Brain Tumor Detection Using Pytorch Model

This is a brain tumor classification model created using transfer learning with resnet-50 model to classify the brain tumor MRI images into 17 classes. The model has achieved an accuracy of 97% on test data.

Steps to Run the Website

• Download the github folder to you local server using following command:

  • git clone https://github.com/anu81785/brain_tumor_classification_into_17_classes.git

• Change the directory to downloaded folder:

  • cd brain_tumor_classification_into_17_classes

• Create a virtual environment using python:

  • python -m venv env_name

• Activate the virtual environment:

  • source /path/to/venv/bin/activate

• Now download all the required packages inside this virtual environment using following command:

  • pip install -r requirements.txt

• Start the following commands to apply the migrations and runserver

  • python manage.py migrate

  • python manage.py runserver

  

• Open the url http://127.0.0.1:8000 in your browser

  

• Upload the brain MRI image for which you want to detect the tumor type

  

Link to Dataset (MRI images of brain) from kaggle

• https://www.kaggle.com/datasets/fernando2rad/brain-tumor-mri-images-17-classes

Plots for Loss and Accuracy for Training and Validation Set

Confusion Matrix for Test Data