# Accelerating 3D radial MPnRAGE using a self‐supervised deep factor model

## TL;DR

This paper introduces a self-supervised deep learning method to improve 3D MRI image reconstruction, offering faster and more accurate results for multicontrast T1 imaging.

## Contribution

A self-supervised deep factor model is proposed for efficient 4D non-Cartesian MRI reconstruction with high resolution and parametric dimensions.

## Key findings

- DFM-SSL improved image quality and reduced bias and variance in T1 estimates compared to other methods.
- DFM-TL reduced inference time while maintaining performance comparable to DFM-SSL.
- The DFM outperformed subspace methods in highly accelerated MPnRAGE settings.

## Abstract

To develop a self‐supervised and memory‐efficient deep learning image reconstruction method for 4D non‐Cartesian MRI with high resolution and a large parametric dimension.

The deep factor model (DFM) represents a parametric series of 3D multicontrast images using a neural network conditioned by the inversion time using efficient zero‐filled reconstructions as input estimates. The model parameters are learned in a single‐shot learning (SSL) fashion from the k‐space data of each acquisition. A compatible transfer learning (TL) approach using previously acquired data is also developed to reduce reconstruction time. The DFM is compared to subspace methods with different regularization strategies in a series of phantom and in vivo experiments using the MPnRAGE acquisition for multicontrast T1 imaging and quantitative T1 estimation.

DFM‐SSL improved the image quality and reduced bias and variance in quantitative T1 estimates in both phantom and in vivo studies, outperforming all other tested methods. DFM‐TL reduced the inference time while maintaining a performance comparable to DFM‐SSL and outperforming subspace methods with multiple regularization techniques.

The proposed DFM offers a superior representation of the multicontrast images compared to subspace models, especially in the highly accelerated MPnRAGE setting. The self‐supervised training is ideal for methods with both high resolution and a large parametric dimension, where training neural networks can become computationally demanding without a dedicated high‐end GPU array.