Magnetic Resonance Fingerprinting Reconstruction via Spatiotemporal Convolutional Neural Networks

TL;DR

This paper introduces a spatiotemporal convolutional neural network for magnetic resonance fingerprinting reconstruction, significantly improving accuracy and speed over traditional dictionary matching methods.

Contribution

It presents a novel neural network approach that exploits spatiotemporal relationships to replace computationally intensive dictionary matching in MRF reconstruction.

Findings

Achieves state-of-the-art accuracy in MRF map reconstruction

Produces more visually appealing parametric maps

Reduces reconstruction time significantly

Abstract

Magnetic resonance fingerprinting (MRF) quantifies multiple nuclear magnetic resonance parameters in a single and fast acquisition. Standard MRF reconstructs parametric maps using dictionary matching, which lacks scalability due to computational inefficiency. We propose to perform MRF map reconstruction using a spatiotemporal convolutional neural network, which exploits the relationship between neighboring MRF signal evolutions to replace the dictionary matching. We evaluate our method on multiparametric brain scans and compare it to three recent MRF reconstruction approaches. Our method achieves state-of-the-art reconstruction accuracy and yields qualitatively more appealing maps compared to other reconstruction methods. In addition, the reconstruction time is significantly reduced compared to a dictionary-based approach.