In this article, we look into some essential aspects of convolutional neural networks (CNNs) with the focus on medical image segmentation. First, we discuss the CNN architecture, thereby highlighting the spatial origin of the data, voxel-wise classification and the receptive field. Second, we discuss the sampling of input-output pairs, thereby highlighting the interaction between voxel-wise classification, patch size and the receptive field. Finally, we give a historical overview of crucial changes to CNN architectures for classification and segmentation, giving insights in the relation between three pivotal CNN architectures: FCN, U-Net and DeepMedic.

翻译：在文章中,我们研究了神经神经网络(CNNs)的一些重要方面,重点是医学图像分割。首先,我们讨论了CNN结构,从而强调了数据的空间起源、Voxel-wise分类和可接受域。第二,我们讨论了投入-产出对子的抽样,从而强调了Voxel-wise分类、补丁大小和可接受域之间的互动。最后,我们从历史角度概述了CNN分类和分割结构的重要变化,对CNN三个枢纽结构(FCN、U-Net和Deep Medi Medic)之间的关系提出了见解。