Document Type
Article
Publication Date
7-11-2019
Publication Title
Journal of Big Data
Publisher
SpringerOpen
Volume
6
Issue
61
First page number:
1
Last page number:
12
Abstract
The human brain is a complex system of neural tissue that varies significantly between individuals. Although the technology that delineates these neural pathways does not currently exist, medical imaging modalities, such as diffusion magnetic resonance imaging (dMRI), can be leveraged for mathematical identification. The purpose of this work is to develop a novel method employing machine learning techniques to determine intravoxel nerve number and direction from dMRI data. The method was tested on multiple synthetic datasets and showed promising estimation accuracy and robustness for multi-nerve systems under a variety of conditions, including highly noisy data and imprecision in parameter assumptions.
Keywords
Ball-and-stick model; Diffusion MRI; Tractography; Nerve; Neural tracts; Brain imaging
Disciplines
Bioimaging and Biomedical Optics | Biomedical Engineering and Bioengineering | Neuroscience and Neurobiology
File Format
File Size
1.498 KB
Language
English
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Repository Citation
Hart, A.,
Smith, B.,
Smith, S.,
Sales, E.,
Hernandez-Camargo, J.,
Mayor Garcia, Y.,
Zhan, F.,
Griswold, L.,
Dunkelberger, B.,
Schwob, M. R.,
Chaudhry, S.,
Zhan, J.,
Gewali, L.,
Oh, P.
(2019).
Resolving Intravoxel White Matter Structures in the Human Brain Using Regularized Regression and Clustering.
Journal of Big Data, 6(61),
1-12.
SpringerOpen.
http://dx.doi.org/10.1186/s40537-019-0223-2