EUVIMEDEUVIMED entdecken
Crossref

Non-invasive individual identification of adult Pleurodeles waltl using deep learning

Kosuke Kagamiyama, Naofumi Saiki, Kosuke Takaya, Atsuro Koga, Masaru Ueki, Toshinori Hayashi, Tetsuya Ohbayashi

Experimental Animals · 2026

DOI: 10.1538/expanim.26-0089 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Experimental Animals, 2026. Verfasst von Kosuke Kagamiyama und 6 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Medical Sciences, Tottori University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable individual identification is essential for long-term tracking and reproducible laboratory animal studies. In amphibians, invasive marking methods like tags and dye injections can cause welfare concerns and may be unreliable because of tag loss or migration. We developed and evaluated a non-invasive identification system for 25 adult Pleurodeles waltl using smartphone-captured images and the pre-trained convolutional neural network EfficientNetV2. To determine the most informative imaging region, separate models were trained and tested using head and whole-body images. The head-image model achieved 95.3% accuracy on the independent test dataset (macro F1-score = 0.946; Cohen’s kappa = 0.951), markedly outperforming the whole-body model (56.6% accuracy). Grad-CAM visualization showed that the model primarily focused on dorsal head spot patterns, indicating that these markings are more informative for individual recognition than whole-body patterns. Because this method requires only a smartphone and a trained model, it can be implemented without specialized marking equipment. This approach enables accurate individual identification, while avoiding invasive marking and therefore supports both animal welfare and research reproducibility. It may provide a practical basis for standardizing individual identification in future amphibian research.

Schlagwörter

Stichwörter der Autor:innen

Deep LearningPleurodeles waltlanimal welfareindividual identificationnon-invasive method

Autor:innen und Institutionen

  • Graduate School of Medical Sciences, Tottori University.
  • Tottori University Robotic Surgery Training and Medical Device Innovation Center, Tottori University Hospital.
  • Faculty of Education, Shimane University.
  • Office for Decision Support & Headquarters for Management Strategy, Tottori University.
  • Department of Medical Education, Tottori University Faculty of Medicine.
  • Amphibian Research Center, Hiroshima University.

Zitieren

APA

Kagamiyama, K., Saiki, N., Takaya, K., Koga, A., Ueki, M., Hayashi, T., & Ohbayashi, T. (2026). Non-invasive individual identification of adult Pleurodeles waltl using deep learning. Experimental Animals. https://doi.org/10.1538/expanim.26-0089

Vancouver

Kagamiyama K, Saiki N, Takaya K, Koga A, Ueki M, Hayashi T, et al. Non-invasive individual identification of adult Pleurodeles waltl using deep learning. Experimental Animals. 2026. doi:10.1538/expanim.26-0089

BibTeX
@article{Kagamiyama2026,
  author = {Kagamiyama, Kosuke and Saiki, Naofumi and Takaya, Kosuke and Koga, Atsuro and Ueki, Masaru and Hayashi, Toshinori and Ohbayashi, Tetsuya},
  title = {Non-invasive individual identification of adult Pleurodeles waltl using deep learning},
  journal = {Experimental Animals},
  year = {2026},
  doi = {10.1538/expanim.26-0089}
}
Kostenlos starten →