Skip to content

MRI-based brain tumor classification using transfer learning, a custom lightweight CNN, saliency maps, and explainable AI (99% accuracy)

Notifications You must be signed in to change notification settings

ObayM/Brain-Tumor-Classification-

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 

Repository files navigation

Brain Tumor Classification

For the full details and a video demo of this project see my linkedin post

Contents

  • brain-tumor-classification.ipynb: end-to-end workflow from data loading to evaluation and visualization.

Dataset

The notebook is written for the Kaggle Brain Tumor MRI dataset with Training/ and Testing/ folders. Update the paths in the notebook if your data is stored elsewhere.

Expected structure:

brain-tumor-mri-dataset/
├── Training/
│   ├── glioma/
│   ├── meningioma/
│   ├── notumor/
│   └── pituitary/
└── Testing/
    ├── glioma/
    ├── meningioma/
    ├── notumor/
    └── pituitary/

Requirements

  • Python 3.8+
  • Jupyter Notebook
  • Core packages used in the notebook:
    • numpy, pandas
    • matplotlib, seaborn, plotly
    • scikit-learn
    • tensorflow (keras)
    • opencv-python, pillow
    • python-dotenv (optional)
    • google-generativeai (optional)

Usage

  1. Install dependencies in your environment.
  2. Open the notebook
  3. Update dataset paths if needed and run the cells in order.

About

MRI-based brain tumor classification using transfer learning, a custom lightweight CNN, saliency maps, and explainable AI (99% accuracy)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published