1. Morphometrics has become an indispensable component of the statistical analysis of size and shape variation in biological structures. Morphometric data have traditionally been gathered through low‐throughput manual landmark annotation, which represents a significant bottleneck for morphometric‐based phenomics. Here we propose a machine‐learning‐based high‐throughput pipeline to collect high‐dimensional morphometric data in two‐dimensional images of semi‐rigid biological structures.
2. The proposed framework has four main strengths. First, it allows for dense phenotyping with minimal impact on specimens. Second, it presents landmarking accuracy comparable to manual annotators, when applied to standardized datasets. Third, it performs data collection at speeds several orders of magnitude higher than manual annotators. And finally, it is of general applicability (i.e. not tied to a specific study system).
3. State‐of‐the‐art validation procedures show that the method achieves low error levels when applied to three morphometric datasets of increasing complexity, with error varying from 0.57% to 2.2% of the structure's length in the automated placement of landmarks. As a benchmark for the speed of the entire automated landmarking pipeline, our framework places 23 landmarks on 13,686 objects (zooids) detected in 1,684 pictures of fossil bryozoans in 3.12 min using a personal computer.
4. The proposed machine‐learning‐based phenotyping pipeline can greatly increase the scale, reproducibility and speed of data collection within biological research. To aid the use of the framework, we have developed a file conversion algorithm that can be used to leverage current morphometric datasets for automation, allowing the entire procedure, from model training all the way to prediction, to be performed in a matter of hours.

中文翻译：

---

ML-morph：一种快速，准确和通用的方法，用于图像中生物结构的自动检测和标记

1. 形态计量学已成为生物结构大小和形状变化的统计分析中不可或缺的组成部分。传统上，形态计量学数据是通过低吞吐量的手动地标标注来收集的，这代表了基于形态计量学的形态学的重大瓶颈。在这里，我们提出了一种基于机器学习的高通量管道，以收集半刚性生物结构的二维图像中的高维形态计量数据。
2. 拟议的框架具有四个主要优点。首先，它可以进行密集的表型分析，并且对标本的影响最小。其次，当应用于标准化数据集时，它提供的地标精度可媲美手动注释器。第三，它以比手动注释器高几个数量级的速度执行数据收集。最后，它具有普遍适用性（即与特定的学习系统无关）。
3. 最新的验证程序表明，该方法应用于三个复杂度不断提高的形态计量数据集时，在自动放置地标时，其误差在结构长度的0.57％至2.2％之间变化，可实现较低的误差水平。作为整个自动化地标管线速度的基准，我们的框架使用个人计算机在23个地标上放置了3.686分钟的13686个物体（类动物），这些物体在1684个化石支原体的图片中检测到。
4. 拟议中的基于机器学习的表型化流程可以大大提高生物学研究中数据收集的规模，可重复性和速度。为了帮助使用该框架，我们开发了一种文件转换算法，该算法可用于利用当前的形态计量数据集进行自动化，从而使整个过程（从模型训练一直到预测）都可以在数小时内完成。