PediMS: A Pediatric Multiple Sclerosis Lesion Segmentation Dataset.

Area of Science:

• Neuroimaging
• Pediatric Neurology
• Medical Data Science

Background:

• Multiple Sclerosis (MS) predominantly affects adults, with pediatric cases being rare and understudied.
• Limited research and datasets exist for pediatric multiple sclerosis, hindering advancements.
• Accurate lesion segmentation is crucial for understanding disease progression in pediatric MS.

Purpose of the Study:

• Introduce the first publicly available MRI dataset for pediatric multiple sclerosis lesion segmentation.
• Facilitate research into rare pediatric MS cases and improve diagnostic tools.
• Support the development of advanced automated lesion segmentation models.

Main Methods:

• Collected longitudinal MRI scans (T1, T2, FLAIR) from 9 pediatric MS patients (28 scans total).
• Provided expert-annotated lesion segmentations for high-quality data.
• Included clinical data and initial symptoms for comprehensive analysis.
• Evaluated deep learning models for segmentation performance.

Main Results:

• Established a novel, high-quality MRI dataset for pediatric MS.
• Demonstrated competitive segmentation performance using deep learning models.
• Provided insights into pediatric MS lesion characteristics and progression.

Conclusions:

• The dataset is a valuable resource for advancing pediatric MS research.
• It will aid in developing and validating improved lesion segmentation algorithms.
• The dataset supports future work in federated learning for rare diseases.