Related Experiment Video
Updated: Aug 8, 2026
Manual Segmentation of the Human Choroid Plexus Using Brain MRI
Published on: December 15, 2023
STREM: a robust multidimensional parametric method to segment MS lesions in MRI
L S Aït-Ali1, S Prima, P Hellier
1IRISA Campus Universitaire Beaulieu 35042 Rennes Cedex, France. laure.ait-ali@irisa.fr
Abstract:
We propose to segment Multiple Sclerosis (MS) lesions overtime in multidimensional Magnetic Resonance (MR) sequences. We use a robust algorithm that allows the segmentation of the abnormalities using the whole time series simultaneously and we propose an original rejection scheme for outliers. We validate our method using the BrainWeb simulator. To conclude, promising preliminary results on longitudinal multi-sequences of clinical data are shown.
Insights
This study introduces a new algorithm for tracking Multiple Sclerosis (MS) lesions over time using Magnetic Resonance (MR) imaging. The method accurately segments changes in MS lesions across multiple scans, showing promising results for clinical data.
Area of Science:
- Medical Imaging
- Neurology
- Biomedical Engineering
Background:
- Multiple Sclerosis (MS) is a chronic neurological disease.
- Accurate lesion segmentation in Magnetic Resonance (MR) imaging is crucial for monitoring MS progression.
- Existing methods may struggle with longitudinal data and outlier detection.
Purpose of the Study:
- To develop and validate a novel algorithm for segmenting Multiple Sclerosis (MS) lesions over time.
- To utilize the entire time series of multidimensional MR sequences for robust segmentation.
- To introduce an original outlier rejection scheme for improved accuracy.
Main Methods:
- A robust segmentation algorithm processing the whole time series simultaneously.
- An original outlier rejection scheme for enhanced data integrity.
- Validation using the BrainWeb simulator for quantitative assessment.
Main Results:
- The proposed algorithm demonstrates effective segmentation of MS lesions across time.
- The outlier rejection scheme improves the robustness of the segmentation process.
- Preliminary results on longitudinal multi-sequence clinical data are promising.
Conclusions:
- The developed method offers a promising approach for longitudinal MS lesion segmentation.
- This technique has the potential to improve the monitoring of MS disease progression.
- Further validation on diverse clinical datasets is warranted.
