Related Experiment Video
Updated: Jun 8, 2026
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
Published on: January 7, 2019
Segmentation of cortical MS lesions on MRI using automated laminar profile shape analysis
Christine L Tardif1, D Louis Collins, Simon F Eskildsen
1McConnell Brain Imaging Centre, Montreal Neurological Institute, Canada.
Abstract:
Cortical multiple sclerosis lesions are difficult to detect in magnetic resonance images due to poor contrast with surrounding grey matter, spatial variation in healthy grey matter and partial volume effects. We propose using an observer-independent laminar profile-based parcellation method to detect cortical lesions. Following cortical surface extraction, profiles are extended from the white matter surface to the grey matter surface. The cortex is parcellated according to profile intensity and shape features using a k-means classifier. The method is applied to a high-resolution quantitative magnetic resonance data set from a fixed post mortem multiple sclerosis brain, and validated using histology.
Insights
Detecting multiple sclerosis lesions in the brain cortex is challenging. A new observer-independent method uses laminar profiles to accurately identify these cortical lesions in magnetic resonance images.
Area of Science:
- Neuroimaging
- Medical image analysis
- Neurology
Background:
- Cortical multiple sclerosis (MS) lesions are difficult to detect using magnetic resonance imaging (MRI) due to low contrast with surrounding grey matter, anatomical variability, and partial volume effects.
- Accurate detection of MS lesions is crucial for understanding disease progression and evaluating treatment efficacy.
Purpose of the Study:
- To develop and validate an observer-independent, laminar profile-based parcellation method for detecting cortical lesions in multiple sclerosis.
- To improve the sensitivity and specificity of cortical lesion detection in high-resolution quantitative MRI data.
Main Methods:
- Extraction of the cortical surface from high-resolution quantitative MRI data.
- Generation of laminar profiles extending from the white matter to the grey matter surface.
- Parcellation of the cortex based on profile intensity and shape features using a k-means classifier.
Main Results:
- The proposed method was applied to a fixed post mortem multiple sclerosis brain dataset.
- The detected cortical lesions were validated using histological analysis, demonstrating the method's efficacy.
Conclusions:
- The observer-independent laminar profile-based parcellation method offers a promising approach for accurate detection of cortical multiple sclerosis lesions.
- This technique has the potential to enhance the diagnostic capabilities of MRI in multiple sclerosis research and clinical practice.
