ACQUA: Automated Cyanobacterial Quantification Algorithm for toxic filamentous genera using spline curves, pattern recognition and machine learning

Emanuele Gandola, Manuela Antonioli, Alessio Traficante, Simone Franceschini, Michele Scardi, Roberta Congestri

Research output: Contribution to journalArticle

Abstract

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.

Original languageEnglish
Pages (from-to)48-56
Number of pages9
JournalJournal of Microbiological Methods
Volume124
DOIs
Publication statusPublished - May 1 2016

    Fingerprint

Keywords

  • Algorithm
  • Bright field imaging
  • Cyanobacteria
  • Filamentous genera
  • Image analysis
  • Quantification

ASJC Scopus subject areas

  • Microbiology
  • Molecular Biology
  • Microbiology (medical)

Cite this