Learning white matter subject‐specific segmentation from structural MRI

• Published in: Medical physics (Lancaster) Vol. 49; no. 4; pp. 2502 - 2513
• Main Authors: Yang, Qi, Hansen, Colin B., Cai, Leon Y., Rheault, Francois, Lee, Ho Hin, Bao, Shunxing, Chandio, Bramsh Qamar, Williams, Owen, Resnick, Susan M., Garyfallidis, Eleftherios, Anderson, Adam W., Descoteaux, Maxime, Schilling, Kurt G., Landman, Bennett A.
• Format: Journal Article
• Language: English
• Published: United States 01.04.2022
• Subjects: Brain - diagnostic imaging; Diffusion Tensor Imaging - methods; Humans; Image Processing, Computer-Assisted - methods; learning methods and patch‐wise deep neural network; Longitudinal Studies; Magnetic Resonance Imaging; T1 weight MRI; tractography algorithms; white matter; White Matter - diagnostic imaging; white matter; tractography algorithms; learning methods and patch-wise deep neural network; T1 weight MRI
• ISSN: 0094-2405; 2473-4209; 2473-4209
• DOI: 10.1002/mp.15495

Purpose Mapping brain white matter (WM) is essential for building an understanding of brain anatomy and function. Tractography‐based methods derived from diffusion‐weighted MRI (dMRI) are the principal tools for investigating WM. These procedures rely on time‐consuming dMRI acquisitions that may not always be available, especially for legacy or time‐constrained studies. To address this problem, we aim to generate WM tracts from structural magnetic resonance imaging (MRI) image by deep learning. Methods Following recently proposed innovations in structural anatomical segmentation, we evaluate the feasibility of training multiply spatial localized convolution neural networks to learn context from fixed spatial patches from structural MRI on standard template. We focus on six widely used dMRI tractography algorithms (TractSeg, RecoBundles, XTRACT, Tracula, automated fiber quantification (AFQ), and AFQclipped) and train 125 U‐Net models to learn these techniques from 3870 T1‐weighted images from the Baltimore Longitudinal Study of Aging, the Human Connectome Project S1200 release, and scans acquired at Vanderbilt University. Results The proposed framework identifies fiber bundles with high agreement against tractography‐based pathways with a median Dice coefficient from 0.62 to 0.87 on a test cohort, achieving improved subject‐specific accuracy when compared to population atlas‐based methods. We demonstrate the generalizability of the proposed framework on three externally available datasets. Conclusions We show that patch‐wise convolutional neural network can achieve robust bundle segmentation from T1w. We envision the use of this framework for visualizing the expected course of WM pathways when dMRI is not available.