Liu Yi, Kolagunda Abhishek, Treible Wayne, Nedo Alex, Caplan Jeffrey, Kambhamettu Chandra
University of Delaware, 18 Amstel Ave, Newark, DE, USA 19716.
Conf Comput Vis Pattern Recognit Workshops. 2019;2019:125-133. doi: 10.1109/cvprw.2019.00021.
Filamentous structures play an important role in biological systems. Extracting individual filaments is fundamental for analyzing and quantifying related biological processes. However, segmenting filamentous structures at an instance level is hampered by their complex architecture, uniform appearance, and image quality. In this paper, we introduce an orientation-aware neural network, which contains six orientation-associated branches. Each branch detects filaments with specific range of orientations, thus separating them at junctions, and turning intersections to overpasses. A terminus pairing algorithm is also proposed to regroup filaments from different branches, and achieve individual filaments extraction. We create a synthetic dataset to train our network, and annotate real full resolution microscopy images of microtubules to test our approach. Our experiments have shown that our proposed method outperforms most existing approaches for filaments extraction. We also show that our approach works on other similar structures with a road network dataset.
丝状结构在生物系统中发挥着重要作用。提取单个丝状结构是分析和量化相关生物过程的基础。然而，丝状结构在实例层面的分割受到其复杂的结构、均匀的外观和图像质量的阻碍。在本文中，我们引入了一种方向感知神经网络，它包含六个与方向相关的分支。每个分支检测具有特定方向范围的丝状结构，从而在交叉点处将它们分开，并将交叉点转变为立交桥。还提出了一种末端配对算法，用于对来自不同分支的丝状结构进行重新组合，以实现单个丝状结构的提取。我们创建了一个合成数据集来训练我们的网络，并对微管的真实全分辨率显微镜图像进行注释以测试我们的方法。我们的实验表明，我们提出的方法在丝状结构提取方面优于大多数现有方法。我们还表明，我们的方法在道路网络数据集上对其他类似结构也有效。
