Premium
Extracting diffusion tensor fractional anisotropy and mean diffusivity from 3‐direction DWI scans using deep learning
Author(s) -
Aliotta Eric,
Nourzadeh Hamidreza,
Patel Sohil H.
Publication year - 2021
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.28470
Subject(s) - fractional anisotropy , diffusion mri , artificial intelligence , anisotropy , voxel , convolutional neural network , pattern recognition (psychology) , nuclear magnetic resonance , nuclear medicine , computer science , mathematics , physics , magnetic resonance imaging , optics , medicine , radiology
Purpose To develop and evaluate machine‐learning methods that reconstruct fractional anisotropy (FA) values and mean diffusivities (MD) from 3‐direction diffusion MRI (dMRI) acquisitions. Methods Two machine‐learning models were implemented to map undersampled dMRI signals with high‐quality FA and MD maps that were reconstructed from fully sampled DTI scans. The first model was a previously described multilayer perceptron (MLP), which maps signals and FA/MD values from a single voxel. The second was a convolutional neural network U‐Net model, which maps dMRI slices to full FA/MD maps. Each method was trained on dMRI brain scans (N = 46), and reconstruction accuracies were compared with conventional linear‐least‐squares (LLS) reconstructions. Results In an independent testing cohort (N = 20), 3‐direction U‐Net reconstructions had significantly lower absolute FA error than both 3‐direction MLP (U‐Net 3‐dir : 0.06 ± 0.01 vs. MLP 3‐dir : 0.08 ± 0.01, P < 1 × 10 −5 ) and 6‐direction LLS (LLS 6‐dir : 0.09 ± 0.03, P = 1 × 10 −5 ). The MD errors were not significantly different among 3‐direction MLP (0.06 ± 0.01 × 10 −3 mm 2 /s), 3‐direction U‐Net (0.06 ± 0.01 × 10 −3 mm 2 /s), and 6‐direction LLS (0.07 ± 0.02 × 10 −3 mm 2 /s, P > .1). Conclusion The proposed U‐Net model reconstructed FA from 3‐direction dMRI scans with improved accuracy compared with both a previously described MLP approach and LLS fitting from 6‐direction scans. The MD reconstruction accuracies did not differ significantly between reconstructions.