3D-UCaps: 3D Capsules Unet for Volumetric Image Segmentation
This work addresses medical image segmentation for healthcare applications, but it is incremental as it builds on existing Capsule and CNN methods.
The authors tackled the problem of volumetric medical image segmentation by proposing 3D-UCaps, a hybrid network combining 3D Capsule blocks and 3D CNNs, which outperformed previous Capsule networks and 3D-Unets on datasets like iSeg-2017, LUNA16, Hippocampus, and Cardiac.
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.