Title : Multiple sclerosis diagnosis based on medical image processing
Abstract:
Multiple sclerosis (MS) is one of the most serious neurological diseases. It is the most frequent reason of non-traumatic disability among young adults. MS lesions cause several disorders such as mobility, vision, cognitive, and memory problems. Indeed, early detection of lesions provides an accurate MS diagnosis. Consequently, and with the adequate treatment, clinicians will be able to deal effectively with the disease and reduce the number of relapses. Magnetic resonance imaging (MRI) is the gold standard imaging tool for early diagnosis of MS patients. However, low contrast MRI images can hide important objects in the image such lesions. Medical image processing could be the solution for this issue. In this context, we have proposed new automated contrast enhancement (CE) methods to ameliorate the low contrast of MRI images for a better enhancement and visibility of MS lesions. The first developed method is called BDS. It is based on Brightness Preserving Dynamic Fuzzy Histogram Equalization (BPDFHE) and Singular Value Decomposition with Discrete Wavelet Transform (SVD-DWT) techniques. BDS is dedicated to improve the low quality of MRI images. The second method called MBDS is an improved version of BDS, wherein, we have proposed a new technique for computing the correction factor. Indeed, with the use of the new correction factor, the contrast has greatly enhanced. MBDS is dedicated for enhancement of very low contrast MRI images.
Experimental results proved the effectiveness of both proposed methods in improving low contrast of MRI images with preservation of brightness level and edge information from degradation. These features are essential in CE approaches for a better lesion recognition. Moreover, performances of both proposed BDS and MBDS algorithms exceeded conventional CE methods. They increase the overall contrast of the image with preservation of edge details, leading to a natural looking of the image with sharper structures and no added artifacts. In addition, the optimized technique MBDS improves considerably the contrast of very low-contrast images and provides better visualization of small details including MS lesions. When applied to various multiple sclerosis MRI images (T1-w, T2-w, and T2-Flair of the brain and the spinal cord), MS lesions present in both the brain and the spinal cord in enhanced images had become sharper than those in the original image with well-defined edges. Proposed methods BDS and MBDS provide a better visualization and delineation of MS lesions. Therefore, they would be a proficient diagnostic tool for MS diagnosis.
