• Tamilaruvi
• Umanandhiini

Brain tumor classification is a challenging task in the field of medical image processing. Early detection brain tumor can increase patient’s survival rate. Various machine learning techniques has been proposed to classify the tumor region areas that are segmented from brain images as benign and malignant. A brain tumor detection method based on Deep Neural Network (DNN) was introduced. In this method, the collected Magnetic Resonance Imaging (MRI) images were segmented by Fuzzy C-Means clustering technique. Then, the features were extracted from the segmented images using Discrete Wavelet Transform (DWT) technique and the dimensionality of the features was reduced by applying Principal Component Analysis (PCA). Finally, DNN was applied for brain tumor detection. In order to improve the brain tumor detection accuracy, DNN with Convolutional Neural Network (DNN-CNN) is introduced in this paper for brain tumor detection. In DNN-CNN, the convolutional layers, pooling layer and fully connected layer are used to refine the brain tumor image classification. The convolutional layer aims to learn feature representations of the input image. The pooling layer reduces the number of connection between convolutional layers. The fully-connected layers take all neurons in the previous layer and connect them to every single neuron of current layer to generate global semantic information. The CNN is used to learn the feature representation and these features are used in the hidden layer of DNN and the image classification output is generated in the output layer of DNN. The experiments are conducted in different MRI images to prove the efficiency of CNN-DNN based brain tumor detection in terms of accuracy, precision, recall and f-measure.

Brain tumor detection, Deep Neural Network, Convolutional Neural Network, Fuzzy C Means, Discrete Wavelet Transform

"Classification using Deep Neural Network and Convolutional Neural Network for Brain Tumors", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.264-269, June 2019, Available :http://www.jetir.org/papers/JETIR1907K40.pdf

"Classification using Deep Neural Network and Convolutional Neural Network for Brain Tumors", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp264-269, June 2019, Available at : http://www.jetir.org/papers/JETIR1907K40.pdf