EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Exploring Nile Red and machine learning for microplastics detection in Tridacna maxima

Irène Godéré iD, Taiamiti Edmunds iD, Nabila Gaertner-Mazouni, Fiona Gimenez iD, Pascal Wong-Wah-Chung, Stéphanie Lebarillier iD, Magalie Baudrimont, Chloé Pupier, Nicolas Maihota, Jean-Claude Gaertner

PLOS One · 2026

DOI: 10.1371/journal.pone.0357014 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Irène Godéré und 9 weiteren Autor:innen. Beteiligte Einrichtung: Université de Polynésie Française, UMR SECOPOL, Tahiti, Polynésie Française. Hauptthemen laut MEDLINE: Oxazines, Microplastics, Bivalvia, Machine Learning. Die Arbeit nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Delegation of Research of French Polynesia, Université de la Polynésie Française – Grant BENIPLAST, École Doctorale du Pacifique.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Small Island Developing States (SIDS) face unique challenges for microplastics (MPs) monitoring due to limited infrastructure and resources. In this context, we propose and test innovative approaches toward a standardized, low-cost methodology for quantifying MPs in SIDS. We evaluate the giant clam T. maxima as a bio-integrator, combining Nile red (NR) fluorescence staining with automated machine-learning detection. We optimized a digestion protocol using KOH and HNO 3 for T. maxima viscera, and developed a DAPI-guided multi-spectra composite imaging approach based on triband fluorescence (DAPI, FITC, TRITC), to enhance polymer detection while reducing blooming artifacts. A semi-automated annotation pipeline using Labkit interactive segmentation with CLIP/UMAP clustering efficiently generated training data from 6711 fluorescence images. A U-Net model was trained on composite images to segment fluorescent particles. The workflow was applied to giant clams from three French Polynesian islands (Makemo, Hao, Tubuai), and NR-based estimates were validated against µFTIR spectroscopy. The model achieved F1-scores of 0.741 for giant clam samples and 0.657 for controls, comparable to human annotation (F1 = 0.680). MPs were detected across all islands, with highest concentrations in gills (16.9–52.7 particles·g −1 wet weight) compared to viscera (2.5–11.0 particles·g −1 ww). µFTIR validation revealed that NR overestimates MP counts (µFTIR: 0.80 ± 0.16 particles·g −1 ww at Tubuai), primarily due to false positives from proteins, cellulose, and stearates. In Tubuai, polyamide (28.9%), PVC (12.6%), and polystyrene (10.7%) were the dominant polymers, suggesting contributions from fishing gear, agriculture, and household waste. While NR-based quantification overestimates absolute MP counts, the automated pipeline demonstrates potential for high-throughput image processing, reproducible sample analysis, and methodological standardization. This workflow represents a first step toward scalable, low-cost approaches for MPs monitoring in insular systems, highlighting areas for further calibration and optimization. Future work should refine fluorescence thresholds and expand validation across species and locations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

OxazinesMicroplasticsBivalviaMachine LearningEnvironmental MonitoringWater Pollutants, ChemicalAnimalsFluorescent Dyes

Substanzen

OxazinesMicroplasticsnile redWater Pollutants, ChemicalFluorescent Dyes

Autor:innen und Institutionen

  • Université de Polynésie Française, UMR SECOPOL, Tahiti, Polynésie Française.
  • AI Freelancer Papeete, Tahiti, Polynésie Française.
  • Aix-Marseille Université, LCE, Aix-en-Provence, France.
  • Université de Bordeaux, CNRS, UMR EPOC 5805, Pessac, France.
  • Institut de Recherche pour le Développement, UMR SECOPOL 241, Tahiti, Polynésie Française.

ORCID-Profile: Irène Godéré, Taiamiti Edmunds, Fiona Gimenez, Stéphanie Lebarillier

Förderung

  • Delegation of Research of French Polynesia
  • Université de la Polynésie Française – Grant BENIPLAST
  • École Doctorale du Pacifique

Zitieren

APA

Godéré, I., Edmunds, T., Gaertner-Mazouni, N., Gimenez, F., Wong-Wah-Chung, P., Lebarillier, S., Baudrimont, M., Pupier, C., Maihota, N., & Gaertner, J. C. (2026). Exploring Nile Red and machine learning for microplastics detection in Tridacna maxima. PLOS One. https://doi.org/10.1371/journal.pone.0357014

Vancouver

Godéré I, Edmunds T, Gaertner-Mazouni N, Gimenez F, Wong-Wah-Chung P, Lebarillier S, et al. Exploring Nile Red and machine learning for microplastics detection in Tridacna maxima. PLOS One. 2026. doi:10.1371/journal.pone.0357014

BibTeX
@article{Godr2026,
  author = {Godéré, Irène and Edmunds, Taiamiti and Gaertner-Mazouni, Nabila and Gimenez, Fiona and Wong-Wah-Chung, Pascal and Lebarillier, Stéphanie and Baudrimont, Magalie and Pupier, Chloé and Maihota, Nicolas and Gaertner, Jean-Claude},
  title = {Exploring Nile Red and machine learning for microplastics detection in Tridacna maxima},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0357014}
}
Kostenlos starten →