论文标题
3D-UCAPS：3D胶囊UNET用于体积图像分割
3D-UCaps: 3D Capsules Unet for Volumetric Image Segmentation
论文作者
论文摘要
到目前为止，通过卷积神经网络（CNN），医疗图像分割已经取得了令人鼓舞的结果。但是，可以说的是，在传统的CNN中，其合并层倾向于丢弃重要信息，例如位置。此外，CNN对旋转和仿射转化很敏感。胶囊网络是一种提出数据效率的网络设计，旨在通过动态路由和卷积步伐替换池层来克服此类局限性，旨在保留零件整体关系。胶囊网络在图像识别和自然语言处理方面表现出色，但是医疗图像分割的应用，尤其是体积图像分段，这是有限的。在这项工作中，我们提出了3D-UCAPS，这是一个基于3D体素的胶囊网络，用于医疗图像分割。我们通过设计具有两个途径的网络来构建胶囊的概念：第一个途径由3D胶囊块编码，而第二个途径由3D CNNS块解码。因此，3D-UCAPS，因此继承了两个胶囊网络的优点，以保留空间关系和CNN以学习视觉表示。我们在各种数据集上进行了实验，以证明包括ISEG-2017，LUNA16，Hippocampus和Cardiac在内的3D-UCAPS的鲁棒性，在这里我们的方法优于先前的胶囊网络和3D-UNET。
Medical image segmentation has been so far achieving promising results with Convolutional Neural Networks (CNNs). However, it is arguable that in traditional CNNs, its pooling layer tends to discard important information such as positions. Moreover, CNNs are sensitive to rotation and affine transformation. Capsule network is a data-efficient network design proposed to overcome such limitations by replacing pooling layers with dynamic routing and convolutional strides, which aims to preserve the part-whole relationships. Capsule network has shown a great performance in image recognition and natural language processing, but applications for medical image segmentation, particularly volumetric image segmentation, has been limited. In this work, we propose 3D-UCaps, a 3D voxel-based Capsule network for medical volumetric image segmentation. We build the concept of capsules into a CNN by designing a network with two pathways: the first pathway is encoded by 3D Capsule blocks, whereas the second pathway is decoded by 3D CNNs blocks. 3D-UCaps, therefore inherits the merits from both Capsule network to preserve the spatial relationship and CNNs to learn visual representation. We conducted experiments on various datasets to demonstrate the robustness of 3D-UCaps including iSeg-2017, LUNA16, Hippocampus, and Cardiac, where our method outperforms previous Capsule networks and 3D-Unets.
