Explainable Deep Learning for Diabetic Foot Ulcer Diagnosis: A Comparative CNN Framework
Advances in Technology Innovation · 20.08.2026 · 11 (4) · 426-438
DOI: 10.46604/aiti.2026.16496 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advances in Technology Innovation, online erschienen am 20.08.2026. Verfasst von Rania Kadhim und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Themen: Diabetisches Fußsyndrom
Abstract (Originalsprache)
This study aims to develop and evaluate an automated deep learning framework for diabetic foot ulcer (DFU) classification to reduce reliance on manual visual inspection. Five transfer-learning architectures (EfficientNetB0, ResNet50, VGG16, InceptionV3, and MobileNetV2) are evaluated on 1,055 localized, augmented foot images using stratified 5-fold cross-validation. The ResNet50 model achieves excellent diagnostic results, with a mean F1-score of 0.997 ± 0.004 and a mean ROC-AUC of 1.000 ± 0.00001 in all the folds. These results demonstrate the potential of the proposed explainable deep learning framework for automated DFU classification. However, the lack of patient-level information in the dataset used may lead to data leakage due to image-level splitting. Therefore, validation of this explainable model on external clinical cohorts is highly recommended for reliable and safe use.
Zitieren
APA
Kadhim, R., Lateef, A., & Kamil, M. (2026). Explainable Deep Learning for Diabetic Foot Ulcer Diagnosis: A Comparative CNN Framework. Advances in Technology Innovation, 11(4), 426-438. https://doi.org/10.46604/aiti.2026.16496
Vancouver
Kadhim R, Lateef A, Kamil M. Explainable Deep Learning for Diabetic Foot Ulcer Diagnosis: A Comparative CNN Framework. Advances in Technology Innovation. 2026;11(4):426-438. doi:10.46604/aiti.2026.16496
BibTeX
@article{Kadhim2026,
author = {Kadhim, Rania and Lateef, Ahmad and Kamil, Mohammed},
title = {Explainable Deep Learning for Diabetic Foot Ulcer Diagnosis: A Comparative CNN Framework},
journal = {Advances in Technology Innovation},
year = {2026},
volume = {11},
number = {4},
pages = {426--438},
doi = {10.46604/aiti.2026.16496}
}
EUVIMED