Keywords: Segmentation, AI/ML Software, Morphometry, Contrast-invariance, Signal Modeling, Deep Learning
Motivation: Brain morphometry is increasingly recognized as potential biomarker for tracking neurodegenerative disease progression. However, variations in MRI acquisition parameters, common in clinical practice, compromise the reliability of morphometric measures.
Goal(s): To achieve contrast-invariant morphometry across MPRAGE images with varying grey/white matter contrasts.
Approach: We retrained a deep-learning-based segmentation tool (DL+DiReCT) by modeling MPRAGE contrast variations as a function of MRI parameters (TI and TR). Cortical thickness variability was assessed before and after retraining.
Results: The retrained model improved contrast invariance, reducing the contrast-related cortical thickness dependence from 5% to 2% across clinically relevant parameters.
Impact: We created a contrast-invariant segmentation tool that improves brain morphometry accuracy across variable MRI settings, enabling more reliable monitoring of neurodegenerative disease progression. This tool improves assessment accuracy across longitudinal and multi-parameter MRI acquisitions common in clinical practice.
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.
Keywords