DiffusionBlend: Learning 3D Image Prior Through Position-Aware Diffusion Score Blending for 3D Computed Tomography Reconstruction

Abstract

Diffusion models face significant challenges when employed for real world large-scale medical image reconstruction problems such as 3D Computed Tomography (CT) due to the demanding memory, time, and data requirements. Existing works utilizing diffusion priors on single 2D image slice with hand-crafted cross-slice regularization would sacrifice the z-axis consistency, which results in severe artifacts along the z-axis. In this work, we propose a novel framework that enables learning the 3D image prior through position-aware 3D-patch diffusion score blending for reconstructing large-scale 3D medical images. To the best of our knowledge, we are the first to utilize a 3D-patch diffusion prior for 3D medical image reconstruction. Extensive experiments on sparse view and limited angle CT reconstruction show that our DiffusionBlend method significantly outperforms previous methods and achieves state-of-the-art performance on real-world CT reconstruction problems with high-dimensional 3D image (i.e., $256 \times 256 \times 500$).