GAMER-MRI in Multiple Sclerosis Identifies the Diffusion-Based Microstructural Measures That Are Most Sensitive to Focal Damage: A Deep-Learning-Based Analysis and Clinico-Biological Validation
Related Experiment Video
Updated: Nov 8, 2025
Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases
Published on: July 28, 2013
Po-Jui Lu1,2,3, Muhamed Barakovic1,2,3, Matthias Weigel1,2,3,4
1Translational Imaging in Neurology (ThINk) Basel, Department of Biomedical Engineering, University Hospital Basel and University of Basel, Basel, Switzerland.
Abstract:
Conventional magnetic resonance imaging (cMRI) in multiple sclerosis (MS) patients provides measures of focal brain damage and activity, which are fundamental for disease diagnosis, prognosis, and the evaluation of response to therapy. However, cMRI is insensitive to the damage to the microenvironment of the brain tissue and the heterogeneity of MS lesions. In contrast, the damaged tissue can be characterized by mathematical models on multishell diffusion imaging data, which measure different compartmental water diffusion. In this work, we obtained 12 diffusion measures from eight diffusion models, and we applied a deep-learning attention-based convolutional neural network (CNN) (GAMER-MRI) to select the most discriminating measures in the classification of MS lesions and the perilesional tissue by attention weights. Furthermore, we provided clinical and biological validation of the chosen metrics-and of their most discriminative combinations-by correlating their respective mean values in MS patients with the corresponding Expanded Disability Status Scale (EDSS) and the serum level of neurofilament light chain (sNfL), which are measures of disability and neuroaxonal damage. Our results show that the neurite density index from neurite orientation and dispersion density imaging (NODDI), the measures of the intra-axonal and isotropic compartments from microstructural Bayesian approach, and the measure of the intra-axonal compartment from the spherical mean technique NODDI were the most discriminating (respective attention weights were 0.12, 0.12, 0.15, and 0.13). In addition, the combination of the neurite density index from NODDI and the measures for the intra-axonal and isotropic compartments from the microstructural Bayesian approach exhibited a stronger correlation with EDSS and sNfL than the individual measures. This work demonstrates that the proposed method might be useful to select the microstructural measures that are most discriminative of focal tissue damage and that may also be combined to a unique contrast to achieve stronger correlations to clinical disability and neuroaxonal damage.
Insights
Deep learning models identify key microstructural MRI measures for multiple sclerosis (MS) lesion characterization. These advanced diffusion imaging metrics correlate better with patient disability and neuroaxonal damage than conventional MRI.
Area of Science:
- Neuroimaging
- Biomedical Engineering
- Radiology
Background:
- Conventional MRI (cMRI) is limited in detecting subtle microstructural brain damage in multiple sclerosis (MS).
- MS lesions exhibit heterogeneity not fully captured by current imaging techniques.
- Diffusion imaging offers insights into tissue microstructure through mathematical modeling of water diffusion.
Purpose of the Study:
- To apply a deep learning approach (GAMER-MRI) to identify and select the most discriminative diffusion imaging metrics for MS lesion characterization.
- To validate the clinical and biological relevance of selected microstructural metrics by correlating them with disability (EDSS) and neuroaxonal damage (sNfL) in MS patients.
Main Methods:
- Acquired 12 diffusion measures from eight diffusion models using multishell diffusion imaging data.
- Utilized a deep-learning attention-based convolutional neural network (CNN) to determine attention weights for metric discrimination.
- Correlated selected metrics and their combinations with Expanded Disability Status Scale (EDSS) and serum neurofilament light chain (sNfL) levels.
Main Results:
- The neurite density index (NODDI), intra-axonal/isotropic measures (Bayesian approach), and intra-axonal measure (spherical mean technique NODDI) were most discriminating.
- Specific combinations of these metrics showed stronger correlations with EDSS and sNfL than individual measures.
- Attention weights highlighted the discriminative power of selected microstructural metrics.
Conclusions:
- The proposed deep learning method effectively selects microstructural MRI measures for MS lesion analysis.
- Selected metrics and their combinations offer improved characterization of focal tissue damage in MS.
- This approach may lead to novel imaging contrasts correlating strongly with clinical disability and neuroaxonal damage.
