Related Experiment Video
Updated: Mar 27, 2026
08:27
Use of Chironomidae Diptera Surface-Floating Pupal Exuviae as a Rapid Bioassessment Protocol for Water Bodies
Published on: July 24, 2015
12.4K
AI-Assisted Tissue Classification in Chironomus riparius: A Potential Tool for Ecotoxicological Studies
Jelena Stojanović1, Aleksandar Milosavljević2, Dimitrija Savić-Zdravković1
1University of Niš, Faculty of Sciences and Mathematics, Department of Biology and Ecology, Višegradska 33, 18000 Niš, Serbia.
Environmental Toxicology and Chemistry
|March 26, 2026
Summary
This study introduces an AI-powered Convolutional Neural Network (CNN) model for automatic histological tissue identification in Chironomus riparius. The deep learning approach achieved 94.21% accuracy, streamlining ecotoxicological research.
Area of Science:
- Ecotoxicology
- Histopathology
- Artificial Intelligence
Background:
- Histological techniques are crucial for assessing pollutant effects on aquatic life.
- Analyzing invertebrate histology, especially for new species, is often time-consuming due to limited reference data.
Purpose of the Study:
- To develop and validate a deep learning model for automated histological tissue classification in Chironomus riparius.
- To establish an AI-assisted workflow for histopathological analysis in ecotoxicology.
Main Methods:
- A Convolutional Neural Network (CNN) deep learning model was designed.
- The model was trained to identify 11 distinct tissue types in Chironomus riparius.
- Model performance was evaluated based on classification accuracy.
Main Results:
- The CNN model achieved an overall accuracy of 94.21% in identifying 11 tissue types.
- Five tissue types were identified with 100% accuracy.
- The highest misclassification rate was 22.72% for the parietal fat body.
Conclusions:
- This study presents the first AI-assisted method for histological tissue classification in an OECD invertebrate model organism.
- The developed deep learning model significantly enhances the efficiency and accuracy of histopathological analysis.
- This approach provides a foundation for integrating AI into future environmental and ecotoxicological research workflows.
