Plug-and-Play blind super-resolution of real MRI images for improved multiple sclerosis diagnosis

TL;DR

This paper introduces a blind super-resolution method to enhance low-resolution 1.5 T MRI images, improving the visualization of features relevant for multiple sclerosis diagnosis without requiring high-field MRI data.

Contribution

It presents a novel plug-and-play framework for blind super-resolution of real MRI images, jointly estimating high-resolution images and blur kernels with convergence guarantees.

Findings

Enhanced structural detail in 1.5 T MRI images

Improved visibility of clinically relevant features

Visual similarity to 3 T MRI images

Abstract

Magnetic resonance imaging (MRI) is central to the diagnosis of multiple sclerosis, where the identification of biomarkers such as the central vein sign benefits from high-resolution images. However, most clinical brain MRI scans are performed using 1.5 T scanners, which provide lower sensitivity compared to higher-field systems. We propose a blind super-resolution framework to enhance real 1.5 T MRI images acquired in clinical settings, where only post-processed data are available and the degradation model is not fully known. The problem is formulated as a non-convex blind inverse problem involving the joint estimation of the high-resolution image and the blur kernel. Image regularization is handled through a Plug-and-Play strategy based on a pretrained denoiser, while suitable constraints are imposed on the blur kernel. To solve the resulting model, we design a heterogeneous alternating block-coordinate method in which the two variables are updated using different types of algorithms. Convergence properties are rigorously established. Experiments on FLAIR and SWI sequences acquired at 1.5 T show improved structural definition and enhanced visibility of clinically relevant features, with visual comparison against 3 T images.