Multi-domain integrative Swin transformer network for sparse-view tomographic reconstruction

Jiayi Pan; Heye Zhang; Weifei Wu; Zhifan Gao; Weiwen Wu

doi:10.1016/j.patter.2022.100498

Multi-domain integrative Swin transformer network for sparse-view tomographic reconstruction

Patterns (N Y). 2022 Apr 22;3(6):100498. doi: 10.1016/j.patter.2022.100498. eCollection 2022 Jun 10.

Authors

Jiayi Pan¹, Heye Zhang¹, Weifei Wu², Zhifan Gao¹, Weiwen Wu¹

Affiliations

¹ School of Biomedical Engineering, Sun Yat-sen University, Shenzhen, Guangdong, China.
² Department of Orthopedics, The People's Hospital of China Three Gorges University, The First People's Hospital of Yichang, Yichang, Hubei, China.

Abstract

Decreasing projection views to a lower X-ray radiation dose usually leads to severe streak artifacts. To improve image quality from sparse-view data, a multi-domain integrative Swin transformer network (MIST-net) was developed and is reported in this article. First, MIST-net incorporated lavish domain features from data, residual data, image, and residual image using flexible network architectures, where a residual data and residual image sub-network was considered as a data consistency module to eliminate interpolation and reconstruction errors. Second, a trainable edge enhancement filter was incorporated to detect and protect image edges. Third, a high-quality reconstruction Swin transformer (i.e., Recformer) was designed to capture image global features. The experimental results on numerical and real cardiac clinical datasets with 48 views demonstrated that our proposed MIST-net provided better image quality with more small features and sharp edges than other competitors.

Keywords: computed tomography; deep learning; inverse problems; multiple domains; transformer.