COLLEMBOT: AI-Based Counting of Collembola for OECD 232 Tests

Résumé fourni par la source

Abstract Ecotoxicological tests with soil organisms, such as the collembolan Folsomia candida , are essential for assessing chemical risks in terrestrial ecosystems. However, the current Organization for Economic Co-operation and Development (OECD) 232 reproduction tests rely on manual counting of juvenile and adult Collembola, a process that is costly, labor-intensive, time-consuming and prone to operator bias. These limitations restrict data availability and hinder robust risk assessments. We therefore developed COLLEMBOT, an automated counting tool based on a YOLOv11 convolutional neural network, designed to integrate seamlessly into OECD workflows without protocol modifications. The model was trained on high-resolution images (n = 3207) from multiple laboratories and validated using 22 independent datasets (n = 1704 images) from Amsterdam (Netherlands), Basel (Switzerland), Bayreuth (Germany), Coimbra (Portugal) and Aarhus (Denmark). Datasets consisted of relevant standard soils (OECD artificial soils with 2.5%, 5% and 10% sphagnum peat; LUFA 2.2) and the springtail Folsomia candida. Automated counts showed strong agreement with manual counts (R² = 0.88–0.99). Dose-response curves derived from automated and manual counts strongly overlapped and effect concentrations (EC₁₀ and EC₅₀) differed minimally (Median %Δ 6.2 ± 23 and EC 10 - EC 90 R 2 ≥ 0.977), remaining within acceptable limits for regulatory risk assessment and confirming reliability. Time efficiency improved significantly: a test with ∼300 images and up to 1,500 individuals per image was processed in less than 3 hours, compared to ∼137 hours needed for manual counting, a reduction of approximately 97%. By reducing labor and improving reproducibility, COLLEMBOT enables broader hazard data generation for collembolans, supporting science-based chemical risk assessment. The code and workflow are publicly available to facilitate adoption and community-driven development. Abstract Figure

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.