This project aims to classify brain tumors as either benign or malignant using a VGG-16 deep learning model. The model is trained on a dataset of brain MRI scans and is able to predict whether a given brain scan contains a tumor or not.
The dataset used for this project consists of MRI scans of the brain, with each scan labeled as either containing a tumor (labeled as "yes") or not containing a tumor (labeled as "no"). The scans are in the form of JPEG/PNG images.
The model used for this project is a VGG-16 model, a convolutional neural network (CNN) trained on the ImageNet dataset. The VGG-16 model is well-suited for image classification tasks and has been shown to perform well on a variety of image classification datasets.
The model is evaluated on the testing set using a variety of evaluation metrics, including accuracy, precision, recall, and F1 score. The confusion matrix is also plotted to visualize the model's performance.
The VGG-16 model was able to achieve good performance on the brain tumor classification task, with an accuracy of over 90% on the testing set. The model was able to effectively differentiate between benign and malignant tumors, as demonstrated by the high precision and recall scores.
No licence assigned.