Related Experiment Video
Updated: Aug 8, 2025
Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging
Published on: November 8, 2012
Using mesoscopic tract-tracing data to guide the estimation of fiber orientation distributions in the mouse brain
Zifei Liang1, Tanzil Mahmud Arefin1, Choong H Lee1
1Department of Radiology, Bernard and Irene Schwartz Center for Biomedical Imaging, New York University School of Medicine, 660 First Ave, New York, NY 10016, USA.
Abstract:
Diffusion MRI (dMRI) tractography is the only tool for non-invasive mapping of macroscopic structural connectivity over the entire brain. Although it has been successfully used to reconstruct large white matter tracts in the human and animal brains, the sensitivity and specificity of dMRI tractography remained limited. In particular, the fiber orientation distributions (FODs) estimated from dMRI signals, key to tractography, may deviate from histologically measured fiber orientation in crossing fibers and gray matter regions. In this study, we demonstrated that a deep learning network, trained using mesoscopic tract-tracing data from the Allen Mouse Brain Connectivity Atlas, was able to improve the estimation of FODs from mouse brain dMRI data. Tractography results based on the network generated FODs showed improved specificity while maintaining sensitivity comparable to results based on FOD estimated using a conventional spherical deconvolution method. Our result is a proof-of-concept of how mesoscale tract-tracing data can guide dMRI tractography and enhance our ability to characterize brain connectivity.
Insights
Deep learning improves diffusion MRI tractography by enhancing fiber orientation estimation using mouse brain connectivity data. This approach boosts specificity while maintaining sensitivity for mapping brain networks.
Area of Science:
- Neuroimaging
- Computational Neuroscience
- Connectomics
Background:
- Diffusion MRI (dMRI) tractography non-invasively maps brain structural connectivity.
- Current dMRI tractography has limitations in sensitivity and specificity, particularly in complex fiber regions.
- Accurate estimation of fiber orientation distributions (FODs) is crucial for tractography.
Purpose of the Study:
- To enhance FOD estimation in mouse brain dMRI data using a deep learning network.
- To improve the specificity and maintain the sensitivity of dMRI tractography.
- To demonstrate the utility of mesoscale tract-tracing data in guiding dMRI tractography.
Main Methods:
- A deep learning network was trained on mesoscopic tract-tracing data from the Allen Mouse Brain Connectivity Atlas.
- The trained network was used to estimate FODs from mouse brain dMRI data.
- Tractography was performed using both network-generated FODs and conventional spherical deconvolution methods.
Main Results:
- The deep learning network improved FOD estimation from mouse brain dMRI data.
- Tractography results using network-generated FODs showed enhanced specificity.
- Sensitivity of tractography remained comparable to conventional methods.
Conclusions:
- Mesoscale tract-tracing data can effectively guide deep learning models for dMRI tractography.
- This approach offers a proof-of-concept for improving the characterization of brain connectivity.
- The study enhances the potential of dMRI tractography in neuroscience research.
