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

2025-07-28

AI Summary

MRI acquisition is time-consuming, limiting clinical throughput and patient comfort. This paper proposes a deep learning framework that leverages a subject’s prior T1-weighted MRI scans to reconstruct high-fidelity accelerated acquisitions—without explicit image registration. The method integrates an initial reconstruction network, an implicit deformation modeling module, and a Transformer-enhanced refinement module, enabling end-to-end joint optimization while eliminating the computational overhead of conventional registration. Evaluated across acceleration factors R=5–20, our approach significantly outperforms state-of-the-art methods (p < 0.05), achieving a 3.2% improvement in Dice score for brain tissue segmentation, a 41% reduction in volumetric consistency error, and an inference time of only 120 ms per reconstruction—demonstrating strong potential for real-time clinical deployment.

Technology Category

• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

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.

Problem

• Reducing MRI scan time using deep learning reconstruction
• Improving image quality with prior subject-specific MRI data
• Accelerating reconstruction process for clinical real-time use

Innovation

• Deep learning reconstruction with prior subject-specific MRI
• Transformer-based enhancement network for MRI quality
• Reduced reconstruction time for clinical applications