Brain Tumor Classification Using Deep Neural Network

Abstract

Brain tumors are a type of tumor with a high mortality rate. Since multifocal-looking tumors in the brain can resemble multicentric gliomas or gliomatosis, accurate detection of the tumor is required during the treatment process. The similarity of neurological and radiological findings also complicates the classification of these tumors. Fast and accurate classification is important for brain tumors. Computer aided diagnostic systems and deep neural network architectures can be used in the diagnosis of multicentric gliomas and multiple lesions. In this study, the Deep Neural Network classification model with Synthetic Minority Over-sampling Technique pre-processing was used on the Visually Accessible Rembrandt Images dataset. The proposed model for the classification of brain tumors consists of 1319 trainable parameters and the proposed method has achieved 95.0% accuracy rate. Precision, Recall, F1-measure values are 95.4%, 95.0% and 94.9% respectively. The proposed decision support system can be used to give an idea to doctors in the detection of glioma type tumors.

Enhancing Phishing URL Detection Accuracy in Software-Defined Networks (SDNs) through Feature Selection and Machine Learning Techniques

“…Moving on to the next layer, a flattening operation is employed to convert the feature maps into a vector form. During the classification phase, this flattened input vector is passed through the network to generate numerical outputs in each output neuron [47]. Essentially, this process transforms the feature representation into a single extended layer that originates from the convolutional layer.…”