What is the best data augmentation for 3D brain tumor segmentation?

TL;DR

This study evaluates various data augmentation techniques for 3D brain tumor segmentation, finding that brightness adjustment and elastic deformation are most effective, with combined methods offering no additional benefit.

Contribution

The paper systematically compares different data augmentation methods for 3D brain tumor segmentation, highlighting the most effective techniques and their combinations.

Findings

Brightness augmentation and elastic deformation yield the best performance.

Combining multiple augmentation techniques does not improve results.

Augmentation significantly enhances segmentation accuracy.

Abstract

Training segmentation networks requires large annotated datasets, which in medical imaging can be hard to obtain. Despite this fact, data augmentation has in our opinion not been fully explored for brain tumor segmentation. In this project we apply different types of data augmentation (flipping, rotation, scaling, brightness adjustment, elastic deformation) when training a standard 3D U-Net, and demonstrate that augmentation significantly improves the network's performance in many cases. Our conclusion is that brightness augmentation and elastic deformation work best, and that combinations of different augmentation techniques do not provide further improvement compared to only using one augmentation technique. Our code is available at https://github.com/mdciri/3D-augmentation-techniques.