Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ICPR 2024 Competition on Multiple Sclerosis Lesion Segmentation -- Methods and Results

Alessia Rondinella, Francesco Guarnera, Elena Crispino, Giulia Russo, Clara Di Lorenzo, Davide Maimone, Francesco Pappalardo, Sebastiano Battiato

TL;DR

This report summarizes the outcomes of the ICPR 2024 Competition on Multiple Sclerosis Lesion Segmentation, which aimed to develop methods capable of automatically segmenting multiple sclerosis lesions in MRI scans.

Abstract

This report summarizes the outcomes of the ICPR 2024 Competition on Multiple Sclerosis Lesion Segmentation (MSLesSeg). The competition aimed to develop methods capable of automatically segmenting multiple sclerosis lesions in MRI scans. Participants were provided with a novel annotated dataset comprising a heterogeneous cohort of MS patients, featuring both baseline and follow-up MRI scans acquired at different hospitals. MSLesSeg focuses on developing algorithms that can independently segment multiple sclerosis lesions of an unexamined cohort of patients. This segmentation approach aims to overcome current benchmarks by eliminating user interaction and ensuring robust lesion detection at different timepoints, encouraging innovation and promoting methodological advances.

ICPR 2024 Competition on Multiple Sclerosis Lesion Segmentation -- Methods and Results

TL;DR

This report summarizes the outcomes of the ICPR 2024 Competition on Multiple Sclerosis Lesion Segmentation, which aimed to develop methods capable of automatically segmenting multiple sclerosis lesions in MRI scans.

Abstract

This report summarizes the outcomes of the ICPR 2024 Competition on Multiple Sclerosis Lesion Segmentation (MSLesSeg). The competition aimed to develop methods capable of automatically segmenting multiple sclerosis lesions in MRI scans. Participants were provided with a novel annotated dataset comprising a heterogeneous cohort of MS patients, featuring both baseline and follow-up MRI scans acquired at different hospitals. MSLesSeg focuses on developing algorithms that can independently segment multiple sclerosis lesions of an unexamined cohort of patients. This segmentation approach aims to overcome current benchmarks by eliminating user interaction and ensuring robust lesion detection at different timepoints, encouraging innovation and promoting methodological advances.

Paper Structure

This paper contains 12 sections, 1 equation, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Dataset
  3. MSLesSeg Dataset
  4. Dataset preprocessing
  5. Lesion delineation
  6. Competition Overview
  7. Competition Protocol and Duration
  8. Evaluation metrics
  9. Participants and Methods
  10. Competition Results
  11. Conclusion
  12. Acknowledgements

Figures (3)

  • Figure 1: Preprocessing steps: all brain MRI (T1-w, T2-w and FLAIR) were aligned to the standard $1 mm^3$ MNI space, then brain tissue was extracted.
  • Figure 2: Sample axial MRI images of the brain of an MS patient of the MSLesSeg Dataset in each modality of acquisition \ref{['subfig:flair']} FLAIR, \ref{['subfig:t1']} T1-weighted, \ref{['subfig:t2']} T2-weighted
  • Figure 3: Example of a (b) segmentation mask generated from the (a) FLAIR sequence. The images are presented in axial, coronal, and sagittal views.