Image Modality Translation Between MRI and CT Using Diffusion and Score-Matching Algorithms

K N Sharma; Tshetiz Dahal; Bimal Nepal

Research and Reviews : A Journal of Medical Science and Technology

Image Modality Translation Between MRI and CT Using Diffusion and Score-Matching Algorithms

K N Sharma Assistant Professor, Department of Radio-diagnosis and Imaging, Sikkim Manipal Institute of Medical Sciences Tadong, East Sikkim, India
Tshetiz Dahal General Physician, Clinical Researcher, Department of Medicine and Surgery Lugansk State Medical University, Lypnia St. Rivne, Ukraine
Bimal Nepal Research Scholar, Department of Radiology and Imaging Technology College of Allied and Healthcare Sciences, Teerthankar Mahaveer University Moradabad, Uttar Pradesh, India

Abstract

MRI and CT are the two most widely used medical imaging techniques. Often, doctors need images from both modalities to diagnose conditions accurately and plan treatments like radiation therapy. However, using both MRI and CT can be costly, and it often results in misaligned images. A practical alternative is to use computational methods to convert images from one modality to another—particularly converting MRI images into CT images. In this study, we explore a deep learning approach using diffusion models and score-matching techniques to address this challenge. We specifically employ denoising diffusion probabilistic models along with score-matching techniques, implement four distinct sampling approaches, and evaluate their effectiveness in comparison to conventional models such as generative adversarial networks (GANs) and convolutional neural networks (CNNs). Our results show that diffusion and score-matching models generate synthetic CT images with higher quality than CNN and GAN approaches. We also assess the uncertainty in these models using Monte Carlo simulations and further improve the final image quality by averaging the Monte Carlo outputs. Overall, our research suggests that diffusion and score-matching models not only rival CNNs and GANs in generating cross-modality medical images but also offer a more mathematically grounded and reliable framework.

Image Modality Translation Between MRI and CT Using Diffusion and Score-Matching Algorithms

Abstract

Keywords

Read more of it

Publish your article

Abstract

Keywords

Related articles

Transfer Learning in Deep Learning Models for Medical Imaging: Utilizing Pretrained Models to Improve Performance in Medical Image Analysis

Advances in Deep Learning for Medical Image Analysis in the Era of Precision Medicine

Brain Tumor Detection by Aggregating Deep Learning and GAN Models for Faster MRI image Synthesis

Dual-Stream Deep Learning Framework for Brain CT Image Classification and Implications for Polymer Composite Neuro Implant Evaluation

Review of Deep Learning in Medical Imaging

Early Alzheimer’s Disease Prediction Using Vision Transformers and Attention-Guided MRI Analysis

Read more of it

Publish your article