Automated quantification of Enchytraeus crypticus juveniles in different soil types using RootPainter

Abstract

The manual counting of juveniles in enchytraeid soil toxicity tests is time-consuming, labour-intensive, repetitive, prone to subjectivity, but can potentially be automated through deep learning methods using convolutional neural networks. This study investigated if RootPainter can be used as a tool to automatically quantify Enchytraeus crypticus juveniles in toxicity tests using different soil types. Toxicity tests were performed following OECD guideline 220 using five different pesticides (two fungicides and three insecticides) and four different soil types (three OECD artificial soils and one natural LUFA 2.2 soil). Manual counts were done by three different operators, with each operator counting images for one pesticide. Correlations between automated and manual counts were strong and significant in all four soils for all operators, with Pearson’s correlation coefficients ≥ 0.955 and intraclass comparability coefficients ≥ 0.936. Toxicity values (EC50 and EC10) calculated from the manual and automated counts were within a factor of 0.85 – 1.30. Overall, the results show that RootPainter is a suitable tool for a reliable, repeatable and accurate quantification of enchytraeid juveniles, and can eliminate the time-consuming manual counting process.

Keywords

• Ecotoxicology
• Toxicity tests
• Soil organism counting
• Soil image analysis
• Interactive machine learning