Bryozoans are becoming an increasingly popular study system in macroevolutionary, ecological, and paleobiological research. Members of this colonial invertebrate phylum display an exceptional degree of division of labor in the form of specialized modules, which allows for the inference of individual allocation of resources to reproduction, defense, and growth using simple morphometric tools. However, morphometric characterizations of bryozoans are notoriously labored. Here, we introduce DeepBryo, a web application for deep-learning-based morphometric characterization of cheilostome bryozoans. DeepBryo is capable of detecting objects belonging to six classes and outputting 14 morphological shape measurements for each object. The users can visualize the predictions, check for errors, and directly filter model outputs on the web browser. DeepBryo was trained and validated on a total of 72,412 structures in six different object classes from images of 109 different families of cheilostome bryozoans. The model shows high (> 0.8) recall and precision for zooid-level structures. Its misclassification rate is low (~ 4%) and largely concentrated in two object classes. The model's estimated structure-level area, height, and width measurements are statistically indistinguishable from those obtained via manual annotation. DeepBryo reduces the person-hours required for characterizing individual colonies to less than 1% of the time required for manual annotation. Our results indicate that DeepBryo enables cost-, labor,- and time-efficient morphometric characterization of cheilostome bryozoans. DeepBryo can greatly increase the scale of macroevolutionary, ecological, taxonomic, and paleobiological analyses, as well as the accessibility of deep-learning tools for this emerging model system.

中文翻译：

---

DeepBryo：一款用于 AI 辅助唇口动物苔藓虫形态测量表征的网络应用程序

苔藓虫正在成为宏观进化、生态和古生物学研究中越来越受欢迎的研究系统。这个群体无脊椎动物门的成员以专门模块的形式表现出特殊程度的劳动分工，这使得可以使用简单的形态测量工具推断出个体对繁殖、防御和生长的资源分配。然而，苔藓虫的形态学表征是出了名的费力。在这里，我们介绍 DeepBryo，一个基于深度学习的唇口动物苔藓虫形态测量表征的 Web 应用程序。DeepBryo 能够检测属于 6 个类别的物体，并为每个物体输出 14 个形态形状测量值。用户可以在网络浏览器上可视化预测、检查错误并直接过滤模型输出。DeepBryo 在来自 109 个不同唇口动物苔藓虫家族图像的 6 个不同对象类别中的总共 72,412 个结构上进行了训练和验证。该模型对类动物级结构显示出高 (> 0.8) 的召回率和精度。其错误分类率较低（约 4%），并且主要集中在两个对象类中。该模型估计的结构水平面积、高度和宽度测量值在统计上与通过手动注释获得的测量结果没有区别。DeepBryo 将表征单个菌落所需的工时减少到手动注释所需时间的 1% 以下。我们的结果表明，DeepBryo 能够对口口动物苔藓虫进行具有成本、劳动力和时间效率的形态测定表征。DeepBryo 可以大大增加宏观进化、生态、分类、