Model-based Dynamic 3D MRI Reconstructions using Neural Fields and Tensor Product Expansions
This work addresses the problem of accurate dynamic MRI reconstruction under high undersampling, which is critical for clinical applications like cardiac imaging.
The paper introduces a model-based, discretization-free framework for dynamic 2D and 3D MRI reconstruction using tensor products of neural fields, achieving state-of-the-art performance with acceleration factors up to 16.
Conventional MRI reconstruction methods treat images and coil sensitivities as discrete objects, leading to high memory demands and limited structural awareness that hamper effective regularization. These limitations hinder accurate reconstruction in highly undersampled scenarios, such as dynamic 3D cardiac magnetic resonance (CMR). We introduce a discretization-free, memory-efficient, model-based framework for dynamic 2D and 3D MRI reconstruction from highly undersampled data. We represent magnetization and coil sensitivities as continuous objects -- differentiable functions -- using tensor products of univariate neural fields. This tensor product structure enables scalable optimization in high-dimensional spatiotemporal settings. Our method outperforms state-of-the-art model-based reconstructions in dynamic 2D and 3D MR settings, preserving structure and motion even under aggressive undersampling (e.g., acceleration factor 16).