nnU-Net for Brain Tumor Segmentation

By Fabian Isensee, Paul F. Jaeger, Peter M. Full, Philipp Vollmuth, Klaus Hermann Maier-Hein. BrainLes@MICCAI, 2020

440 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Neurology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/30b6a2331e5436467c8cb448ac8169b364ab449f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Bo Wang
2. Jun Ma
3. Feifei Li
4. Vishwesh Nath
5. Dong Yang
6. Holger R. Roth
7. Ali Hatamizadeh
8. Daguang Xu

In Neurology

1. Vishwesh Nath
2. Dong Yang
3. Holger R. Roth
4. Feifei Li
5. Jun Ma
6. Bo Wang
7. Ali Hatamizadeh
8. Daguang Xu

In Radiology, Nuclear Medicine and Imaging

1. Dong Yang
2. Holger R. Roth
3. Daguang Xu
4. Vishal M. Patel
5. Jeya Maria Jose Valanarasu
6. Yin Dai
7. Yifan Gao

Citations in the corpus

• Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images (2022, background): “We have compared the performance of Swin UNETR in our internal cross validation split against the winning methologies of previous years such as SegRes-Net [31], nnU-Net [19] and TransBTS [39].”
• U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation (2024, background): “Furthermore, U-Mamba’s design inherently supports integration with advanced techniques, such as strong data augmentations for small datasets, loss functions for highly imbalanced targets, and region-based training for nested objects [23].”