The extreme complexity of mammalian brains requires a comprehensive deconstruction of neuroanatomical structures. Scientists normally use a brain stereotactic atlas to determine the locations of neurons and neuronal circuits. However, different brain images are normally not naturally aligned even when they are imaged with the same setup, let alone under the differing resolutions and dataset sizes used in mesoscopic imaging. As a result, it is difficult to achieve high-throughput automatic registration without manual intervention. Here, we propose a deep learning-based registration method called DeepMapi to predict a deformation field used to register mesoscopic optical images to an atlas. We use a self-feedback strategy to address the problem of imbalanced training sets (sampling at a fixed step size in nonuniform brains of structures and deformations) and use a dual-hierarchical network to capture the large and small deformations. By comparing DeepMapi with other registration methods, we demonstrate its superiority over a set of ground truth images, including both optical and MRI images. DeepMapi achieves fully automatic registration of mesoscopic micro-optical images, even macroscopic MRI datasets, in minutes, with an accuracy comparable to those of manual annotations by anatomists.

哺乳动物大脑的极端复杂性要求对神经解剖结构进行全面的解构。科学家通常使用大脑立体定位图谱来确定神经元和神经元回路的位置。但是，即使使用相同的设置对不同的大脑图像进行成像，通常它们也不自然对齐，更不用说在介观成像中使用的不同分辨率和数据集大小了。结果，在没有人工干预的情况下很难实现高吞吐量的自动注册。在这里，我们提出一种称为DeepMapi的基于深度学习的配准方法，以预测用于将介观光学图像配准给地图集的变形场。我们使用一种自反馈策略来解决训练集不平衡的问题（在结构和变形的非均匀大脑中以固定步长采样），并使用双层次网络来捕获大小变形。通过将DeepMapi与其他配准方法进行比较，我们证明了它比一组地面真实图像（包括光学图像和MRI图像）优越。DeepMapi可以在数分钟内实现对介观微光学图像甚至宏观MRI数据集的全自动配准，其准确性可与解剖学家手动注解的准确性相媲美。