MambaRecon: MRI Reconstruction with Structured State Space Models
This work addresses faster MRI reconstruction for medical imaging, but it appears incremental as it applies a recently proposed model type to a known domain.
The authors tackled the problem of slow MRI scanning by proposing a new reconstruction framework using structured state space models, which achieved state-of-the-art results on public brain MRI datasets.
Magnetic Resonance Imaging (MRI) is one of the most important medical imaging modalities as it provides superior resolution of soft tissues, albeit with a notable limitation in scanning speed. The advent of deep learning has catalyzed the development of cutting-edge methods for the expedited reconstruction of MRI scans, utilizing convolutional neural networks and, more recently, vision transformers. Recently proposed structured state space models (e.g., Mamba) have gained some traction due to their efficiency and low computational requirements compared to transformer models. We propose an innovative MRI reconstruction framework that employs structured state space models at its core, aimed at amplifying both long-range contextual sensitivity and reconstruction efficacy. Comprehensive experiments on public brain MRI datasets show that our model sets new benchmarks beating state-of-the-art reconstruction baselines. Code will be available (https://github.com/yilmazkorkmaz1/MambaRecon).