Fig. 2: Base network architectures (left) and loss functions (right) used by the participants of the 2018 Decathlon challenge who provided full algorithmic information (n = 14 teams). | Nature Communications

Fig. 2: Base network architectures (left) and loss functions (right) used by the participants of the 2018 Decathlon challenge who provided full algorithmic information (n = 14 teams).

From: The Medical Segmentation Decathlon

Fig. 2

Network architectures: DeepMedic—Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation45, QuickNAT—Fully Convolutional Network for Quick and Accurate Segmentation of Neuroanatomy44, ResNet—Deep Residual Learning for Image Recognition15, U-Net—Convolutional Networks for Biomedical Image Segmentation11, V-Net—Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation43. DSC Dice Similarity Coefficient.

Back to article page