UNI-EM: An Environment for Deep Neural Network-Based Automated Segmentation of Neuronal Electron Microscopic Images
UNI-EM: An Environment for Deep Neural Network-Based Automated Segmentation of Neuronal Electron Microscopic Images
复制标题
DOI：
10.1038/s41598-019-55431-0
复制
发表时间：
2019-12-19
影响因子：
4.6
通讯作者：
Ishii, Shin
中科院分区：
文献类型：
--
作者：
Urakubo, Hidetoshi;Bullmann, Torsten;Ishii, Shin
最近，在微连接组学领域中已经迅速扩展，其目标是从二维（2D）电子显微镜（EM）图像的堆叠中三维（3D）重建神经元网络。由于深度卷积神经网络（CNN）能够实现自动图像分割，3D重建的空间尺度迅速增加。几个研究团队已经开发了自己的基于CNN分割的软件管道。然而，这种管道的复杂性使得它们的使用即使对于计算机专家也是困难的，并且对于非专家是不可能的。在这项研究中，我们开发了一种新的软件程序，称为UNI-EM，用于基于CNN的2D和3D分割。UNI-EM是一个基于CNN的EM图像分割的软件集合，包括地面真值生成，训练，推理，后处理，校对和可视化。UNI-EM包含一组2D CNN，即，U-Net、ResNet、HighwayNet和DenseNet。我们进一步包装了洪水填充网络（FFNs）作为代表性的基于3D CNN的神经元分割算法。已知2D和3D-CNN展示了最先进的分割性能。然后，我们提供了两个示例工作流程：使用2D CNN的线粒体分割和使用FFN的神经元分割。通过遵循这些示例工作流程，用户可以从基于CNN的分割中受益，而无需具备Python编程或CNN框架的知识。
Recently, there has been rapid expansion in the field of micro-connectomics, which targets the three-dimensional (3D) reconstruction of neuronal networks from stacks of two-dimensional (2D) electron microscopy (EM) images. The spatial scale of the 3D reconstruction increases rapidly owing to deep convolutional neural networks (CNNs) that enable automated image segmentation. Several research teams have developed their own software pipelines for CNN-based segmentation. However, the complexity of such pipelines makes their use difficult even for computer experts and impossible for non-experts. In this study, we developed a new software program, called UNI-EM, for 2D and 3D CNN-based segmentation. UNI-EM is a software collection for CNN-based EM image segmentation, including ground truth generation, training, inference, postprocessing, proofreading, and visualization. UNI-EM incorporates a set of 2D CNNs, i.e., U-Net, ResNet, HighwayNet, and DenseNet. We further wrapped flood-filling networks (FFNs) as a representative 3D CNN-based neuron segmentation algorithm. The 2D- and 3D-CNNs are known to demonstrate state-of-the-art level segmentation performance. We then provided two example workflows: mitochondria segmentation using a 2D CNN and neuron segmentation using FFNs. By following these example workflows, users can benefit from CNN-based segmentation without possessing knowledge of Python programming or CNN frameworks.