NLCG-Net: A Model-Based Zero-Shot Learning Framework for Undersampled Quantitative MRI Reconstruction
This addresses biases in quantitative MRI for medical imaging, though it appears incremental as it builds on existing model-based and neural network methods.
The paper tackled the problem of error propagation in quantitative MRI reconstruction by proposing NLCG-Net, a model-based zero-shot learning framework that directly estimates T1 and T2 maps from undersampled k-space data, resulting in improved estimation quality at high accelerations compared to subspace reconstruction.
Typical quantitative MRI (qMRI) methods estimate parameter maps after image reconstructing, which is prone to biases and error propagation. We propose a Nonlinear Conjugate Gradient (NLCG) optimizer for model-based T2/T1 estimation, which incorporates U-Net regularization trained in a scan-specific manner. This end-to-end method directly estimates qMRI maps from undersampled k-space data using mono-exponential signal modeling with zero-shot scan-specific neural network regularization to enable high fidelity T1 and T2 mapping. T2 and T1 mapping results demonstrate the ability of the proposed NLCG-Net to improve estimation quality compared to subspace reconstruction at high accelerations.