A deep learning approach for magnetic resonance fingerprinting: Scaling capabilities and good training practices investigated by simulations. |
| |
Institution: | 1. Siemens Healthcare, Erlangen, Germany;2. Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany;3. Departments of Biomedical Engineering and Radiology, University of Virginia, Charlottesville, VA, USA;1. Institute for Biomedical Engineering, University and ETH Zurich, Zurich, Switzerland;2. Division of Gastroenterology and Hepatology, University Hospital Zurich, Zurich, Switzerland;1. The Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Health Sciences Research Building, 1760 Haygood Drive, Suite W200, Atlanta, GA 30322, USA;2. Center for Biomedical Imaging Research, Tsinghua University, Beijing 100084, China;3. Department of Bioengineering, University of California, Riverside, 900 University Avenue, Riverside, CA 92521, USA;2. The Sackler Institute at the New York University School of Medicine, 550 First Avenue, New York, NY 10016, USA |
| |
Abstract: | MR fingerprinting (MRF) is an innovative approach to quantitative MRI. A typical disadvantage of dictionary-based MRF is the explosive growth of the dictionary as a function of the number of reconstructed parameters, an instance of the curse of dimensionality, which determines an explosion of resource requirements. In this work, we describe a deep learning approach for MRF parameter map reconstruction using a fully connected architecture. Employing simulations, we have investigated how the performance of the Neural Networks (NN) approach scales with the number of parameters to be retrieved, compared to the standard dictionary approach. We have also studied optimal training procedures by comparing different strategies for noise addition and parameter space sampling, to achieve better accuracy and robustness to noise. Four MRF sequences were considered: IR-FISP, bSSFP, IR-FISP-, and IR-bSSFP-. A comparison between NN and the dictionary approaches in reconstructing parameter maps as a function of the number of parameters to be retrieved was performed using a numerical brain phantom. Results demonstrated that training with random sampling and different levels of noise variance yielded the best performance. NN performance was at least as good as the dictionary-based approach in reconstructing parameter maps using Gaussian noise as a source of artifacts: the difference in performance increased with the number of estimated parameters because the dictionary method suffers from the coarse resolution of the parameter space sampling. The NN proved to be more efficient in memory usage and computational burden, and has great potential for solving large-scale MRF problems. |
| |
Keywords: | MR fingerprinting Deep learning qMRI Parameter mapping |
本文献已被 ScienceDirect 等数据库收录! |
|