# NLCG-Net: A Model-Based Zero-Shot Learning Framework for Undersampled Quantitative MRI Reconstruction

arXiv: https://arxiv.org/abs/2401.12004 · HTML: https://mlsanity.com/paper/2401.12004/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 6 references that are in the map.
- First posted on arXiv 22 Jan 2024.

## Builds on (most cited first, 3 of 3)

- [MoDL: Model Based Deep Learning Architecture for Inverse Problems](https://mlsanity.com/paper/1712.02862/) (2017)
- [Zero-Shot Self-Supervised Learning for MRI Reconstruction](https://mlsanity.com/paper/2102.07737/) (2021)
- [SSL-QALAS: Self-Supervised Learning for Rapid Multiparameter Estimation in Quantitative MRI Using 3D-QALAS](https://mlsanity.com/paper/2302.14240/) (2023)

## Abstract (arXiv)

Typical quantitative MRI (qMRI) methods estimate parameter maps in a two-step pipeline that first reconstructs images from undersampled k-space data and then performs model fitting, which is prone to biases and error propagation. We propose NLCG-Net, a model-based nonlinear conjugate gradient (NLCG) framework for joint T2/T1 estimation that incorporates a U-Net regularizer trained in a scan-specific, zero-shot fashion. The method directly estimates qMRI maps from undersampled k-space using mono-exponential signal modeling with scan-specific neural network regularization, enabling high-fidelity T1 and T2 mapping. Experimental results on T2 and T1 mapping demonstrate that NLCG-Net improves estimation quality over subspace reconstruction at high acceleration factors.