A review of microscopic cell imaging and neural network recognition for synergistic cyanobacteria identification and enumeration

Abstract

Real-time cyanobacteria/algal monitoring is a valuable tool for early detection of harmful algal blooms, water treatment efficacy evaluation, and assists tailored water quality risk assessments by considering taxonomy and cell counts. This review evaluates and proposes a synergistic approach using neural network image recognition and microscopic imaging devices by first evaluating published literature for both imaging microscopes and image recognition. Quantitative phase imaging was considered the most promising of the investigated imaging techniques due to the provision of enhanced information relative to alternatives. This information provides significant value to image recognition neural networks, such as the convolutional neural networks discussed within this review. Considering published literature, a cyanobacteria monitoring system and corresponding image processing workflow using in situ sample collection buoys and on-shore sample processing was proposed. This system can be implemented using commercially available equipment to facilitate accurate, real-time water quality monitoring. Graphical abstract

Tracking the frequency of phytoplankton clonal lineages using multispectral image flow cytometry and neural networks

“…It is not equipped with lasers, has a higher magnification, and when combined with an automated sampling robot (e.g. OC‐300; Vaughan et al., 2022) it could also efficiently collect sufficient training data. An advantage is the reduced cost of purchase and its widespread use in phytoplankton studies, contributing to an extensive collection of phytoplankton images (Dashkova et al., 2017; Vaughan et al., 2022).…”

“…It is not equipped with lasers, has a higher magnification, and when combined with an automated sampling robot (e.g. OC-300;Vaughan et al, 2022) it could also efficiently collect sufficient training data.…”

“…automated sampling process, which creates the possibility for live tracking of frequency shifts within populations and communities.Another promising imaging technique is quantitative phase imaging, which could detect small morphological differences between phenotypes. Compared to the Imagestream MK II and Flowcam this method has a significantly lower imaging rates(Vaughan et al, 2022). It remains to be tested how other technologies can be used to acquire training data for NN for differentiate between clonal lineages.…”

Chronological development of functional fluorophores for bio-imaging

“…Over time, numerous reviews, book chapters, and scholarly works have meticulously summarized the advancements in this field, particularly concerning cellular imaging. [93][94][95][96][97][98][99][100][101][102][103] Thus, this review concentrates exclusively on the latest developments in fluorescent core scaffolds and their advanced applications.…”

Using FlowCam and molecular techniques to assess the diversity of Cyanobacteria species in water used for food production

“…When these conditions are favourable, cyanobacteria form blooms and increase biomass accumulation and scum 3 . As secondary metabolites, they produce and release a variety of compounds known as cyanotoxins that pose threat to human health 2,4,5 . The risk to human health comes after direct or indirect contact with water or food contaminated with these compounds 3,[6][7][8] .…”