Abstract
Multiple sclerosis (MS) is a neurological disease affecting the brain and spinal cord, which leads to several troubles such as numbness, memory problems, pain, fatigue and even paralysis. Magnetic resonance imaging (MRI) is commonly used for MS diagnosis. However, low-contrast MRI images need a contrast enhancement process to ameliorate the quality of images for better visualization of lesions. Nevertheless, most existing contrast enhancement methods add diverse types of alteration such as intensity modification, wash-out, noise and intensity saturation. Also, these methods change image brightness level. This paper presents a novel method for contrast improvement of low-contrast images referred to as BPDFHE-DWT-SVD. It is based on brightness preserving dynamic fuzzy histogram equalization (BPDFHE) and singular value decomposition with discrete wavelet transform (SVD-DWT) techniques. The aim behind the combination of those techniques is to enhance low-contrast images with preservation of the brightness level and without adding artifacts which is very important in lesion detection. To evaluate the performance of the new proposed method against existing contrast enhancement methods, different evaluation metrics are considered. Qualitative and quantitative analyses proved that the proposed method outperformed conventional methods. It enhances low-contrast MRI images with protection of brightness level and edge details from any distortion.