Enhancing and Accelerating Brain MRI through Deep Learning Reconstruction Using Prior Subject-Specific Imaging

TL;DR

This paper introduces a deep learning framework that leverages prior subject-specific MRI scans to enhance and accelerate brain MRI reconstruction, improving quality, reducing time, and aiding downstream segmentation tasks.

Contribution

A novel deep learning reconstruction method integrating registration and transformer networks for faster, higher-quality MRI imaging using prior scans.

Findings

Outperforms existing MRI reconstruction methods with statistical significance.

Improves brain segmentation accuracy and volumetric agreement.

Reduces total reconstruction time for real-time clinical use.

Abstract

Magnetic resonance imaging (MRI) is a crucial medical imaging modality. However, long acquisition times remain a significant challenge, leading to increased costs, and reduced patient comfort. Recent studies have shown the potential of using deep learning models that incorporate information from prior subject-specific MRI scans to improve reconstruction quality of present scans. Integrating this prior information requires registration of the previous scan to the current image reconstruction, which can be time-consuming. We propose a novel deep-learning-based MRI reconstruction framework which consists of an initial reconstruction network, a deep registration model, and a transformer-based enhancement network. We validated our method on a longitudinal dataset of T1-weighted MRI scans with 2,808 images from 18 subjects at four acceleration factors (R5, R10, R15, R20). Quantitative metrics confirmed our approach's superiority over existing methods (p < 0.05, Wilcoxon signed-rank test). Furthermore, we analyzed the impact of our MRI reconstruction method on the downstream task of brain segmentation and observed improved accuracy and volumetric agreement with reference segmentations. Our approach also achieved a substantial reduction in total reconstruction time compared to methods that use traditional registration algorithms, making it more suitable for real-time clinical applications. The code associated with this work is publicly available at https://github.com/amirshamaei/longitudinal-mri-deep-recon.