Novel Deep Neural Network Model For Brain Tumor and Breast Cancer Classification to promote E-Health

Abstract

Neural network models are a big segment of machine learning which is highly useful to segregate based on its feature. They have the immense capability to extract and learn the features. Predicting cancer well before the patient shows symptoms can help avoid deaths drastically. Since deep learning can do the task of feature extraction, we designed a DL model which can classify various cancer images into cancerous or non-cancerous. The proposed model was separately trained over breast cancer (BC) and brain tumor (BT) dataset and has achieved an overall accuracy of 0.95 and 0.72 respectively. For this reason, we compared the proposed model with Resnet-50, VGG-19 and VGG-16. The proposed model achieved 0.95 accuracy on brain tumor dataset. Where as vgg16 obtained 0.94 accuracy and resnet-50 obtained only 0.81 accuracy respectively on brain tumor dataset. Clearly, our model surpassed the rest not only in terms of accuracy but also speed. The proposed model performed far better than Resnet-50.