Department of Organismal Biology and Anatomy, The University of Chicago, 1027 E 57th St, Chicago, IL 60637, USA
Department of Ecology and Evolutionary Biology, Brown University, 80 Waterman Street, Providence, RI 02912, USA.
J Exp Biol. 2020 Sep 4;223(Pt 17):jeb226720. doi: 10.1242/jeb.226720.
Marker tracking is a major bottleneck in studies involving X-ray reconstruction of moving morphology (XROMM). Here, we tested whether DeepLabCut, a new deep learning package built for markerless tracking, could be applied to videoradiographic data to improve data processing throughput. Our novel workflow integrates XMALab, the existing XROMM marker tracking software, and DeepLabCut while retaining each program's utility. XMALab is used for generating training datasets, error correction and 3D reconstruction, whereas the majority of marker tracking is transferred to DeepLabCut for automatic batch processing. In the two case studies that involved an behavior, our workflow achieved a 6 to 13-fold increase in data throughput. In the third case study, which involved an acyclic, post-mortem manipulation, DeepLabCut struggled to generalize to the range of novel poses and did not surpass the throughput of XMALab alone. Deployed in the proper context, this new workflow facilitates large scale XROMM studies that were previously precluded by software constraints.
标记跟踪是涉及运动形态的 X 射线重建（XROMM）研究的主要瓶颈。在这里，我们测试了 DeepLabCut 是否可以应用于视频射线照相数据，以提高数据处理吞吐量，DeepLabCut 是一个新的深度学习软件包，用于无标记跟踪。我们的新工作流程集成了 XMALab，现有的 XROMM 标记跟踪软件和 DeepLabCut，同时保留每个程序的实用性。XMALab 用于生成训练数据集、错误校正和 3D 重建，而大多数标记跟踪则转移到 DeepLabCut 进行自动批处理。在涉及行为的两个案例研究中，我们的工作流程使数据吞吐量增加了 6 到 13 倍。在第三个案例研究中，涉及非循环、死后操作，DeepLabCut 难以推广到新的姿势范围，并且没有超过 XMALab 单独的吞吐量。在适当的情况下部署，这种新的工作流程可以促进以前由于软件限制而无法进行的大规模 XROMM 研究。
