PhenoLearn: a user-friendly toolkit for image annotation and deep learning-based phenotyping for biological datasets
Journal of Evolutionary Biology · 2025
DOI: 10.1093/jeb/voaf058 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Evolutionary Biology, 2025. Verfasst von Yichen He und 3 weiteren Autor:innen. Beteiligte Einrichtung: Ecology and Evolutionary Biology, School of Biosciences, University of Sheffield, Sheffield, United Kingdom. Hauptthemen laut MEDLINE: Deep Learning, Software, Phenotype, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Leverhulme Early Career Fellowship, Natural Environment Research Council Independent Research Fellowship, European Research Council.
Abstract (Originalsprache)
The digitization of natural history specimens has unlocked opportunities for large-scale phenotypic trait analysis. In recent years, deep learning has shown significant results in accurately predicting annotations on 2D specimen photographs. However, it can be challenging for biologists without extensive related expertise to easily use deep learning. Here, we introduce PhenoLearn, a toolkit developed for biologists to generate annotations on 2D specimen images using deep learning. PhenoLearn integrates graphical user interfaces (GUIs) within its two main modules, PhenoLabel for image annotation and PhenoTrain for model training and prediction. GUIs increase accessibility and reduce the need for computational expertise, allowing biologists to intuitively go through a workflow of labelling training sets, using deep learning, and reviewing predictions in the same tool. We demonstrate PhenoLearn’s capabilities through a case study involving the segmentation of plumage areas on bird images, showcasing prediction accuracy and the running time with and without graphics processing unit, highlighting its potential to generate annotations with minimal computational cost and time. The toolkit’s modular design and flexibility ensure adaptability, allowing for integration with other tools amidst rapidly evolving deep learning approaches. PhenoLearn bridges the gap between specimen digitization and downstream analysis, providing biologists with broader access to deep learning. The source code, installation guides, tutorials with screenshots, and a small demo dataset for PhenoLearn can be found at https://github.com/echanhe/phenolearn.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Ecology and Evolutionary Biology, School of Biosciences, University of Sheffield, Sheffield, United Kingdom.
- Department of Life Sciences, Natural History Museum, London, United Kingdom.
- Department of Computer Science, University of Sheffield, Sheffield, United Kingdom.
- Bird Group, Department of Life Sciences, Natural History Museum, Tring, United Kingdom.
ORCID-Profile: Yichen He, Christopher R Cooney, Steve Maddock, Gavin H Thomas
Förderung
- Leverhulme Early Career Fellowship
- Natural Environment Research Council Independent Research Fellowship
- European Research Council
- Royal Society University Research Fellowship
Zitieren
APA
He, Y., Cooney, C. R., Maddock, S., & Thomas, G. H. (2025). PhenoLearn: a user-friendly toolkit for image annotation and deep learning-based phenotyping for biological datasets. Journal of Evolutionary Biology. https://doi.org/10.1093/jeb/voaf058
Vancouver
He Y, Cooney CR, Maddock S, Thomas GH. PhenoLearn: a user-friendly toolkit for image annotation and deep learning-based phenotyping for biological datasets. Journal of Evolutionary Biology. 2025. doi:10.1093/jeb/voaf058
BibTeX
@article{He2025,
author = {He, Yichen and Cooney, Christopher R and Maddock, Steve and Thomas, Gavin H},
title = {PhenoLearn: a user-friendly toolkit for image annotation and deep learning-based phenotyping for biological datasets},
journal = {Journal of Evolutionary Biology},
year = {2025},
doi = {10.1093/jeb/voaf058}
}
EUVIMED