Classification of MRI Brain Images Using Neural Network

There are many difficult problems in the field of pattern recognition. These problems are the focus of much active research in order to find efficient approaches to address them. We have tried to address the problem of classification MRI brain images by creating a robust and more accurate classifier which can act as an expert assistant to medical practitioners. 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. MRI plays an important role in assessing pathological conditions of the ankle, foot and brain. In proposed methodology three supervised neural networks has been used: Back Propagation Algorithm (BPA), Learning Vector Quantization (LVQ) and Radial Basis Function (RBF). The features of magnetic resonance images have been reduced, using principal component analysis (PCA), to the more essential features. The proposed technique has been carried out over a larger database as compare to any previous work and is more robust and effective. KeywordsMagnetic Resonance Image(MRI) , Principal Component Analysis (PCA), Radial Basis Function (RBF), Back Propagation (BP), Learning Vector Quantization (LVQ), Multi Layer Neural Network . INTRODUCTION Magnetic resonance imaging (MRI) is often the medical imaging method of choice when soft tissue delineation is necessary. This is especially true for any attempt to classify brain tissues [1]. The most important advantage of MR imaging is that it is noninvasive technique [2]. The use of computer technology in medical decision support is now widespread and pervasive across a wide range of medical area, such as cancer research, gastroenterology, hart diseases, brain tumors etc. [3, 4]. Fully automatic normal and diseased human brain classification from magnetic resonance images (MRI) is of great importance for research and clinical studies. Recent work [2, 5] has shown that classification of human brain in magnetic resonance (MR) images is possible via supervised techniques such as artificial neural networks and support vector machine (SVM) [2], and unsupervised classification techniques unsupervised such as self organization map (SOM) [2] and fuzzy c-means combined with feature extraction techniques [5]. Other supervised classification techniques, such as k-nearest neighbors (k-NN) also group pixels based on their similarities in each feature image [1, 6, 7, 8] can be used to classify the normal/pathological T2-wieghted MRI images. We used supervised machine learning algorithms (ANN and k-NN) to obtain the classification of images under two categories, either normal or abnormal. Usually an image of size p × q pixels is represented by a vector in p.q dimensional space. In practice, however, these (p.q) -dimensional spaces are too large to allow robust and fast object recognition. A common way to attempt to resolve this problem is to use dimension reduction techniques. In order to reduce the feature vector dimension and increase the discriminative power, the principal component analysis (PCA) has been used. In these approaches, the 2-dimensional image is considered as a vector, by concatenating each row or column of the image. Each classifier has its own representation of basis vectors of a high dimensional face vector space. The dimension is reduced by projecting the face vector to the basis vectors, and is used as the feature representation of each images. [8],[15] The Back Propagation (BP) algorithm looks for the minimum of the error function in weight space using the method of gradient descent. Properly trained back propagation networks tend to give reasonable answers when presented with inputs that they have never seen. Typically, a new input leads to an output similar to the correct output for input vectors used in training that are similar to the new input being presented. This generalization property makes it possible to train a network on a representative set of input/target pairs and get good results without training the network on all possible input/output pairs. [3] The RBF network performs similar function mapping with the BP, however its structure and function are much different. An RBF is a local network that is trained in a supervised manner contrasts with the BP network that is a global network. A BP performs a global mapping, meaning all inputs cause an output, while an RBF performs a local mapping, meaning only inputs near a receptive field produce activation. The LVQ network has two layers: a layer of input neurons, and a layer of output neurons. The Lalit P. Bhaiya, Virendra Kumar Verma / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 www.ijera.com Vol. 2, Issue 5, SeptemberOctober 2012, pp.751-756 752 | P a g e network is given by prototypes W=(w(i),...,w(n)). It changes the weights of the network in order to classify the data correctly. For each data point, the prototype (neuron) that is closest to it is determined (called the winner neuron). The weights of the connections to this neuron are then adapted, i.e. made closer if it correctly classifies the data point or made less similar if it incorrectly classifies it. [16] We performed classification of MRI brain images on a database of 192 images which contains 107 normal images and 85 pathological images. We experimented with three different sets of training and testing taken from clump of images. In first case s 98 (55 normal and 43 pathological) images have been used for training purpose and remaining 94 images for testing. In second case we swapped the testing and training database and in third case we used 90(50 normal and 40 pathological) images for training and remaining 102 images for testing. For feature vectors generation, images are preprocessed by PCA which has been described shortly below. PCA Preprocessing PCA can be used to approximate the original data with lower dimensional feature vectors. The basic approach is to compute the eigenvectors of the covariance matrix of the original data, and approximate it by a linear combination of the leading eigenvectors. By using PCA procedure, the test image can be identified by first, projecting the image onto the eigen face space to obtain the corresponding set of weights, and then comparing with the set of weights of the faces in the training set. [2],[5] The problem of low-dimensional feature representation can be stated as follows: Let X= (x1 ,x2,..., xi,..., xn) represents the n × N data matrix, where each xi is a face vector of dimension n, concatenated from a p × q face image. Here n represents the total number of pixels (p.q) in the face image and N is the number of face images in the training set. The PCA can be considered as a linear transformation (1) from the original image vector to a projection feature vector, i.e.