Assessing the use of Diffusion models for motion artifact correction in brain MRI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Angella, Paolo, Pastore, Vito Paolo, Santacesaria, Matteo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912217378586624
author Angella, Paolo
Pastore, Vito Paolo
Santacesaria, Matteo
author_facet Angella, Paolo
Pastore, Vito Paolo
Santacesaria, Matteo
contents Magnetic Resonance Imaging generally requires long exposure times, while being sensitive to patient motion, resulting in artifacts in the acquired images, which may hinder their diagnostic relevance. Despite research efforts to decrease the acquisition time, and designing efficient acquisition sequences, motion artifacts are still a persistent problem, pushing toward the need for the development of automatic motion artifact correction techniques. Recently, diffusion models have been proposed as a solution for the task at hand. While diffusion models can produce high-quality reconstructions, they are also susceptible to hallucination, which poses risks in diagnostic applications. In this study, we critically evaluate the use of diffusion models for correcting motion artifacts in 2D brain MRI scans. Using a popular benchmark dataset, we compare a diffusion model-based approach with state-of-the-art methods consisting of Unets trained in a supervised fashion on motion-affected images to reconstruct ground truth motion-free images. Our findings reveal mixed results: diffusion models can produce accurate predictions or generate harmful hallucinations in this context, depending on data heterogeneity and the acquisition planes considered as input.
format Preprint
id arxiv_https___arxiv_org_abs_2502_01418
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Assessing the use of Diffusion models for motion artifact correction in brain MRI
Angella, Paolo
Pastore, Vito Paolo
Santacesaria, Matteo
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Numerical Analysis
Magnetic Resonance Imaging generally requires long exposure times, while being sensitive to patient motion, resulting in artifacts in the acquired images, which may hinder their diagnostic relevance. Despite research efforts to decrease the acquisition time, and designing efficient acquisition sequences, motion artifacts are still a persistent problem, pushing toward the need for the development of automatic motion artifact correction techniques. Recently, diffusion models have been proposed as a solution for the task at hand. While diffusion models can produce high-quality reconstructions, they are also susceptible to hallucination, which poses risks in diagnostic applications. In this study, we critically evaluate the use of diffusion models for correcting motion artifacts in 2D brain MRI scans. Using a popular benchmark dataset, we compare a diffusion model-based approach with state-of-the-art methods consisting of Unets trained in a supervised fashion on motion-affected images to reconstruct ground truth motion-free images. Our findings reveal mixed results: diffusion models can produce accurate predictions or generate harmful hallucinations in this context, depending on data heterogeneity and the acquisition planes considered as input.
title Assessing the use of Diffusion models for motion artifact correction in brain MRI
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Numerical Analysis
url https://arxiv.org/abs/2502.01418