IEEE Trans Med Imaging. 2019 Nov;38(11):2596-2606. doi: 10.1109/TMI.2019.2905990. Epub 2019 Mar 22.
In this paper, we introduce and compare different approaches for incorporating shape prior information into neural network-based image segmentation. Specifically, we introduce the concept of template transformer networks, where a shape template is deformed to match the underlying structure of interest through an end-to-end trained spatial transformer network. This has the advantage of explicitly enforcing shape priors, and this is free of discretization artifacts by providing a soft partial volume segmentation. We also introduce a simple yet effective way of incorporating priors in the state-of-the-art pixel-wise binary classification methods such as fully convolutional networks and U-net. Here, the template shape is given as an additional input channel, incorporating this information significantly reduces false positives. We report results on synthetic data and sub-voxel segmentation of coronary lumen structures in cardiac computed tomography showing the benefit of incorporating priors in neural network-based image segmentation.
在本文中，我们介绍并比较了将形状先验信息纳入基于神经网络的图像分割的不同方法。具体来说，我们介绍了模板变形网络的概念，其中通过端到端训练的空间变形网络，将形状模板变形以匹配感兴趣的基础结构。这具有显式强制形状先验的优点，并且通过提供软部分体积分割来避免离散化伪影。我们还介绍了一种简单而有效的方法，可将先验信息纳入最先进的像素级二进制分类方法（例如全卷积网络和 U 形网络）中。在这里，模板形状被作为附加输入通道给出，将此信息纳入显著减少了假阳性。我们报告了在合成数据和心脏计算机断层扫描中的冠状动脉管腔结构的亚像素分割方面的结果，表明在基于神经网络的图像分割中纳入先验信息的益处。
