SS-3DCapsNet: Self-supervised 3D Capsule Networks for Medical Segmentation on Less Labeled Data
This work addresses medical image segmentation for healthcare applications, but it is incremental as it builds on existing capsule network and self-supervised learning methods.
The paper tackles the problem of volumetric medical image segmentation with limited labeled data by extending capsule networks with self-supervised pre-training, resulting in SS-3DCapsNet, which outperforms previous capsule networks and 3D-UNets on datasets like iSeg-2017, Hippocampus, and Cardiac.
Capsule network is a recent new deep network architecture that has been applied successfully for medical image segmentation tasks. This work extends capsule networks for volumetric medical image segmentation with self-supervised learning. To improve on the problem of weight initialization compared to previous capsule networks, we leverage self-supervised learning for capsule networks pre-training, where our pretext-task is optimized by self-reconstruction. Our capsule network, SS-3DCapsNet, has a UNet-based architecture with a 3D Capsule encoder and 3D CNNs decoder. Our experiments on multiple datasets including iSeg-2017, Hippocampus, and Cardiac demonstrate that our 3D capsule network with self-supervised pre-training considerably outperforms previous capsule networks and 3D-UNets.