Self-Supervised Missing Wedge Correction in Soft X-Ray Tomography: Towards Accurate Cellular Morphology and Volume Quantification

Abstract

Soft X-Ray tomography (SXT) is a non-invasive bio-imaging technique that enables 3D imaging of cellular structures in large volume, with a unique resolution range that bridges the gap between fluorescence and transmission electron microscopy. However, a fundamental limitation, the missing wedge artefact caused by incomplete tilt-series acquisition, introduces systematic structural elongation in the reconstructed tomograms. This artifact compromises accurate quantitative biological analysis by overestimating cellular and organelle volumes. To overcome this persistent issue, we introduce a novel, self-supervised missing wedge correction model that learns key sine-wave patterns from existing SXT sinograms of the tilt series stacks. This model can be applied to recover the missing-angle region of the sinogram, reducing distortions and elongations in the reconstructed tomograms. We demonstrate a significant quantitative improvement in artifact removal, achieving faithful recovery of the spherical morphology of lipid droplets. We further applied this method to Plasmodium falciparum hemozoin crystals, a biomarker in antimalarial drug efficacy studies. Our model successfully reduced volume overestimation, achieving up to a 16% decrease in distorted volume. This level of precision is paramount for correctly interpreting the mode of action of antimalarial drugs.