Serre Nelson B C, Fendrych Matyáš
Department of Experimental Plant Biology, Faculty of Sciences, Charles University, Prague, Czech Republic.
Quant Plant Biol. 2022 May 24;3:e9. doi: 10.1017/qpb.2022.4. eCollection 2022.
The ability of plants to sense and orient their root growth towards gravity is studied in many laboratories. It is known that manual analysis of image data is subjected to human bias. Several semi-automated tools are available for analysing images from flatbed scanners, but there is no solution to automatically measure root bending angle over time for vertical-stage microscopy images. To address these problems, we developed ACORBA, which is an automated software that can measure root bending angle over time from vertical-stage microscope and flatbed scanner images. ACORBA also has a semi-automated mode for camera or stereomicroscope images. It represents a flexible approach based on both traditional image processing and deep machine learning segmentation to measure root angle progression over time. As the software is automated, it limits human interactions and is reproducible. ACORBA will support the plant biologist community by reducing labour and increasing reproducibility of image analysis of root gravitropism.
许多实验室都在研究植物感知重力并使根系朝着重力方向生长的能力。众所周知,对图像数据进行人工分析会受到人为偏差的影响。有几种半自动工具可用于分析平板扫描仪的图像,但对于垂直阶段显微镜图像,尚无自动测量随时间变化的根系弯曲角度的解决方案。为了解决这些问题,我们开发了ACORBA,这是一款自动化软件,可从垂直阶段显微镜和平板扫描仪图像中随时间测量根系弯曲角度。ACORBA还具有针对相机或体视显微镜图像的半自动模式。它代表了一种基于传统图像处理和深度机器学习分割的灵活方法,用于测量随时间变化的根角进展。由于该软件是自动化的,因此它限制了人为干预并且具有可重复性。ACORBA将通过减少劳动力并提高根系向重力性图像分析的可重复性来支持植物生物学界。