Geometric Constraints Enable Self-Supervised Sinogram Inpainting in Sparse-View Tomography
This work addresses the challenge of improving CT reconstruction quality for medical imaging applications, particularly in reducing radiation exposure and scan time, but it is incremental as it builds on existing self-supervised and optimization techniques.
The paper tackles the problem of image artifacts and noise in sparse-view tomography by presenting a self-supervised projection inpainting method that optimizes missing projective views via gradient-based optimization, resulting in improvements of 3.1-7.4% in PSNR and 7.7-17.6% in SSIM compared to interpolation baselines on real X-ray microscope mouse tibia bone scans.
The diagnostic quality of computed tomography (CT) scans is usually restricted by the induced patient dose, scan speed, and image quality. Sparse-angle tomographic scans reduce radiation exposure and accelerate data acquisition, but suffer from image artifacts and noise. Existing image processing algorithms can restore CT reconstruction quality but often require large training data sets or can not be used for truncated objects. This work presents a self-supervised projection inpainting method that allows optimizing missing projective views via gradient-based optimization. By reconstructing independent stacks of projection data, a self-supervised loss is calculated in the CT image domain and used to directly optimize projection image intensities to match the missing tomographic views constrained by the projection geometry. Our experiments on real X-ray microscope (XRM) tomographic mouse tibia bone scans show that our method improves reconstructions by 3.1-7.4%/7.7-17.6% in terms of PSNR/SSIM with respect to the interpolation baseline. Our approach is applicable as a flexible self-supervised projection inpainting tool for tomographic applications.