Semi-Automated Segmentation of Multiple Sclerosis Lesions in Brain MRI using Texture Analysis

Reliable segmentation of multiple sclerosis lesions in magnetic resonance brain imaging is important for at least three types of practical applications: pharmaceutical trials, decision making for drug treatment or surgery, and patient follow-up. Manual segmentation of the MS lesions in brain MRI by well qualified experts is usually preferred. However, manual segmentation is hard to reproduce and can be time consuming in the presence of large volumes of MRI data. On the other hand, automated segmentation methods are significantly faster and yield reproducible results. However, these automated methods generally produce segmentation results that agree only partially with the ground truth segmentation provided by the experts. They also suffer from miss-classification errors, especially false-negative miss-classification where true lesions are left undetected, which is a grave concern from a medical point of view. In this work, we propose a semi-automated MS lesion detection system that combines the knowledge of the expert with the computational capacity to produce faster and more reliable MS segmentation results. In particular, the user selects coarse regions of interest (ROIs) that may potentially contain MS lesions. Then any MS lesions within the provided ROI's are then detected and segmented based on texture analysis. The method is applied on real MRI data and the results are qualitatively compared to a ground truth, which is manually segmented by a human expert