Limited-angle tomography reconstruction with a U-Conv-Swin-Net

X-ray computed tomography (CT) is widely used as a non-destructive inspection technology. However, due to various limitations such as sample dimensions and blocking of in-situ instruments, projections can be acquired only in a limited-angle range during CT acquisition. When such projections are reconstructed with conventional algorithms, the details and contours are deteriorated by artefacts due to lack of information at certain view angles. To address this problem, we propose a reconstruction method based on U-Conv-Swin-Net (UCSN) in this paper. Validated through synthetic and experimental data, the proposed method can effectively remove the degrading artefacts and fully restore the sample details and edges. In addition, the UCSN method exhibits superior reconstruction effect for different scanning ranges compared with conventional reconstruction methods.