MSDiff: Multi-Scale Diffusion Model for Ultra-Sparse View CT Reconstruction
This work addresses the challenge of reducing radiation exposure in medical imaging by enabling high-quality CT reconstruction from ultra-sparse views, though it appears incremental as it builds on existing diffusion models for a specific domain.
The paper tackled the problem of image quality degradation in computed tomography (CT) reconstruction with very few sampling angles by proposing a multi-scale diffusion model (MSDiff) that integrates comprehensive and sparse sampling techniques, resulting in significant improvements in reconstruction quality under ultra-sparse angles with good generalization across datasets.
Computed Tomography (CT) technology reduces radiation haz-ards to the human body through sparse sampling, but fewer sampling angles pose challenges for image reconstruction. Score-based generative models are widely used in sparse-view CT re-construction, performance diminishes significantly with a sharp reduction in projection angles. Therefore, we propose an ultra-sparse view CT reconstruction method utilizing multi-scale dif-fusion models (MSDiff), designed to concentrate on the global distribution of information and facilitate the reconstruction of sparse views with local image characteristics. Specifically, the proposed model ingeniously integrates information from both comprehensive sampling and selectively sparse sampling tech-niques. Through precise adjustments in diffusion model, it is capable of extracting diverse noise distribution, furthering the understanding of the overall structure of images, and aiding the fully sampled model in recovering image information more effec-tively. By leveraging the inherent correlations within the projec-tion data, we have designed an equidistant mask, enabling the model to focus its attention more effectively. Experimental re-sults demonstrated that the multi-scale model approach signifi-cantly improved the quality of image reconstruction under ultra-sparse angles, with good generalization across various datasets.