A Novel Brain Tumor Classification Model Using Machine Learning Techniques

The objective of this research work is to classify brain tumor images into 4 different classes by using Convolutional Neural Network (CNN) algorithm i.e. a deep learning method with VGG16 architecture. four are pituitary, glioma, meningioma, and no tumor. dataset used for publicly available MRI Image 7023 images. methodology followed in project includes data pre-processing, model building, evaluation. pre-processed resizing the 64x64 normalizing pixel values. architecture build CNN model, it trained on 10 epochs batch size 64. evaluated area under operating characteristic curve (AUC) metric receiver. results show that achieves an AUC 0.92 classifying classes. performs best meningioma 0.90, pituitary 0.91, glioma 0.93, 0.89. In conclusion, effective approach multiple high accuracy identifying types tumors, which could potentially aid early diagnosis treatment tumors.