Share Email Print

Proceedings Paper

Machine-learning enhanced photoacoustic computed tomography in a limited view configuration
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Photoacoustic imaging is an emerging optical imaging modality which provides optical absorption contrasts and high resolution in the optical diffusive regime. In photoacoustic computed tomography (PACT), often times the detection of the photoacoustic signal only covers a partial solid angle less than 4π, due to experimental or economic constraints. Incomplete spatial coverage always jeopardizes image quality and resolution, and results in significant artifacts and missing of image features. This problem is referred to as “limited view” and has remained unsolved for decades. In this work, we present a new machine-learning-based method that is specifically designed to compensate for the missing information due to limited view. The robustness and effectiveness of our method were demonstrated using numerical, phantom, and in vivo experiments.

Paper Details

Date Published: 19 November 2019
PDF: 8 pages
Proc. SPIE 11186, Advanced Optical Imaging Technologies II, 111860J (19 November 2019); doi: 10.1117/12.2539148
Show Author Affiliations
Handi Deng, Tsinghua Univ. (China)
Xuanhao Wang, Tsinghua Univ. (China)
Chuangjian Cai, Tsinghua Univ. (China)
Jianwen Luo, Tsinghua Univ. (China)
Cheng Ma, Tsinghua Univ. (China)

Published in SPIE Proceedings Vol. 11186:
Advanced Optical Imaging Technologies II
Xiao-Cong Yuan; P. Scott Carney; Kebin Shi; Michael G. Somekh, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?