Related Experiment Video
Updated: Sep 16, 2025
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
Published on: December 15, 2023
PediMS: A Pediatric Multiple Sclerosis Lesion Segmentation Dataset
Maria Popa1, Gabriela Adriana Vișa2, Ciprian Radu Șofariu2
1Babeș-Bolyai University, Faculty of Mathematics and Computer Science, Department of Computer Science, Mihail Kogălniceanu 1, Cluj-Napoca, Romania. maria.popa@ubbcluj.ro.
Insights
This study presents the first MRI dataset for pediatric multiple sclerosis (MS) lesion segmentation. It aids research into rare pediatric MS cases and improves automated segmentation models.
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.
Abstract:
Multiple Sclerosis (MS) is a chronic autoimmune disease that primarily affects the central nervous system and is predominantly diagnosed in adults, making pediatric cases rare and underrepresented in medical research. This paper introduces the first publicly available MRI dataset specifically dedicated to pediatric multiple sclerosis lesion segmentation. The dataset comprises longitudinal MRI scans from 9 pediatric patients, each with between one and six timepoints, with a total of 28 MRI scans. It includes T1-weighted (MPRAGE), T2-weighted, and FLAIR sequences. Additionally, it provides clinical data and initial symptoms for each patient, offering valuable insights into disease progression. Lesion segmentation was performed by senior experts, ensuring high-quality annotations. To demonstrate the dataset's reliability and utility, we evaluated two deep learning models, achieving competitive segmentation performance. This dataset aims to advance research in pediatric MS, improve lesion segmentation models, and contribute to federated learning approaches.
