# Magnetic Resonance Fingerprinting using Recurrent Neural Networks

arXiv: https://arxiv.org/abs/1812.08155 · HTML: https://mlsanity.com/paper/1812.08155/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2018.

## Built on by (most cited first, 7 of 7)

- [Cram'er-Rao bound-informed training of neural networks for quantitative MRI](https://mlsanity.com/paper/2109.10535/) (2021)
- [Learning Personal Representations from fMRIby Predicting Neurofeedback Performance](https://mlsanity.com/paper/2112.04902/) (2021)
- [Solving inverse problems with deep neural networks driven by sparse signal decomposition in a physics-based dictionary](https://mlsanity.com/paper/2107.10657/) (2021)
- [Improving Urban Flood Prediction using LSTM-DeepLabv3+ and Bayesian Optimization with Spatiotemporal feature fusion](https://mlsanity.com/paper/2304.09994/) (2023)
- [Magnetic Resonance Spectroscopy Deep Learning Denoising Using Few In Vivo Data](https://mlsanity.com/paper/2101.11442/) (2021)
- [fMRI Neurofeedback Learning Patterns are Predictive of Personal and Clinical Traits](https://mlsanity.com/paper/2112.11014/) (2021)
- [Exploiting Manifold Structured Data Priors for Improved MR Fingerprinting Reconstruction](https://mlsanity.com/paper/2310.05647/) (2023)

## Abstract (arXiv)

Magnetic Resonance Fingerprinting (MRF) is a new approach to quantitative magnetic resonance imaging that allows simultaneous measurement of multiple tissue properties in a single, time-efficient acquisition. Standard MRF reconstructs parametric maps using dictionary matching and lacks scalability due to computational inefficiency. We propose to perform MRF map reconstruction using a recurrent neural network, which exploits the time-dependent information of the MRF signal evolution. We evaluate our method on multiparametric synthetic signals and compare it to existing MRF map reconstruction approaches, including those based on neural networks. Our method achieves state-of-the-art estimates of T1 and T2 values. In addition, the reconstruction time is significantly reduced compared to dictionary-matching based approaches.