Shedding Light on the Invisible: A New Paradigm for Predicting Multiple Sclerosis Disease Progression Using Novel MRI Tools for Probing Pathology in Normal Appearing Tissues

Applying advanced quantitative MRI to detect pathology invisible to current clinical tools, this project builds an AI model to predict MS progression and enable earlier, more personalized diagnosis and treatment.
Ongoing Multiple Sclerosis Neurologic Diseases Biomarker Discovery Data-Driven & Quantitative Early Disease Detection Experimental Platforms & Models Human Cohorts Machine Learning & AI Precision Medicine Translational & Clinical

Funding Year: 2023

Project Overview

Current clinical tools are poorly suited to predicting multiple sclerosis progression, limiting treatment decision-making and reducing the effectiveness of existing therapies. While recent advances in quantitative MRI have demonstrated significantly higher sensitivity to pathological tissue changes, these techniques remain unused in clinical settings. This project applies state-of-the-art q/µMRI to follow patients over two years, probing MS pathology in normal-appearing brain tissue invisible to standard imaging. Combined with cognitive and clinical scores, these datasets will train an AI tool capable of predicting MS progression — with goals of identifying unknown disease mechanisms, supporting personalized treatment planning, and enabling earlier diagnosis in patients with CIS or RIS.

Impact & Innovation

Seeing MS pathology that current tools miss.

 

By applying q/µMRI to normal-appearing brain tissue and combining findings with cognitive and clinical scores, this project builds an AI tool that predicts MS progression from signals previously invisible to clinicians.

  • Improves correlation between MRI-detected brain pathology and disease symptoms, surfacing mechanisms that standard imaging cannot capture
  • Generates a patentable AI-based prognostic tool for MS, with applications in differential diagnosis and early identification of CIS and RIS patients
  • Advances the Consortium’s Integrated Data and Discovery Platforms pillar by combining novel imaging modalities with AI to create a new standard for MS disease monitoring
Research Approach

A framework designed for discovery

This project combines advanced quantitative MRI acquisition with longitudinal patient follow-up and artificial intelligence to develop a predictive tool for MS disease progression. The work moves from novel imaging data collection through AI model construction and clinical validation.

Application of state-of-the-art q/µMRI techniques to detect pathological changes in normal-appearing brain tissue, longitudinal patient follow-up over two years, and integration of MRI-derived data with cognitive and clinical scores to train and validate an AI-based disease progression prediction model.

Quantitative MRI datasets from MS patients followed over a two-year period, cognitive assessment scores, clinical outcome measures, and integrated imaging-clinical datasets used to construct and validate the AI progression prediction tool.

Development of a validated AI tool that predicts MS disease progression by correlating novel MRI-detected brain pathology with clinical and cognitive outcomes, with translational goals including improved differential diagnosis, earlier identification of CIS and RIS patients at risk of MS, and support for personalized treatment planning and drug development.

Investigators & Institutions

Powering the science

Principal Investigators

Noam Ben-Eliezer, PhD, Colton Consortium Member

Professor, School of Biomedical Engineering; Sagol School of Neuroscience, Tel Aviv University

Hadar Kolb, MD, Colton Consortium Member

Head of Precision Medicine, Neuroimmunology, Neurology, Tel Aviv Sourasky Medical Center, Tel Aviv University

Colton Centers & Institutions

Colton Center for Autoimmunity at Tel Aviv University