Optimized U-Net for Brain Tumor Segmentation
This work addresses brain tumor segmentation for medical imaging applications, but it is incremental as it builds on the established U-Net framework with optimizations.
The authors tackled brain tumor segmentation in the BraTS21 challenge by optimizing a U-Net architecture through extensive ablation studies on components like loss functions and attention mechanisms, achieving first place in validation and third place in test phases.
We propose an optimized U-Net architecture for a brain tumor segmentation task in the BraTS21 challenge. To find the optimal model architecture and the learning schedule, we have run an extensive ablation study to test: deep supervision loss, Focal loss, decoder attention, drop block, and residual connections. Additionally, we have searched for the optimal depth of the U-Net encoder, number of convolutional channels and post-processing strategy. Our method won the validation phase and took third place in the test phase. We have open-sourced the code to reproduce our BraTS21 submission at the NVIDIA Deep Learning Examples GitHub Repository.