Interpreting Venous and Arterial Ulcer Images Through the Grad-CAM Lens: Insights and Implications in CNN-Based Wound Image Classification
Diagnostics · 28.08.2025 · 15 (17) · 2184
DOI: 10.3390/diagnostics15172184 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 28.08.2025. Verfasst von Hannah Neuwieser und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Plastic, Hand, and Reconstructive Surgery, University Hospital Regensburg, 93053 Regensburg, Germany. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bavarian Research Foundation, Bayerische Forschungsstiftung.
Abstract (Originalsprache)
Background/Objectives: Chronic wounds of the lower extremities, particularly arterial and venous ulcers, represent a significant and costly challenge in medical care. To assist in differential diagnosis, we aim to evaluate various advanced deep-learning models for classifying arterial and venous ulcers and visualize their decision-making processes.
Methods
A retrospective dataset of 607 images (198 arterial and 409 venous ulcers) was used to train five convolutional neural networks: ResNet50, ResNeXt50, ConvNeXt, EfficientNetB2, and EfficientNetV2. Model performance was assessed using accuracy, precision, recall, F1-score, and ROC-AUC. Grad-CAM was applied to visualize image regions contributing to classification decisions.
Results
The models demonstrated high classification performance, with accuracy ranging from 72% (ConvNeXt) to 98% (ResNeXt50). Precision and recall values indicated strong discrimination between arterial and venous ulcers, with EfficientNetV2 achieving the highest precision.
Conclusions
AI-assisted classification of venous and arterial ulcers offers a valuable method for enhancing diagnostic efficiency.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Plastic, Hand, and Reconstructive Surgery, University Hospital Regensburg, 93053 Regensburg, Germany.
- Ambient Assisted Living & Medical Assistance Systems, Department of Computer Science, University of Bayreuth, 95447 Bayreuth, Germany.
- Machine Learning and Data Analytics Lab (MaD Lab), Department Artificial Intelligence in Biomedical Engineering (AIBE), Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), 91052 Erlangen, Germany.
- Imaging Solutions, PreSens Precision Sensing GmbH, 93053 Regensburg, Germany.
- Department of Dermatology, University Hospital Regensburg, 93053 Regensburg, Germany.
ORCID-Profile: Naga Venkata Sai Jitin Jami, Oliver Felthaus, Stephan Schreml, Lukas Prantl, Heike Leutheuser
Förderung
- Bavarian Research Foundation
- Bayerische Forschungsstiftung
Zitieren
APA
Neuwieser, H., Jami, N. V. S. J., Meier, R. J., Liebsch, G., Felthaus, O., Klein, S., Schreml, S., Berneburg, M., Prantl, L., Leutheuser, H., & Kempa, S. (2025). Interpreting Venous and Arterial Ulcer Images Through the Grad-CAM Lens: Insights and Implications in CNN-Based Wound Image Classification. Diagnostics, 15(17), 2184. https://doi.org/10.3390/diagnostics15172184
Vancouver
Neuwieser H, Jami NVSJ, Meier RJ, Liebsch G, Felthaus O, Klein S, et al. Interpreting Venous and Arterial Ulcer Images Through the Grad-CAM Lens: Insights and Implications in CNN-Based Wound Image Classification. Diagnostics. 2025;15(17):2184. doi:10.3390/diagnostics15172184
BibTeX
@article{Neuwieser2025,
author = {Neuwieser, Hannah and Jami, Naga Venkata Sai Jitin and Meier, Robert Johannes and Liebsch, Gregor and Felthaus, Oliver and Klein, Silvan and Schreml, Stephan and Berneburg, Mark and Prantl, Lukas and Leutheuser, Heike and Kempa, Sally},
title = {Interpreting Venous and Arterial Ulcer Images Through the Grad-CAM Lens: Insights and Implications in CNN-Based Wound Image Classification},
journal = {Diagnostics},
year = {2025},
volume = {15},
number = {17},
pages = {2184},
doi = {10.3390/diagnostics15172184}
}
EUVIMED