Gandola Emanuele, Antonioli Manuela, Traficante Alessio, Franceschini Simone, Scardi Michele, Congestri Roberta
University of Rome Tor Vergata, Department of Biology, via della Ricerca Scientifica 1, 00133 Rome, Italy; Department of Mathematics, University of Rome Tor Vergata, via della Ricerca Scientifica 1, 00133 Rome, Italy.
University of Rome Tor Vergata, Department of Biology, via della Ricerca Scientifica 1, 00133 Rome, Italy; National Institute for Infectious Diseases 'L. Spallanzani' IRCCS, Via Portuense, 292 00149 Rome, Italy; Freiburg Institute for Advanced Studies (FRIAS), University of Freiburg, Freiburg 79104, Germany.
J Microbiol Methods. 2016 May;124:48-56. doi: 10.1016/j.mimet.2016.03.007. Epub 2016 Mar 21.
Toxigenic cyanobacteria are one of the main health risks associated with water resources worldwide, as their toxins can affect humans and fauna exposed via drinking water, aquaculture and recreation. Microscopy monitoring of cyanobacteria in water bodies and massive growth systems is a routine operation for cell abundance and growth estimation. Here we present ACQUA (Automated Cyanobacterial Quantification Algorithm), a new fully automated image analysis method designed for filamentous genera in Bright field microscopy. A pre-processing algorithm has been developed to highlight filaments of interest from background signals due to other phytoplankton and dust. A spline-fitting algorithm has been designed to recombine interrupted and crossing filaments in order to perform accurate morphometric analysis and to extract the surface pattern information of highlighted objects. In addition, 17 specific pattern indicators have been developed and used as input data for a machine-learning algorithm dedicated to the recognition between five widespread toxic or potentially toxic filamentous genera in freshwater: Aphanizomenon, Cylindrospermopsis, Dolichospermum, Limnothrix and Planktothrix. The method was validated using freshwater samples from three Italian volcanic lakes comparing automated vs. manual results. ACQUA proved to be a fast and accurate tool to rapidly assess freshwater quality and to characterize cyanobacterial assemblages in aquatic environments.
产毒蓝藻是全球水资源面临的主要健康风险之一，因为它们产生的毒素会影响通过饮用水、水产养殖和娱乐活动接触到的人类和动物。对水体和大规模生长系统中的蓝藻进行显微镜监测是估计细胞丰度和生长情况的常规操作。在此，我们介绍ACQUA（自动蓝藻定量算法），这是一种全新的全自动图像分析方法，专为明场显微镜下的丝状蓝藻属设计。我们开发了一种预处理算法，以从其他浮游植物和灰尘产生的背景信号中突出感兴趣的丝状蓝藻。设计了一种样条拟合算法，用于重组中断和交叉的丝状蓝藻，以便进行精确的形态计量分析，并提取突出显示对象的表面模式信息。此外，还开发了17种特定的模式指标，并将其用作机器学习算法的输入数据，该算法专门用于识别淡水中五种广泛存在的有毒或潜在有毒丝状蓝藻属：水华束丝藻、柱孢藻、链球藻、泥生颤藻和浮游颤藻。通过比较意大利三个火山湖的淡水样本的自动分析结果和人工分析结果，对该方法进行了验证。结果证明，ACQUA是一种快速准确的工具，可用于快速评估淡水质量并表征水生环境中的蓝藻群落。
