Conversion Between CT and MRI Images Using Diffusion and Score-Matching Models

TL;DR

This paper explores the use of diffusion and score-matching deep learning models to convert MRI images into synthetic CT images, aiming to improve accuracy and reduce costs in multi-modality medical imaging.

Contribution

It adapts diffusion and score-matching models for MRI-to-CT conversion, compares their performance with CNN and GAN models, and investigates uncertainty quantification methods.

Findings

Diffusion and score-matching models outperform CNN and GAN in synthetic CT quality.

Monte-Carlo averaging improves the stability and accuracy of the generated images.

The proposed models are analytically rigorous and highly competitive for medical image synthesis.

Abstract

MRI and CT are most widely used medical imaging modalities. It is often necessary to acquire multi-modality images for diagnosis and treatment such as radiotherapy planning. However, multi-modality imaging is not only costly but also introduces misalignment between MRI and CT images. To address this challenge, computational conversion is a viable approach between MRI and CT images, especially from MRI to CT images. In this paper, we propose to use an emerging deep learning framework called diffusion and score-matching models in this context. Specifically, we adapt denoising diffusion probabilistic and score-matching models, use four different sampling strategies, and compare their performance metrics with that using a convolutional neural network and a generative adversarial network model. Our results show that the diffusion and score-matching models generate better synthetic CT images than the CNN and GAN models. Furthermore, we investigate the uncertainties associated with the diffusion and score-matching networks using the Monte-Carlo method, and improve the results by averaging their Monte-Carlo outputs. Our study suggests that diffusion and score-matching models are powerful to generate high quality images conditioned on an image obtained using a complementary imaging modality, analytically rigorous with clear explainability, and highly competitive with CNNs and GANs for image synthesis.