Lemna minor Bioassay Evaluation Using Computer Image Analysis

Abstract

This article deals with using computer vision in the evaluation of the Lemna minor bioassay. According to the conventional method, the growth of Lemna minor mass is determined from the number of leaves grown. In this work, instead of counting individual leaves, we propose measuring the area occupied by the leaves using computer vision and compare the new approach with the conventional one. The bioassay is performed according to the ISO 20079 standard as a 168 h growth inhibition test; the aim of the experiment was to quantify the negative effects on the vegetative growth using two parameters—the number of leaves and the area occupied by the leaves. The method based on image processing was faster and also more precise since it enabled us to detect the negative effect of the tested substance on leave size, not only on their number. It can be concluded that the toxic effect has shown to be more significant when considering the leaves area rather than the number of leaves. Moreover, mistakes caused by human factor during leaves counting are eliminated using the computer vision based method.

A Machine Learning Method to Assess Growth Patterns in Plants of the Family Lemnaceae

“…Results show that the newly proposed method is faster and as reliable as the other methods previously used to measure the growth rate of Lemnaceae [31][32]. Our experiment did not compare results with a fresh or dry weight of plants nevertheless, this was not the main aim of our work, and we considered reliable the correlation between weight and frond area [32].…”

“…The newly proposed approach of using a machine learning system has numerous advantages and fewer disadvantages than previously proposed methods based on image analysis [27]. In fact, with the initial setup of a photo booth box, researchers can rely on coherent methods that discard human input in the analysis process.…”

“…This approach can increase confidence in experimental results and speed up image analysis techniques by offloading the image analysis process to a machine [26]. Due to scientists' strong interest in this family of plants, we shared the view that it is mandatory to standardise analysis methods [27] and decided to contribute to achieving such a goal.…”

Flowering and Seed Production across the Lemnaceae

“…To facilitate rapid and accurate measurement of duckweed growth in toxicity tests, there has been a recent shift from frond counts and fresh or dry weight measurements to image analysis software, which can measure total area, plant health, and possibly flowering. The company Lemnatec sells commercial imaging chambers, with software packages, while researchers have applied the Aphelion software package [ 25 ], the NI vision Assistant software [ 26 ] in data analysis pipelines, or the free software Image J, with manual assistance in selecting green surface area (P. Fourounjian, unpublished) to take non-destructive measurements of biomass.…”

Water Quality Engineering and Wastewater Treatment

“…One of the water species used to assess ecotoxicity is Lemna minor (Lesser duckweed-Angiospermae, Lemnaceae). Haffner et al [3] tested a cheaper process for a Lemna minor bioassay assessment by computer and machine vision. The aim was to use a digital camera and a framework software instrument to design a methodology for image analysis.…”