Related Experiment Video
Updated: May 9, 2026
12:23
Dynamic Visual Tests to Identify and Quantify Visual Damage and Repair Following Demyelination in Optic Neuritis Patients
Published on: April 14, 2014
14.0K
New approaches to lesion assessment in multiple sclerosis
Paolo Preziosa1,2,3, Massimo Filippi1,2,3,4,5, Maria A Rocca1,2,3
1Neuroimaging Research Unit, Division of Neuroscience, IRCCS San Raffaele Scientific Institute.
Current Opinion in Neurology
|May 16, 2025
Summary
Artificial intelligence (AI) enhances multiple sclerosis (MS) lesion segmentation, improving accuracy and efficiency. Novel neuroimaging techniques offer deeper insights into MS lesion pathology for better diagnosis and treatment.
Area of Science:
- Neuroimaging
- Artificial Intelligence
- Multiple Sclerosis Research
Background:
- Multiple sclerosis (MS) is a chronic neurological disease characterized by lesions in the central nervous system.
- Accurate identification and characterization of MS lesions are crucial for diagnosis, monitoring disease progression, and assessing treatment response.
Purpose of the Study:
- To review recent advancements in artificial intelligence (AI)-driven lesion segmentation for MS.
- To highlight novel neuroimaging modalities that improve the identification and characterization of MS lesions.
- To discuss the clinical and research implications of these advancements.
Main Methods:
- Review of recent literature on AI applications in MS lesion segmentation.
- Summary of novel neuroimaging techniques relevant to MS lesion characterization.
- Analysis of the potential impact on clinical practice and research.
Main Results:
- AI, particularly deep learning, significantly improves the accuracy, reproducibility, and efficiency of MS lesion segmentation.
- AI tools can automate the detection of various lesion types, including T2-hyperintense, gadolinium-enhancing, and cortical lesions, which have diagnostic and prognostic value.
- Emerging neuroimaging techniques like quantitative susceptibility mapping (QSM) and PET provide enhanced insights into lesion pathology and heterogeneity.
Conclusions:
- AI-powered lesion segmentation offers potential for faster, more accurate, and reproducible MS lesion assessment in clinical settings.
- These tools can improve MS diagnosis, monitoring, and treatment response evaluation.
- Novel neuroimaging modalities may advance the understanding of MS pathophysiology, offering specific markers for disease progression and potential therapeutic targets.
