Emerging deep learning-based methods have enabled great progress in automatic neuron segmentation from Electron Microscopy (EM) volumes. However, the success of existing methods is heavily reliant upon a large number of annotations that are often expensive and time-consuming to collect due to dense distributions and complex structures of neurons. If the required quantity of manual annotations for learning cannot be reached, these methods turn out to be fragile. To address this issue, in this article, we propose a two-stage, semi-supervised learning method for neuron segmentation to fully extract useful information from unlabeled data. First, we devise a proxy task to enable network pre-training by reconstructing original volumes from their perturbed counterparts. This pre-training strategy implicitly extracts meaningful information on neuron structures from unlabeled data to facilitate the next stage of learning. Second, we regularize the supervised learning process with the pixel-level prediction consistencies between unlabeled samples and their perturbed counterparts. This improves the generalizability of the learned model to adapt diverse data distributions in EM volumes, especially when the number of labels is limited. Extensive experiments on representative EM datasets demonstrate the superior performance of our reinforced consistency learning compared to supervised learning, i.e., up to 400% gain on the VOI metric with only a few available labels. This is on par with a model trained on ten times the amount of labeled data in a supervised manner. Code is available at https://github.com/weih527/SSNS-Net.

中文翻译：

---

通过强化一致性学习进行半监督神经元分割


新兴的基于深度学习的方法使得电子显微镜（EM）体积的自动神经元分割取得了巨大进展。然而，现有方法的成功很大程度上依赖于大量注释，由于神经元的密集分布和复杂结构，收集这些注释通常既昂贵又耗时。如果无法达到学习所需的手动注释数量，这些方法就会变得脆弱。为了解决这个问题，在本文中，我们提出了一种用于神经元分割的两阶段半监督学习方法，以从未标记的数据中充分提取有用的信息。首先，我们设计了一个代理任务，通过从受扰动的对应部分重建原始体积来实现网络预训练。这种预训练策略隐式地从未标记的数据中提取有关神经元结构的有意义的信息，以促进下一阶段的学习。其次，我们利用未标记样本与其扰动样本之间的像素级预测一致性来规范监督学习过程。这提高了学习模型的通用性，以适应 EM 卷中的不同数据分布，特别是当标签数量有限时。对代表性 EM 数据集进行的大量实验证明，与监督学习相比，我们的强化一致性学习具有卓越的性能，即仅使用少数可用标签，VOI 指标即可获得高达 400% 的增益。这与以监督方式训练十倍标记数据量的模型相当。代码可在 https://github.com/weih527/SSNS-Net 获取。