A Deep Network for Joint Registration and Parcellation of Cortical Surfaces.
A Deep Network for Joint Registration and Parcellation of Cortical Surfaces.
复制标题
一种用于关节配准和皮质表面分割的深度网络。
DOI：
10.1007/978-3-030-87202-1_17
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Li, Gang
中科院分区：
文献类型：
--
作者：
Zhao, Fenqiang;Wu, Zhengwang;Wang, Li;Lin, Weili;Xia, Shunren;Li, Gang
皮层表面定位和包裹是神经成像分析的两个重要步骤。传统上，它们是作为两个任务独立执行的，忽略了这两个密切相关的任务之间的内在联系。本质上，这两个任务都依赖于有意义的皮层特征表示，因此它们可以通过学习共享的有用的皮层特征来联合优化。为此，我们提出了一个关节皮质表面配准和分割的深度学习框架。具体来说，我们的方法利用皮质表面的球形拓扑结构，并使用球形网络作为共享编码器，首先学习两个任务的共享特征。然后，我们分别训练两个特定于任务的解码器进行注册和打包。我们进一步利用它们之间更明确的联系，结合新的分割图相似度损失来强制区域的边界一致性，从而为注册任务提供额外的监督。相反，分块网络训练也受益于配准，它通过将一个具有手动分块映射的表面扭曲到另一个表面来提供大量的增强数据，特别是当只有少数手动标记的表面可用时。在超过600个皮质表面的数据集上的实验表明，我们的方法在分割和配准精度（在单独训练的网络上）上取得了很大的进步，并且能够使用更少的标记数据训练高质量的分割和配准模型。
Cortical surface registration and parcellation are two essential steps in neuroimaging analysis. Conventionally, they are performed independently as two tasks, ignoring the inherent connections of these two closely-related tasks. Essentially, both tasks rely on meaningful cortical feature representations, so they can be jointly optimized by learning shared useful cortical features. To this end, we propose a deep learning framework for joint cortical surface registration and parcellation. Specifically, our approach leverages the spherical topology of cortical surfaces and uses a spherical network as the shared encoder to first learn shared features for both tasks. Then we train two task-specific decoders for registration and parcellation, respectively. We further exploit the more explicit connection between them by incorporating the novel parcellation map similarity loss to enforce the boundary consistency of regions, thereby providing extra supervision for the registration task. Conversely, parcellation network training also benefits from the registration, which provides a large amount of augmented data by warping one surface with manual parcellation map to another surface, especially when only few manually-labeled surfaces are available. Experiments on a dataset with more than 600 cortical surfaces show that our approach achieves large improvements on both parcellation and registration accuracy (over separately trained networks) and enables training high-quality parcellation and registration models using much fewer labeled data.