Share Email Print
cover

Proceedings Paper

GPU-accelerated compressed-sensing (CS) image reconstruction in chest digital tomosynthesis (CDT) using CUDA programming
Author(s): Sunghoon Choi; Haenghwa Lee; Donghoon Lee; Seungyeon Choi; Jungwook Shin; Woojin Jang; Chang-Woo Seo; Hee-Joung Kim
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A compressed-sensing (CS) technique has been rapidly applied in medical imaging field for retrieving volumetric data from highly under-sampled projections. Among many variant forms, CS technique based on a total-variation (TV) regularization strategy shows fairly reasonable results in cone-beam geometry. In this study, we implemented the TV-based CS image reconstruction strategy in our prototype chest digital tomosynthesis (CDT) R/F system. Due to the iterative nature of time consuming processes in solving a cost function, we took advantage of parallel computing using graphics processing units (GPU) by the compute unified device architecture (CUDA) programming to accelerate our algorithm. In order to compare the algorithmic performance of our proposed CS algorithm, conventional filtered back-projection (FBP) and simultaneous algebraic reconstruction technique (SART) reconstruction schemes were also studied. The results indicated that the CS produced better contrast-to-noise ratios (CNRs) in the physical phantom images (Teflon region-of-interest) by factors of 3.91 and 1.93 than FBP and SART images, respectively. The resulted human chest phantom images including lung nodules with different diameters also showed better visual appearance in the CS images. Our proposed GPU-accelerated CS reconstruction scheme could produce volumetric data up to 80 times than CPU programming. Total elapsed time for producing 50 coronal planes with 1024×1024 image matrix using 41 projection views were 216.74 seconds for proposed CS algorithms on our GPU programming, which could match the clinically feasible time (~ 3 min). Consequently, our results demonstrated that the proposed CS method showed a potential of additional dose reduction in digital tomosynthesis with reasonable image quality in a fast time.

Paper Details

Date Published: 9 March 2017
PDF: 7 pages
Proc. SPIE 10132, Medical Imaging 2017: Physics of Medical Imaging, 1013202 (9 March 2017); doi: 10.1117/12.2254206
Show Author Affiliations
Sunghoon Choi, Yonsei Univ. (Korea, Republic of)
Haenghwa Lee, Yonsei Univ. (Korea, Republic of)
Donghoon Lee, Yonsei Univ. (Korea, Republic of)
Seungyeon Choi, Yonsei Univ. (Korea, Republic of)
Jungwook Shin, LISTEM Corp. (Korea, Republic of)
Woojin Jang, LISTEM Corp. (Korea, Republic of)
Chang-Woo Seo, Yonsei Univ. (Korea, Republic of)
Hee-Joung Kim, Yonsei Univ. (Korea, Republic of)


Published in SPIE Proceedings Vol. 10132:
Medical Imaging 2017: Physics of Medical Imaging
Thomas G. Flohr; Joseph Y. Lo; Taly Gilat Schmidt, Editor(s)

© SPIE. Terms of Use
Back to Top