Premium
Artificial neural network for myelin water imaging
Author(s) -
Lee Jieun,
Lee Doohee,
Choi Joon Yul,
Shin Dongmyung,
Shin HyeongGeol,
Lee Jongho
Publication year - 2020
Publication title -
magnetic resonance in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.696
H-Index - 225
eISSN - 1522-2594
pISSN - 0740-3194
DOI - 10.1002/mrm.28038
Subject(s) - artificial neural network , white matter , mri scan , pattern recognition (psychology) , mean squared error , multiple sclerosis , nuclear medicine , mathematics , artificial intelligence , computer science , magnetic resonance imaging , statistics , medicine , radiology , psychiatry
Purpose To demonstrate the application of artificial neural network (ANN) for real‐time processing of myelin water imaging (MWI). Methods Three neural networks, ANN‐I MWF , ANN‐I GMT2 , and ANN‐II, were developed to generate MWI. ANN‐I MWF and ANN‐I GMT2 were designed to output myelin water fraction (MWF) and geometric mean T 2 of intra‐ and extra‐cellular water signal (GMT 2,IEW ), respectively, whereas ANN‐II generates a T 2 distribution. For the networks, gradient and spin echo data from 18 healthy controls (HC) and 26 multiple sclerosis patients (MS) were utilized. Among them, 10 HC and 12 MS had the same scan parameters and were used for training (6 HC and 6 MS), validation (1 HC and 1 MS), and test sets (3 HC and 5 MS). The remaining data had different scan parameters and were applied to exam effects of the scan parameters. The network results were compared with those of conventional MWI in the white matter mask and regions of interest. Results The networks produced highly accurate results, showing averaged normalized root‐mean‐squared error under 3% for MWF and 0.4% for GMT 2,IEW in the white matter mask of the test set. In the region of interest analysis, the differences between ANNs and conventional MWI were less than 0.1% in MWF and 0.1 ms in GMT 2,IEW (no statistical difference and R 2 > 0.97). Datasets with different scan parameters showed increased errors. The average processing time was 0.68 s in ANNs, gaining 11,702 times acceleration in the computational speed (conventional MWI: 7,958 s). Conclusion The proposed neural networks demonstrate the feasibility of real‐time processing for MWI with high accuracy.