DeepProjection: Specific and robust projection of curved 2D tissue sheets from 3D microscopy using deep learning

The efficient extraction of image data from curved tissue sheets embedded
in volumetric imaging data remains a serious and unsolved problem in
quantitative studies of embryogenesis. Here we present DeepProjection
(DP), a trainable projection algorithm based on deep learning. This
algorithm is trained on user-generated training data to locally classify
the 3D stack content and rapidly and robustly predict binary masks
containing the target content, e.g., tissue boundaries, while masking
highly fluorescent out-of-plane artifacts. A projection of the masked 3D
stack then yields background-free 2D images with undistorted fluorescence
intensity values. The binary masks can further be applied to other
fluorescent channels or to extract the local tissue curvature. DP is
designed as a first processing step than can be followed, for example, by
segmentation to track cell fate. We apply DP to follow the dynamic
movements of 2D-tissue sheets during dorsal closure in Drosophila embryos
and of the periderm layer in the elongating Danio embryo. DeepProjection
is available as fully documented Python package.

从嵌入于体积成像数据（volumetric imaging data）中的弯曲组织薄片中高效提取图像数据，仍是胚胎发生（embryogenesis）定量研究领域尚未解决的重大难题。为此，我们提出了深度投影算法（DeepProjection，简称DP），这是一种基于深度学习的可训练投影算法。该算法基于用户生成的训练数据集进行训练，可对三维图像堆栈的内容进行局部分类，并能快速且稳健地预测出包含目标内容的二值掩码（binary masks）——例如组织边界，同时屏蔽高荧光的平面外伪影。对掩码后的三维图像堆栈进行投影后，即可得到背景纯净且荧光强度值无畸变的二维图像。该二值掩码还可进一步应用于其他荧光通道（fluorescent channels），或用于提取局部组织的曲率信息。深度投影算法被设计为首个预处理步骤，后续可衔接诸如细胞分割以追踪细胞命运等任务。我们将DP应用于追踪果蝇（Drosophila）胚胎背闭合过程中二维组织薄片的动态运动，以及伸长阶段斑马鱼（Danio）胚胎周皮层的动态变化。深度投影算法现已作为带有完整文档说明的Python软件包（Python package）对外发布。