This project focuses on the detection of brain tumors using deep learning techniques. It employs a Convolutional Neural Network (CNN) model built using the TensorFlow Keras framework. The aim of the model is to accurately diagnos the tumor in the brain based on four classes that is

1. Glioma
2. Meningioma
3. No Tumor
4. Pituitary

Brain tumors are a serious medical condition that require timely detection and treatment. Manual analysis of MRI scans for tumor detection is a time-consuming and error-prone task. This project addresses the challenge of automating the detection process using deep learning techniques to improve the efficiency and accuracy of tumor identification.

The objective of this project is to develop a CNN model that can accurately classify brain MRI images into four classes of tumor including a healthy brain. By automating the detection process, we aim to provide a reliable tool for assisting medical professionals in diagnosing brain tumors more efficiently.

• Python version: 3.9 or above
• Important libraries: TensorFlow, Keras, NumPy, Matplotlib

To run the code, ensure you have the following libraries installed:

• TensorFlow: pip install tensorflow
• Keras: pip install keras
• NumPy: pip install numpy
• Matplotlib: pip install matplotlib

├── EDA (Exploratory Data Analysis)
│ └── EDA.md
├── Model
│ └── Brain_Tumor_detection_Corrected.ipynb
└── Deployment
│ └── Web_Deployment_Code.ipynb`

Contributions to this project are welcome. If you have any suggestions, improvements, or bug fixes, feel free to open an issue or submit a pull request.

The project MRI Brain Tumor Diagnosis system is developed by Akshit Srivastava. You can contact the author at [email protected]

1. Kaggle: Used for accessing and exploring the brain tumor dataset.
2. SIIM-PCR-Pneumothorax-segmentation, Brain Tumor Detection by MohamedAliHabib: Referred to various open-source repositories for guidance and inspiration during the project development.
3. GeeksforGeeks-VGG16 Model : Used to learn about VGG-16 CNN model and to correctly implement it.