Optimal Filter Design for Multiple Sclerosis Lesions Segmentation from Regions of Interest in Brain MRI

In this paper, we propose an optimal filter design strategy for the purpose of detecting and segmenting MS lesions in prescribed regions of interest within brain MRI data. 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 methods generally produce segmentation results that agree only partially with the ground truth segmentation provided by the expert. 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 (ROI's) that enclose potential MS lesions and a sufficient background of healthy white matter tissues. Having this two-class classification problem, we propose a feature extraction method based on optimal filter design that aim for producing output texture features corresponding to the MS lesions and healthy tissues background which are maximally separable. If this is achieved, the two output features may be easily separated using simple thresholding operations. 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