; unstable behavior; Computed tomography;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), 2013 IEEE
Conference_Location :
Seoul
Print_ISBN :
978-1-4799-0533-1
Type :
conf
DOI :
10.1109/NSSMIC.2013.6829298
Filename :
6829298
Link To Document :
بازگشت