SS-3DCapsNet: Self-supervised 3D Capsule Networks for Medical Segmentation on Less Labeled Data
Abstract
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.
Cite
@article{arxiv.2201.05905,
title = {SS-3DCapsNet: Self-supervised 3D Capsule Networks for Medical Segmentation on Less Labeled Data},
author = {Minh Tran and Loi Ly and Binh-Son Hua and Ngan Le},
journal= {arXiv preprint arXiv:2201.05905},
year = {2022}
}
Comments
Accepted to ISBI 2022