Brain-Tumor-Classification

Faculty incharge:

• Dr. TAN Wee Kek
• Dr. LEK Hsiang Hui
• Dr. Amirhassan Monajemi
  
• Mr. Shantanu Pandey

  Project Abstract :-
  The aim of our project is to develop a Deep Learning model which will be able to classify among different types of benign and malignant tumors using MRI imaging.​

  
  Dependencies:- NumPy​, Pandas​, Tensorflow​,Keras​, Os​, Matplotlib​, Scikit Library (All these dependencies need to be installed before running the project.) ​
  Data preprocessing:- For data preprocessing, we used various techniques like rescaling, cropping, augmentation and normalize the data.

  Total Number of images:

  • Training: 2870
  • Test: 394

    Deep learning models used:-

    1. VGG-16
    2. DENSENet

    Testing data: 70%, Training data: 30%

    Steps to run it:

    1. To run the project, first clone the repo.

    2. Run brain-tumour-densenet.ipynb file: This file containings the data preprocessing part and DenseNet model.

    3. Run brain-tumour-vgg16.ipynb file: This file containings the data preprocessing part and VGG16 model.

    4. To directly download the models, download the files with ".h5":

    • mine_model_weights.h5
    • model_1_densenet.h5

      Group Members :

      • Ayush Bachuwar
      • Dhathri Meda
      • Mrinmoy Kumar Das
      • Rishy Parasar
      • Shikhar Gupta
      • Sughosh Deshpande