Performance evaluation of brain tumor detection using watershed Segmentation and thresholding

Abstract

Brain tumors and cancers are life-threatening diseases to human beings and have been on the rise. If undetected, they are deadly.With the advent of advanced medical technology, it has becomeimperative to accurately spot and identify these tumors at the earliest.The manuscript aims at providing an accurate method to detectand segment brain tumors from MRI scans. This is achieved byimplementing watershed segmentation and threshold algorithm pairedwith pre and post image processing techniques. Apart from detectingthe tumor region, the proposed process also enhances image qualityby noise removal techniques and image quality improvement. Theseresults give promising values when verified using several evaluationparameters such as Structural Similarity Index Measure (SSIM),Feature Similarity Index Measure (FSIM) and Peak Signal-to-NoiseRatio (PSNR) and stand out among the other similar pre-existingalgorithms that they are compared with in a comparative analysis