Deep learning within a priori temporal feature spaces for large-scale dynamic MR image reconstruction: Application to 5-D cardiac MR Multitasking

TL;DR

This paper introduces a novel deep learning approach that utilizes a priori temporal feature spaces to enable efficient, large-scale dynamic MRI reconstruction, significantly reducing computation time and facilitating clinical use.

Contribution

The work presents a new method combining deep neural networks with a priori temporal features, allowing global temporal modeling in large-scale dynamic MRI sequences.

Findings

Speeds up feature space calculation by 3000x

Enables reconstruction of sequences with over 40,000 frames

Makes large-scale dynamic MRI feasible for routine clinical use

Abstract

High spatiotemporal resolution dynamic magnetic resonance imaging (MRI) is a powerful clinical tool for imaging moving structures as well as to reveal and quantify other physical and physiological dynamics. The low speed of MRI necessitates acceleration methods such as deep learning reconstruction from under-sampled data. However, the massive size of many dynamic MRI problems prevents deep learning networks from directly exploiting global temporal relationships. In this work, we show that by applying deep neural networks inside a priori calculated temporal feature spaces, we enable deep learning reconstruction with global temporal modeling even for image sequences with >40,000 frames. One proposed variation of our approach using dilated multi-level Densely Connected Network (mDCN) speeds up feature space coordinate calculation by 3000x compared to conventional iterative methods, from 20 minutes to 0.39 seconds. Thus, the combination of low-rank tensor and deep learning models not only makes large-scale dynamic MRI feasible but also practical for routine clinical application.