We present a method combining affinity prediction with region agglomeration, which improves significantly upon the state of the art of neuron segmentation from electron microscopy (EM) in accuracy and scalability. Our method consists of a 3D U-Net, trained to predict affinities between voxels, followed by iterative region agglomeration. We train using a structured loss based on Malis, encouraging topologically correct segmentations obtained from affinity thresholding. Our extension consists of two parts: First, we present a quasi-linear method to compute the loss gradient, improving over the original quadratic algorithm. Second, we compute the gradient in two separate passes to avoid spurious gradient contributions in early training stages. Our predictions are accurate enough that simple learning-free percentile-based agglomeration outperforms more involved methods used earlier on inferior predictions. We present results on three diverse EM datasets, achieving relative improvements over previous results of 27, 15, and 250 percent. Our findings suggest that a single method can be applied to both nearly isotropic block-face EM data and anisotropic serial sectioned EM data. The runtime of our method scales linearly with the size of the volume and achieves a throughput of ~2.6 seconds per megavoxel, qualifying our method for the processing of very large datasets.

中文翻译：

---

基于结构化损失的大规模图像分割用于连接组重建的深度学习


我们提出了一种将亲和力预测与区域聚集相结合的方法，该方法在准确性和可扩展性方面显着提高了电子显微镜（EM）神经元分割的现有技术水平。我们的方法由 3D U-Net 组成，经过训练来预测体素之间的亲和力，然后进行迭代区域聚集。我们使用基于 Malis 的结构化损失进行训练，鼓励从亲和力阈值处理中获得拓扑正确的分割。我们的扩展由两部分组成：首先，我们提出了一种准线性方法来计算损失梯度，改进了原始的二次算法。其次，我们在两个单独的过程中计算梯度，以避免在早期训练阶段产生虚假梯度。我们的预测足够准确，以至于简单的无学习的基于百分位数的聚合优于之前在较差预测中使用的更复杂的方法。我们展示了三个不同 EM 数据集的结果，与之前的结果相比，实现了 27%、15% 和 250% 的相对改进。我们的研究结果表明，单一方法可以应用于近各向同性块面电磁数据和各向异性串行截面电磁数据。我们方法的运行时间与体积大小呈线性关系，每兆体素的吞吐量约为 2.6 秒，使我们的方法能够处理非常大的数据集。