Qi Yang1, Colin B Hansen1, Leon Y Cai2, Francois Rheault3, Ho Hin Lee1, Shunxing Bao3, Bramsh Qamar Chandio4, Owen Williams5, Susan M Resnick5, Eleftherios Garyfallidis4,6, Adam W Anderson2,7, Maxime Descoteaux8, Kurt G Schilling7,9, Bennett A Landman1,2,3,7,9. 1. Department of Computer Science, Vanderbilt University, Nashville, Tennessee, USA. 2. Department of Biomedical Engineering, Vanderbilt University, Nashville, Tennessee, USA. 3. Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, Tennessee, USA. 4. Department of Intelligent Systems Engineering, Indiana University, Bloomington, Indiana, USA. 5. Laboratory of Behavioral Neuroscience, National Institute on Aging, Baltimore, Maryland, USA. 6. Program of Neuroscience, Indiana University, Bloomington, Indiana, USA. 7. Vanderbilt University Institute of Imaging Science, Vanderbilt University Medical Centre, Nashville, Tennessee, USA. 8. Sherbrooke Connectivity Imaging Laboratory (SCIL), Université de Sherbrooke, Sherbrooke, Canada. 9. Department of Radiology and Radiological Sciences, Vanderbilt University Medical Centre, Nashville, Tennessee, USA.
Abstract
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.
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.
Authors: Stephen M Smith; Mark Jenkinson; Mark W Woolrich; Christian F Beckmann; Timothy E J Behrens; Heidi Johansen-Berg; Peter R Bannister; Marilena De Luca; Ivana Drobnjak; David E Flitney; Rami K Niazy; James Saunders; John Vickers; Yongyue Zhang; Nicola De Stefano; J Michael Brady; Paul M Matthews Journal: Neuroimage Date: 2004 Impact factor: 6.556
Authors: Susumu Mori; Kenichi Oishi; Hangyi Jiang; Li Jiang; Xin Li; Kazi Akhter; Kegang Hua; Andreia V Faria; Asif Mahmood; Roger Woods; Arthur W Toga; G Bruce Pike; Pedro Rosa Neto; Alan Evans; Jiangyang Zhang; Hao Huang; Michael I Miller; Peter van Zijl; John Mazziotta Journal: Neuroimage Date: 2008-01-03 Impact factor: 6.556
Authors: Anastasia Yendiki; Patricia Panneck; Priti Srinivasan; Allison Stevens; Lilla Zöllei; Jean Augustinack; Ruopeng Wang; David Salat; Stefan Ehrlich; Tim Behrens; Saad Jbabdi; Randy Gollub; Bruce Fischl Journal: Front Neuroinform Date: 2011-10-14 Impact factor: 4.081
Authors: Colin B Hansen; Qi Yang; Ilwoo Lyu; Francois Rheault; Cailey Kerley; Bramsh Qamar Chandio; Shreyas Fadnavis; Owen Williams; Andrea T Shafer; Susan M Resnick; David H Zald; Laurie E Cutting; Warren D Taylor; Brian Boyd; Eleftherios Garyfallidis; Adam W Anderson; Maxime Descoteaux; Bennett A Landman; Kurt G Schilling Journal: Neuroinformatics Date: 2020-11-16