# Cascaded V-Net using ROI masks for brain tumor segmentation

## TL;DR

This paper introduces a cascaded V-Net architecture utilizing ROI masks to improve brain tumor segmentation by focusing training on relevant regions, effectively handling class imbalance.

## Contribution

It proposes a novel cascaded V-Net model with ROI masks for targeted training in brain tumor segmentation, enhancing accuracy on skewed data.

## Key findings

- Effective segmentation on BraTS2017 dataset
- Improved focus on tumor regions reduces false negatives
- Demonstrates robustness in highly skewed class distributions

## Abstract

In this work we approach the brain tumor segmentation problem with a cascade of two CNNs inspired in the V-Net architecture \cite{VNet}, reformulating residual connections and making use of ROI masks to constrain the networks to train only on relevant voxels. This architecture allows dense training on problems with highly skewed class distributions, such as brain tumor segmentation, by focusing training only on the vecinity of the tumor area. We report results on BraTS2017 Training and Validation sets.