A Comparative Study and Analysis of Contrast Enhancement Algorithms for MRI Brain Image Sequences

Brain tumor extraction is a challenging task in medical imaging research because its structure is complicated and can be diagnosed appropriately only by expert radiologists. Magnetic Resonance Imaging (MRI) is a commonly used modality to effectively diagnose, treat and monitor brain disease. Contrast enhancement is an important pre-processing step in which perceptual information is improved to obtain detailed information in the image. The motivation of this paper is to perform a comparative study and analysis of five different contrast enhancement algorithms such as Histogram Equalization which is a global contrast enhancement method, Adaptive histogram equalization perform local contrast enhancement by transforming each pixel based on the histogram of surrounding pixels. Morphological enhancement, Morphological filtering performed at single scale and at multiple scales of structuring element and to identify the suitability of a particular algorithm for each type of MR sequences for trans-axial orientation. Analysis was performed on the international database collected from Whole brain Atlas. The performance was evaluated using the standard measures Root Mean Square Error (RMSE), Peak Signal to Noise Ratio (PSNR), and Tenengrad Measure(TGD)