Brain Tumor Detector

• 

  Hugging Face

• 

  Creation Pipepline

• 

  Model Accu Plot

• 

  Github Page

Inspiration

Cancer is disease that claims about 10-15 millions lives per year, however numbers usually don't affect us till the time it isn't a close one who gets targeted by it. Last year, I lost my maternal grandfather to cancer, if his cyst was detected earlier he would be still be today with us

What it does

My project takes in as input an image of a MRI scan and tells the possibility for brain tumor and its type(glioma, meningioma, pituitary and no tumor).

How we built it

I trained an Efficient Net Model on kaggle's chest MRI Scan (dataset)[https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset] by Nickparvar, at first the accuracy wasn't good so I added a hint of data augmentation and a scheduler which improved my models performance.

Challenges we ran into

Finding the right dataset for the model since too big would mean its trains slowly as I don't have access to GPUs while too small might be too biased
Hosting on Hugging Face
Learning Gradio
Which model works best

Accomplishments that we're proud of

A training accuracy of about 97% and a testing accuracy of 92% so hopefully people with possible brain tumor might get early detection and hence early treatment.
Model is deployed for all to leverage if needed

What we learned

To host on Hugging Face
How to tackle overfitting and underfitting

What's next for Brain Tumor Detector

Testing on bigger datasets
Changing and improving the base model

Built With

• canva
• computer-vision
• deep-learning
• gradio
• huggingface
• machine-learning
• python
• pytorch