Optimized U-Net for Brain Tumor Segmentation
We propose an optimized U-Net architecture for a brain segmentation task in the BraTS21 Challenge. To find the model architecture and learning schedule we ran 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 and number of convolutional channels. Our solution was the winner of the challenge validation phase, with the normalized statistical ranking score of 0.267 and mean Dice score of 0.8855
READ FULL TEXT