Skip to content

Detecting Brain Tumors in MRIs using a Convolutional Neural Network with Transfer Learning

License

Notifications You must be signed in to change notification settings

jarred13/brain_tumor_classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Brain Tumor Classification

Overview

This notebook detects tumors in brain MRI scans using a convolutional neural network with data augmentation and transfer learning. This notebook has 3 models: the first one is your standard CNN, the second model added data agumentation, and the third model added the pre-trained model VGG16. The first model had an accuracy of 86%, the final model had an accuracy of 98%. This notebook is hosted on Kaggle and can be found here: https://www.kaggle.com/code/jarredpriester/detecting-brain-tumors-vgg16-accuracy-98

Purpose of the Project

The purpose of this project is to learn how to apply a convolutional neural network to brain MRI scans and to learn how to improve a CNN model's performance.

What Did I Learn

I learned about data augmentation and pre-trained models. I learned how to start with a regular CNN model, add data augmentation, and add the pre-trained model.

Dataset Used

The dataset has 139 images of MRI brain scans. The dataset was found on Kaggle.

Files Used

archive(3).zip - dataset
detecting-brain-tumors-vgg16-accuracy-98.ipynb - Kaggle python notebook

Releases

No releases published

Packages

No packages published