A Skip-Connected 3D DenseNet Networks with Adversarial Training for Volumetric Segmentation

In this paper, we propose a novel end-to-end adversarial training on volumetric brain segmentation architecture that allows to enforce long-range spatial label contiguity and label consistency. The proposed network consists of two networks: generator and discriminator. The generator network allows to take volumetric image as input and provides a volumetric probability map for each tissue. Then, the discriminator network learns to differentiate ground-truth maps from the probability maps of generator network. We design a discriminator in a fully convolutional manner to differentiate the predicted probability maps from the ground-truth segmentation distribution with the consideration of the spatial information on voxel level, which makes it difficult to learn the discriminator. In order to overcome it, the proposed discriminator provides a 3D confidence map which indicates corresponding regions of the probability maps close to the ground-truth. Based on the 3D confidence map information, the generator network will refine prediction output close to the ground-truth maps in a high-order structure.