Multi-atlas parcellation (MAP) is carried out on a brain image by propagating and fusing labelled regions from brain atlases. Typical nonlinear registration-based label propagation is time-consuming and sensitive to inter-subject differences. Recently, deep learning parcellation (DLP) has been proposed to avoid nonlinear registration for better efficiency and robustness than MAP. However, most existing DLP methods neglect using brain atlases, which contain high-level information (e.g., manually labelled brain regions), to provide auxiliary features for improving the parcellation accuracy. In this paper, we propose a novel multi-atlas DLP method for brain parcellation. Our method is based on fully convolutional networks (FCN) and squeeze-and-excitation (SE) modules. It can automatically and adaptively select features from the most relevant brain atlases to guide parcellation. Moreover, our method is trained via a generative adversarial network (GAN), where a convolutional neural network (CNN) with multi-scale $l_{1}$ loss is used as the discriminator. Benefiting from brain atlases, our method outperforms MAP and state-of-the-art DLP methods on two public image datasets (LPBA40 and NIREP-NA0).

中文翻译：

---

使用挤压和激发全卷积网络进行多图集大脑分割

通过传播和融合来自大脑图谱的标记区域，在大脑图像上执行多图谱拆分（MAP）。典型的基于非线性配准的标签传播既耗时又对对象间差异敏感。近来，为了避免非线性配准，提出了深度学习分类法（DLP），以实现比MAP更好的效率和鲁棒性。但是，大多数现有的DLP方法都忽略了使用包含高级信息（例如，手动标记的大脑区域）的脑图谱来提供辅助功能以提高切碎的准确性。在本文中，我们提出了一种新颖的多图集DLP方法进行脑细胞分裂。我们的方法基于完全卷积网络（FCN）和挤压激励（SE）模块。它可以从最相关的大脑图集中自动适应性地选择特征，以指导切碎。此外，我们的方法是通过生成对抗网络（GAN）进行训练的，其中具有多尺度的卷积神经网络（CNN） $ l_ {1} $ 损失被用作判别器。得益于脑图谱，我们的方法在两个公共图像数据集（LPBA40和NIREP-NA0）上的表现优于MAP和最新的DLP方法。