nnU-Net for Brain Tumor Segmentation

TL;DR

This paper demonstrates how adapting nnU-Net with specific modifications and ensemble techniques achieves state-of-the-art brain tumor segmentation results in the BraTS 2020 challenge.

Contribution

The authors enhance nnU-Net with BraTS-specific modifications and ensemble strategies, leading to top-ranking segmentation performance.

Findings

Achieved first place in BraTS 2020 with high Dice scores.

Modified nnU-Net with data augmentation and postprocessing.

Ensemble approach outperformed baseline models.

Abstract

We apply nnU-Net to the segmentation task of the BraTS 2020 challenge. The unmodified nnU-Net baseline configuration already achieves a respectable result. By incorporating BraTS-specific modifications regarding postprocessing, region-based training, a more aggressive data augmentation as well as several minor modifications to the nnUNet pipeline we are able to improve its segmentation performance substantially. We furthermore re-implement the BraTS ranking scheme to determine which of our nnU-Net variants best fits the requirements imposed by it. Our final ensemble took the first place in the BraTS 2020 competition with Dice scores of 88.95, 85.06 and 82.03 and HD95 values of 8.498,17.337 and 17.805 for whole tumor, tumor core and enhancing tumor, respectively.