In this project we perform image segmentation to find tumors on brain images. The neural network architecture chosen for this task is an Unet, model that was originally invented for biomedical uses and it is a popular choice when it comes to image segmentation. This kind of network is capable of working with relatively small data-sets while still being efficient.
The dataset used is the Br35H Brain Tumor Segmentation 2020, from Kaggle.
- Sarah Bellefroid
- Andrea Gómez
- Jade Rompen