Two-stage deep learning network-based few-view image reconstruction for parallel-beam projection tomography

Huiyuan Wang; Nan Wang; Hui Xie; Lin Wang; Wangting Zhou; Defu Yang; Xu Cao; Shouping Zhu; Jimin Liang; Xueli Chen

doi:10.21037/qims-21-778

Two-stage deep learning network-based few-view image reconstruction for parallel-beam projection tomography

Quant Imaging Med Surg. 2022 Apr;12(4):2535-2551. doi: 10.21037/qims-21-778.

Authors

Huiyuan Wang^#^{1

2}, Nan Wang^#^{1

2}, Hui Xie^{1

2}, Lin Wang³, Wangting Zhou^{1

2}, Defu Yang⁴, Xu Cao^{1

2}, Shouping Zhu^{1

2}, Jimin Liang⁵, Xueli Chen^{1

2}

Affiliations

¹ Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education, School of Life Science and Technology, Xidian University, Xi'an, China.
² Xi'an Key Laboratory of Intelligent Sensing and Regulation of Trans-scale Life Information, Xi'an, China.
³ School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China.
⁴ Research Center for Healthcare Data Science, Zhejiang Lab, Hangzhou, China.
⁵ School of Electronic Engineering, Xidian University, Xi'an, China.

^# Contributed equally.

Abstract

Background: Projection tomography (PT) is a very important and valuable method for fast volumetric imaging with isotropic spatial resolution. Sparse-view or limited-angle reconstruction-based PT can greatly reduce data acquisition time, lower radiation doses, and simplify sample fixation modes. However, few techniques can currently achieve image reconstruction based on few-view projection data, which is especially important for in vivo PT in living organisms.

Methods: A 2-stage deep learning network (TSDLN)-based framework was proposed for parallel-beam PT reconstructions using few-view projections. The framework is composed of a reconstruction network (R-net) and a correction network (C-net). The R-net is a generative adversarial network (GAN) used to complete image information with direct back-projection (BP) of a sparse signal, bringing the reconstructed image close to reconstruction results obtained from fully projected data. The C-net is a U-net array that denoises the compensation result to obtain a high-quality reconstructed image.

Results: The accuracy and feasibility of the proposed TSDLN-based framework in few-view projection-based reconstruction were first evaluated with simulations, using images from the DeepLesion public dataset. The framework exhibited better reconstruction performance than traditional analytic reconstruction algorithms and iterative algorithms, especially in cases using sparse-view projection images. For example, with as few as two projections, the TSDLN-based framework reconstructed high-quality images very close to the original image, with structural similarities greater than 0.8. By using previously acquired optical PT (OPT) data in the TSDLN-based framework trained on computed tomography (CT) data, we further exemplified the migration capabilities of the TSDLN-based framework. The results showed that when the number of projections was reduced to 5, the contours and distribution information of the samples in question could still be seen in the reconstructed images.

Conclusions: The simulations and experimental results showed that the TSDLN-based framework has strong reconstruction abilities using few-view projection images, and has great potential in the application of in vivo PT.

Keywords: Projection tomography (PT); deep learning; few-view reconstruction; sparse reconstruction; two-stage network; volumetric imaging.