SRIP: A Self-Refined Iterative Pipeline to Integrate Whole Body MRI-CT Registration and Pseudo-CT Generation

Motivation: Typical pipelines for MR synthesizing pseudo-CT (pCT) consist of two sequential steps: a MRI-CT registration model and a pCT generation model. pCT generation is particularly challenging in the body due to the difficulty in cross-modality image registration. Goal(s): To improve the performance of the pCT generation pipeline for the body in a fully automated approach. Approach: Integrates the deep learning cross-modality (MR to CT) registration model and deep learning pCT generation model by iteratively refining the registration process and thus provides better aligned MR and CT training data for pCT generation. Results: SRIP significantly improves the quality of generated pCT images. Impact: SRIP introduces a novel pCT generation pipeline that produces high-quality pCT images through a fully automated approach, demonstrating the potential for various applications, such as radiation therapy and PET attenuation correction.