Brain Tumor Detection with Biologically Inspired Watershed Segmentation and Classification Based on Feed-Forward Neural Network (FNN)

Abstract

Image segmentation plays a very vital role in gathering information by dividing the images into various segments to achieve the meaningful information, whereas the image segmentation gives importance in the area of medical imaging to analyze and process the anatomical structures of various internal organs of the body with high resolution images that are captured during medical examination. Medical experts will go through the reports which give the various reasons for the existence of the disease. Brain which is considered the important part of the body so the detection and the segmentation of brain tumors will be considered as the major task of the medical field whereas they are using the high resolution images in the form of MRI reports. The MRI images are considered as the vital source for the identification of tumors in the brain. The accuracy of the segmentation and identification of the tumor depends upon the experience of the radiologist and also it is time consuming task. Therefore the watershed segmentation is performed for the extraction of the tumor region and the features are extracted for the classification, whereas the classification is carried out by the Feed-Forward Neural Network (FNN). The experimental results are evaluated based on the performance and the quality analysis, Furthermore the results give the accuracy of 91.2% in the training model and 71.8% as the testing during the classification process.