Data from: A Deep Learning Approach for Fast Muscle Water T2 Mapping with Subject Specific Fat T2 Calibration from Multi-Spin-Echo Acquisitions
Authors/Creators
Description
This repository contains the imaging data (in NIfTI) and analysis code to reproduce the work presented in "A Deep Learning Approach for Fast Muscle Water T2 Mapping with Subject Specific Fat T2 Calibration from Multi-Spin-Echo Acquisitions" by Marco Barbieri, Melissa T. Hooijmans, Kevin Moulin, Tyler E. Cork, Daniel B. Ennis, Garry E. Gold, Feliks Kogan and Valentina Mazzoli.
Citation: "Barbieri, M., Hooijmans, M.T., Moulin, K. et al. A deep learning approach for fast muscle water T2 mapping with subject specific fat T2 calibration from multi-spin-echo acquisitions. Sci Rep 14, 8253 (2024). https://doi.org/10.1038/s41598-024-58812-2"
The source code for setting up the Deep Learning application can be found in the GitHub repository https://github.com/barma7/Deep_Learning_for_Muscle_T2_mapping.git
Notes
If you use any of the data or script included in this repository, please cite the original paper:
Barbieri, M., Hooijmans, M.T., Moulin, K. et al. A deep learning approach for fast muscle water T2 mapping with subject specific fat T2 calibration from multi-spin-echo acquisitions. Sci Rep 14, 8253 (2024). https://doi.org/10.1038/s41598-024-58812-2
Abstract
This work presents a deep learning approach for rapid and accurate muscle water T2 with subject-specific fat T2 calibration using Multi-Spin-Echo (MESE) acquisitions. This method addresses the computational limitations of conventional bi-component Extended Phase Graph (EPG) fitting methods (nonlinear-least-squares and dictionary-based) by leveraging fully connected neural networks for fast processing with minimal computational resources. We validated the approach through in vivo experiments using two different MRI vendors. The results showed strong agreement of our deep learning approach with reference methods, summarized by Lin's concordance correlation coefficients ranging from 0.89 to 0.97. Further, the deep learning method achieved a significant computational time improvement, processing data 116 and 33 times faster than the nonlinear least squares and dictionary methods, respectively. In conclusion, the proposed approach demonstrated significant time and resource efficiency improvements over conventional methods while maintaining similar accuracy. This methodology makes the processing of water T2 data faster and easier for the user and will facilitate the utilization of the use of a quantitative water T2 map of muscle in clinical and research studies.