论文标题
SS-3DCAPSNET：自我监督的3D胶囊网络用于较少标记的数据
SS-3DCapsNet: Self-supervised 3D Capsule Networks for Medical Segmentation on Less Labeled Data
论文作者
论文摘要
胶囊网络是一种最新的新深网架构，已成功应用于医疗图像分割任务。这项工作扩展了胶囊网络，以通过自我监督的学习来进行体积的医学图像细分。为了改善与以前的胶囊网络相比的重量初始化问题，我们利用胶囊网络预训练的自我监督学习，在这种学习中，我们的借口任务是通过自我重构优化的。我们的胶囊网络SS-3DCAPSNET具有带有3D胶囊编码器和3D CNNS解码器的基于UNET的体系结构。我们在包括ISEG-2017，Hippocampus和Cardiac在内的多个数据集上进行的实验表明，我们的3D胶囊网络具有自我监督的预训练的前一个胶囊网络和3D-UNET的表现相当大。
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.
