Detecting Multiple Sclerosis with Machine Learning using DTI Metrics

Motivation: Diagnosing early-stage multiple sclerosis is challenging due to symptom variability, highlighting the need for reliable, non-invasive tools to detect MS-specific microstructural changes. Goal(s): This study aimed to evaluate the effectiveness of Diffusion Tensor Imaging metrics, combined with machine learning, to distinguish MS patients from healthy controls. Approach: A total of 630 DTI measurements were acquired using a 3T MRI scanner. FA, MD, AD, and RD values were calculated for 98 ROIs, followed by analysis with a Histogram-Based Gradient Boosting model. Results: The best model achieved high accuracy (83.97%) and ROC AUC (0.91), indicating strong potential for MS detection. Impact: Using DTI metrics allows the development of machine learning models that are capable of distinguishing multiple sclerosis patients from healthy controls, enabling accurate early-stage diagnosis, and providing clinicians with a non-invasive diagnostic tool.