New HiGDiff framework enhances CT image reconstruction from degraded projections

Researchers have developed HiGDiff, a novel feed-forward hierarchical Gaussian diffusion framework designed to reconstruct three-dimensional computed tomography (CT) images from severely degraded projections. This method decomposes the reconstruction process both spatially and by detail level, first recovering global anatomy and then refining local tissue transitions. Experiments on benchmark datasets, including the Low Dose CT Image and Projection Data (LDCT-PD) collection, show HiGDiff achieving state-of-the-art performance across various degradation scenarios, outperforming existing methods. AI

IMPACT This research could lead to more accurate medical imaging from lower-quality scans, potentially improving diagnostic capabilities.

RANK_REASON The cluster contains an academic paper detailing a new method for image reconstruction. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• computed tomography
• Gaussian diffusion sinogram inpainting for X-ray CT metal artifact reduction
• HiGDiff
• LDCT-PD

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →