Automated Brain Tumor Detection and Identification Using Image Processing and Probabilistic Neural Network Techniques Dina Aboul Dahab 1 , Samy S. A. Ghoniemy 2 , Gamal M. Selim 3 Dep. of Computer Engineering, Arab Academy for Science, Technology & Maritime Transport Cairo, Egypt 1 dina_aboul_dahab@hotmail.com 2 ghoniemy@cis.asu.edu.eg 3drgamal55@yahoo.com Abstract— In this paper, modified image segmentation techniques were applied on MRI scan images in order to detect brain tumors. Also in this paper, a modified Probabilistic Neural Network (PNN) model that is based on learning vector quantization (LVQ) with image and data analysis and manipulation techniques is proposed to carry out an automated brain tumor classification using MRI-scans. The assessment of the modified PNN classifier performance is measured in terms of the training performance, classification accuracies and computational time. The simulation results showed that the modified PNN gives rapid and accurate classification compared with the image processing and published conventional PNN techniques. Simulation results also showed that the proposed system out performs the corresponding PNN system presented in [30], and successfully handle the process of brain tumor classification in MRI image with 100% accuracy when the spread value is equal to 1. These results also claim that the proposed LVQ-based PNN system decreases the processing time to approximately 79% compared with the conventional PNN which makes it very promising in the field of in-vivo brain tumor detection and identification. Keywords— Probabilistic Neural Network, Edge detection, image segmentation, brain tumor detection and identification I. INTRODUCTION The National Cancer Institute (NCI) estimated that 22,070 new cases of brain and other central nervous system (CNS) cancers would be diagnosed in the United States in 2009. The American Brain Tumor Association (ABTA) clarifies this statistic further by estimating that 62,930 new cases of primary brain tumors would be diagnosed in 2010 [1-3]. Today, tools and methods to analyze tumors and their behaviour are becoming more prevalent. Clearly, efforts over the past century have yielded real advances; however, we have also come to realize that gains in survival must be enhanced by better diagnosis tools [1, 3]. Although we have yet to cure brain tumors, clear steps forward have been taken toward reaching this ultimate goal, more and more researchers have incorporated measures into clinical trials each advance injects hope to the team of caregivers and, more importantly, to those who live with this diagnosis [1-3]. Magnetic Resonance Imaging (MRI) is the state-of the-art medical imaging technology which allows cross sectional view of the body with unprecedented tissue contrast [4-5]. MRI is an effective tool that provides detailed information about the targeted brain tumor anatomy, which in turn enables effective diagnosis, treatment and monitoring of the disease. Its techniques have been optimized to provide measures of change within and around primary and metastatic brain tumors, including edema, deformation of volume and anatomic features within tumors, etc [6]. MRI provides a digital representation of tissue characteristic that can be obtained in any tissue plane. The images produced by an MRI scanner are best described as slices through the brain. MRI has the added advantage of being able to produce images which slice through the brain in both horizontal and vertical planes. This makes the MRI-scan images an ideal source for detecting; identifying and classifying the right infected regions of the brain. Most of the current conventional diagnosis techniques are based on human experience in interpreting the MRI-scan for judgment; certainly this increases the possibility to false detection and identification of the brain tumor. On the other hand, applying digital image processing ensures the quick and precise detection of the tumor [7]. One of the most effective techniques to extract information from complex medical images that has wide application in medical field is the segmentation process [5, 8]. The main objective of the image segmentation is to partition an image into mutually exclusive and exhausted regions such that each region of interest is spatially contiguous and the pixels within the region are homogeneous with respect to a predefined criterion. Widely used homogeneity criteria include values of intensity, texture, color, range, surface normal and surface curvatures. Color- based segmentation using K-means clustering for brain tumor detection has been proposed, in which better results were obtained using the developed algorithm than that in other edge detection algorithms [9]. A modified method was proposed that additionally takes into account the symmetry analysis and any significant prior information of the region of interest as well as the region area and edge information in the tumor location of pathological cases [10]. However, all of these research efforts pushed the limit of tumor detection accuracy, they have been based on edge detection and were employed to International Journal of Image Processing and Visual Communication ISSN 2319-1724 : Volume 1 , Issue 2 , October 2012 (Online) 1