Meeting Banner
Abstract #5104

Detecting Multiple Sclerosis with Machine Learning using DTI Metrics

Julia Lasek1, Agnieszka Słowik2, and Artur Tadeusz Krzyżak1
1AGH University of Kraków, Krakow, Poland, 2UJ CM: Department of Neurology, Jagiellonian University Medical College, University Hospital in Krakow, Kraków, Poland

Synopsis

Keywords: Diagnosis/Prediction, Diagnosis/Prediction

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.

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