Automated acute skin toxicity scoring in a mouse model through deep learning
Radiation and Environmental Biophysics · 2025
DOI: 10.1007/s00411-024-01096-x ↗Kurz gefasst
Fachartikel in der Zeitschrift Radiation and Environmental Biophysics, 2025. Verfasst von Morten Sahlertz und 6 weiteren Autor:innen. Beteiligte Einrichtung: Danish Centre for Particle Therapy, Aarhus University Hospital, Aarhus, Denmark. mortsa@clin.au.dk. Hauptthemen laut MEDLINE: Deep Learning, Skin. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Novo Nordisk Foundation, Danish Cancer Society, The Independent Research Fond.
Abstract (Originalsprache)
This study presents a novel approach to skin toxicity assessment in preclinical radiotherapy trials through an advanced imaging setup and deep learning. Skin reactions, commonly associated with undesirable side effects in radiotherapy, were meticulously evaluated in 160 mice across four studies. A comprehensive dataset containing 7542 images was derived from proton/electron trials with matched manual scoring of the acute toxicity on the right hind leg, which was the target area irradiated in the trials. This dataset was the foundation for the subsequent model training. The two-step deep learning framework incorporated an object detection model for hind leg detection and a classification model for toxicity classification. An observer study involving five experts and the deep learning model, was conducted to analyze the retrospective capabilities and inter-observer variations. The results revealed that the hind leg object detection model exhibited a robust performance, achieving an accuracy of almost 99%. Subsequently, the classification model demonstrated an overall accuracy of about 85%, revealing nuanced challenges in specific toxicity grades. The observer study highlighted high inter-observer agreement and showcased the model’s superiority in accuracy and misclassification distance. In conclusion, this study signifies an advancement in objective and reproducible skin toxicity assessment. The imaging and deep learning system not only allows for retrospective toxicity scoring, but also presents a potential for minimizing inter-observer variation and evaluation times, addressing critical gaps in manual scoring methodologies. Future recommendations include refining the system through an expanded training dataset, paving the way for its deployment in preclinical research and radiotherapy trials.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Danish Centre for Particle Therapy, Aarhus University Hospital, Aarhus, Denmark. mortsa@clin.au.dk.
- Department of Clinical Medicine, Aarhus University, Aarhus, Denmark. mortsa@clin.au.dk.
- Danish Centre for Particle Therapy, Aarhus University Hospital, Aarhus, Denmark.
- Department of Clinical Medicine, Aarhus University, Aarhus, Denmark.
- Department of Oncology, Aarhus University Hospital, Aarhus, Denmark.
Förderung
- Novo Nordisk Foundation
- Danish Cancer Society
- The Independent Research Fond
- Aarhus Universitet
Zitieren
APA
Sahlertz, M., Kristensen, L., Sørensen, B. S., Poulsen, P. R., Asonganyi, F. C., Sinha, P., & Nijkamp, J. (2025). Automated acute skin toxicity scoring in a mouse model through deep learning. Radiation and Environmental Biophysics. https://doi.org/10.1007/s00411-024-01096-x
Vancouver
Sahlertz M, Kristensen L, Sørensen BS, Poulsen PR, Asonganyi FC, Sinha P, et al. Automated acute skin toxicity scoring in a mouse model through deep learning. Radiation and Environmental Biophysics. 2025. doi:10.1007/s00411-024-01096-x
BibTeX
@article{Sahlertz2025,
author = {Sahlertz, Morten and Kristensen, Line and Sørensen, Brita Singers and Poulsen, Per Rugaard and Asonganyi, Folefac Charlemagne and Sinha, Priyanshu and Nijkamp, Jasper},
title = {Automated acute skin toxicity scoring in a mouse model through deep learning},
journal = {Radiation and Environmental Biophysics},
year = {2025},
doi = {10.1007/s00411-024-01096-x}
}
EUVIMED