Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces Longitudinal Guided Group Sparsity (LGGS), a deep learning framework that leverages prior MRI scans to accelerate current scan reconstruction by incorporating learned phase-invariant attention. LGGS addresses challenges like misregistration and phase variation to effectively utilize longitudinal information, achieving state-of-the-art performance on accelerated brain MRI reconstruction. The framework demonstrates robustness and efficiency, outperforming existing methods with fewer learned parameters.
Prior MRI scans can slash reconstruction times by 4x without sacrificing image quality, even with significant patient movement between visits.
Serial MRI is routinely performed in current clinical practice for disease surveillance and applications such as MR-guided radiotherapy. However, long MRI scan times increase costs and limit patient access, making accelerated image reconstruction of broad clinical importance. Previous scans of the same patient contain image information highly correlated with the current exam, yet existing reconstruction methods rarely exploit this information. Major challenges in the effective use of prior scans include inter-visit misregistration, pathological changes, and image phase variation. In this work, we propose Longitudinal Guided Group Sparsity (LGGS), an interpretable deep-learning framework for longitudinally informed MRI reconstruction derived from classical group sparsity. The prior scan is incorporated into the reconstruction regularizer through learned phase-invariant circulant attention that identifies corresponding features across exams. This formulation provides robustness to local in-plane and through-plane misregistration as well as inter-visit phase variation. Across acceleration rates, LGGS achieves state-of-the-art performance on longitudinal T1-weighted multi-coil brain MRI data, outperforming the evaluated unguided and longitudinally informed reconstruction methods, with substantially fewer learned parameters. We further evaluated the contributions of multiple guide slices and phase-invariant similarity and demonstrated that accelerated prior images can also serve as effective guides with minimal degradation in reconstruction quality.