Inter-slice Super-resolution of Magnetic Resonance Images by Pre-training and Self-supervised Fine-tuning

TL;DR

This paper introduces a self-supervised inter-slice super-resolution method for MRI that leverages pre-training on video data and fine-tuning on medical datasets, improving image quality without requiring paired high- and low-resolution images.

Contribution

It presents a novel self-supervised framework combining video pre-training and medical data fine-tuning for MRI super-resolution, addressing data scarcity issues.

Findings

Outperforms existing self-supervised super-resolution methods.

Effective in enhancing MRI image resolution and quality.

Potential benefits for downstream medical imaging tasks.

Abstract

In clinical practice, 2D magnetic resonance (MR) sequences are widely adopted. While individual 2D slices can be stacked to form a 3D volume, the relatively large slice spacing can pose challenges for both image visualization and subsequent analysis tasks, which often require isotropic voxel spacing. To reduce slice spacing, deep-learning-based super-resolution techniques are widely investigated. However, most current solutions require a substantial number of paired high-resolution and low-resolution images for supervised training, which are typically unavailable in real-world scenarios. In this work, we propose a self-supervised super-resolution framework for inter-slice super-resolution of MR images. Our framework is first featured by pre-training on video dataset, as temporal correlation of videos is found beneficial for modeling the spatial relation among MR slices. Then, we use public high-quality MR dataset to fine-tune our pre-trained model, for enhancing awareness of our model to medical data. Finally, given a target dataset at hand, we utilize self-supervised fine-tuning to further ensure our model works well with user-specific super-resolution tasks. The proposed method demonstrates superior performance compared to other self-supervised methods and also holds the potential to benefit various downstream applications.