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.

Gandola, E., Antonioli, M., Traficante, A., Franceschini, S., Scardi, M., & Congestri, R. (2016). ACQUA: Automated Cyanobacterial Quantification Algorithm for toxic filamentous genera using spline curves, pattern recognition and machine learning. JOURNAL OF MICROBIOLOGICAL METHODS, 124, 48-56 [10.1016/j.mimet.2016.03.007].

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

GANDOLA, EMANUELE;ANTONIOLI, MANUELA;TRAFICANTE, ALESSIO;FRANCESCHINI, SIMONE;SCARDI, MICHELE;CONGESTRI, ROBERTA
2016

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.
Pubblicato
Rilevanza internazionale
Articolo
Esperti anonimi
Settore BIO/01
Settore BIO/03 - Botanica Ambientale e Applicata
English
Algorithm; Bright field imaging; Cyanobacteria; Filamentous genera; Image analysis; Quantification; Algorithms; Automation; Cyanobacteria; Environmental Monitoring; Fresh Water; Italy; Machine Learning; Microscopy; Microbiology; Molecular Biology; Microbiology (medical)
www.elsevier.com/locate/jmicmeth
Gandola, E., Antonioli, M., Traficante, A., Franceschini, S., Scardi, M., & Congestri, R. (2016). ACQUA: Automated Cyanobacterial Quantification Algorithm for toxic filamentous genera using spline curves, pattern recognition and machine learning. JOURNAL OF MICROBIOLOGICAL METHODS, 124, 48-56 [10.1016/j.mimet.2016.03.007].
Gandola, E; Antonioli, M; Traficante, A; Franceschini, S; Scardi, M; Congestri, R
Articolo su rivista
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/2108/187112
Citazioni
  • ???jsp.display-item.citation.pmc??? 2
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 10
social impact