Skip to content

Brain Tumor Detection is a deep learning-based project that detects brain tumors in MRI scans using Convolutional Neural Networks (CNNs) and TensorFlow. It processes MRI images, classifies them as Tumor or No Tumor and achieves high accuracy. Built with Python, OpenCV, NumPy and Pandas.

License

Notifications You must be signed in to change notification settings

khushiiagrawal/BrainTumor-Detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Brain Tumor Analysis📈

A deep learning-based project to detect the presence of a Brain Tumor in MRI images using TensorFlow and data science libraries.

📌Features

  • Uses Convolutional Neural Networks (CNNs) for tumor classification
  • Processes and visualizes MRI scanned images
  • Utilizes TensorFlow, NumPy, Pandas, OpenCV, and Matplotlib
  • Successfully detects tumor and non-tumor

🛠️Technologies Used

  • Python
  • TensorFlow
  • NumPy
  • Pandas
  • OpenCV
  • Matplotlib

📂Notebook and Dataset

Link of the dataset used for Training the model: Dataset

Open the notebook: Brain Tumor Analysis Notebook

📊 Model Training & Evaluation

  • Utilizes CNNs for image classification
  • Achieves 75%-85% accuracy
  • Evaluated using metrics like accuracy, precision and recall

🧠 Sample Prediction

Screenshot 2025-03-22 at 1 50 23 AM Screenshot 2025-03-22 at 1 49 35 AM

☑️Result

  • The model correctly identified MRI scans with and without tumors.
  • Successfully tested on brain MRI images with accurate classification.

License

This project is licensed under the MIT License.

About

Brain Tumor Detection is a deep learning-based project that detects brain tumors in MRI scans using Convolutional Neural Networks (CNNs) and TensorFlow. It processes MRI images, classifies them as Tumor or No Tumor and achieves high accuracy. Built with Python, OpenCV, NumPy and Pandas.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published