We show dense voxel embeddings learned via deep metric learning can be employed to produce a highly accurate segmentation of neurons from 3D electron microscopy images. A "metric graph" on a set of edges between voxels is constructed from the dense voxel embeddings generated by a convolutional network. Partitioning the metric graph with long-range edges as repulsive constraints yields an initial segmentation with high precision, with substantial accuracy gain for very thin objects. The convolutional embedding net is reused without any modification to agglomerate the systematic splits caused by complex "self-contact" motifs. Our proposed method achieves state-of-the-art accuracy on the challenging problem of 3D neuron reconstruction from the brain images acquired by serial section electron microscopy. Our alternative, object-centered representation could be more generally useful for other computational tasks in automated neural circuit reconstruction.
翻译:我们展示了通过深层光学学习所学的密集 voxel 嵌入, 可用于从 3D 电子显微镜图像中产生高度精确的神经元分解。 在 voxel 之间的一组边缘上, 从一个卷变网络产生的稠密的 voxel 嵌入中构建了一个“ 度图 ” 。 将光图与长距离边缘分隔开来, 因为可厌恶性限制产生一个高度精确的初始分解, 非常薄的物体的精度获得相当的增益 。 循环嵌入网被再利用时, 并未对复杂的“ 自我接触” motifs 造成的系统分解作任何修改 。 我们建议的方法在3D 神经元重建的难题上, 实现了最先进的精确度, 也就是从序列段电子显微镜中获取的大脑图像中重建。 在自动神经电路重建中, 我们的替代的、 以物体为中心的表达方式可以更普遍地用于其他计算任务 。