TD-STrans: Tri-domain sparse-view CT reconstruction based on sparse transformer

Yu Li; Xueqin Sun; Sukai Wang; Lina Guo; Yingwei Qin; Jinxiao Pan; Ping Chen

doi:10.1016/j.cmpb.2024.108575

TD-STrans: Tri-domain sparse-view CT reconstruction based on sparse transformer

Comput Methods Programs Biomed. 2024 Dec 25:260:108575. doi: 10.1016/j.cmpb.2024.108575. Online ahead of print.

Authors

Yu Li¹, Xueqin Sun¹, Sukai Wang², Lina Guo¹, Yingwei Qin¹, Jinxiao Pan¹, Ping Chen³

Affiliations

¹ Department of Information and Communication Engineering, North University of China, Taiyuan 030051, China; The State Key Lab for Electronic Testing Technology, North University of China, Taiyuan 030051, China.
² The State Key Lab for Electronic Testing Technology, North University of China, Taiyuan 030051, China; Department of computer science and technology, North University of China, Taiyuan 030051, China.
³ Department of Information and Communication Engineering, North University of China, Taiyuan 030051, China; The State Key Lab for Electronic Testing Technology, North University of China, Taiyuan 030051, China. Electronic address: chenping@nuc.edu.cn.

PMID: 39733746
DOI: 10.1016/j.cmpb.2024.108575

Abstract

Background and objective: Sparse-view computed tomography (CT) speeds up scanning and reduces radiation exposure in medical diagnosis. However, when the projection views are severely under-sampled, deep learning-based reconstruction methods often suffer from over-smoothing of the reconstructed images due to the lack of high-frequency information. To address this issue, we introduce frequency domain information into the popular projection-image domain reconstruction, proposing a Tri-Domain sparse-view CT reconstruction model based on Sparse Transformer (TD-STrans).

Methods: TD-STrans integrates three essential modules: the projection recovery module completes the sparse-view projection, the Fourier domain filling module mitigates artifacts and over-smoothing by filling in missing high-frequency details; the image refinement module further enhances and preserves image details. Additionally, a multi-domain joint loss function is designed to simultaneously enhance the reconstruction quality in the projection domain, image domain, and frequency domain, thereby further improving the preservation of image details.

Results: The results of simulation experiments on the lymph node dataset and real experiments on the walnut dataset consistently demonstrate the effectiveness of TD-STrans in artifact removal, suppression of over-smoothing, and preservation of structural fidelity.

Conclusion: The reconstruction results of TD-STrans indicate that sparse transformer across multiple domains can alleviate over-smoothing and detail loss caused by reduced views, offering a novel solution for ultra-sparse-view CT imaging.

Keywords: Deep learning; Multi-domain joint loss function; Sparse transformer; Sparse-view computed tomography (CT).