Meeting Banner
Abstract #3410

Bi-parametric Joint Label Fusion: An Improved Segmentation Tool for Deep Gray Matter in QSM

Fahad Salman1,2, Kevin Thomas1, Ademola Adegbemigun1, Niels P. Bergsland1, Michael G. Dwyer1,3, Robert Zivadinov1,3, and Ferdinand Schweser1,3
1Buffalo Neuroimaging Analysis Center, Department of Neurology at the Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, The State University of New York, Buffalo, NY, United States, 2Department of Biomedical Engineering, University at Buffalo, The State University of New York, Buffalo, NY, United States, 3Center for Biomedical Imaging, Clinical and Translational Science Institute, University at Buffalo, The State University of New York, Buffalo, NY, United States

Synopsis

Keywords: Segmentation, Segmentation, Deep gray matter, multiple sclerosis, susceptibility, T1 contrast, FSL FIRST, SynthSeg, FreeSurfer, joint label fusion, multi-contrast, automated segmentation

Motivation: Publicly available T1-weighted-based segmentation tools may introduce systematic errors, especially in conditions like multiple sclerosis (MS), where atrophy is common.

Goal(s): We aimed to improve segmentation accuracy by developing a multi-atlas, bi-parametric DGM tool (bi-parametric joint label fusion [B-JLF], leveraging QSM and T1-weighted images.

Approach: We generated nine group-specific atlases across age and disease spectra, and modified the original ANTs JLF for multi-contrast based segmentation. We compared our tool against T1-based methods using overlap and susceptibility measures against manual segmentations.

Results: B-JLF achieved superior voxel overlap (75%) and highest correlation with ground truth susceptibility (R²=0.88), outperforming T1-based methods.

Impact: B-JLF provides reliable DGM segmentation, enhancing quantitative accuracy in neurodegenerative studies. The tool and atlases are publicly accessible, supporting broader neuroimaging applications.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords