Enhancing Early Detection of Diabetic Foot Ulcers Using Deep Neural Networks
Verbesserung der Früherkennung diabetischer Fußulzera mit Deep Neural Networks
Diagnostics · 09.08.2025 · 15 (16) · 1996
DOI: 10.3390/diagnostics15161996 ↗Auf einen Blick
Eine hybride CAD-Methode für plantare Thermogramme zeigte bei 1.670 Bildern eine hohe diagnostische Leistung zur Erkennung von DFU. Die Autor:innen berichten 98,51 % Genauigkeit und eine AUC von 1,00.
Fragestellung
Kann ein hybrides Deep-Learning-Verfahren die frühe computerassistierte Erkennung diabetischer Fußulzera aus plantaren Thermogrammen verbessern?
Methode
Hybrides Diagnosesystem mit ORB, Bag of Features und tiefen Merkmalen aus ResNet50, AlexNet und EfficientNet; Klassifikation mit einem leichten DNN in einem öffentlich verfügbaren Datensatz.
Ergebnisse
In 1.670 Bildern: Accuracy 98,51 %, Precision 100 %, Sensitivität 98,98 % und AUC 1,00. Eine Ablationsanalyse stützte die Überlegenheit der ORB+DL-Fusion gegenüber Einzelansätzen.
Schlussfolgerung der Autor:innen
Die Autor:innen folgern, dass die erste Integration von ORB-basierten Merkmalen mit tiefen neuronalen Repräsentationen für die DFU-Erkennung hohe Genauigkeit, Robustheit gegenüber Rauschen und Echtzeitfähigkeit bietet.
Kernaussagen
- Plantare Thermogramme wurden mit einem hybriden ORB+DL-Ansatz ausgewertet.
- Genannt werden 98,51 % Accuracy, 100 % Precision, 98,98 % Sensitivität und AUC 1,00.
- Die Autor:innen sehen Potenzial für den klinischen Einsatz bei Echtzeitfähigkeit.
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 09.08.2025. Verfasst von A Sharaf Eldin und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information and Decision Support Systems, Faculty of Information Technology and Computer Science, Sinai University, Arish 16020, Egypt. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: This research was funded by Princess Nourah bint Abdulrahman University., Princess Nourah bint Abdulrahman University Researchers.
Themen: Diabetisches Fußsyndrom
Abstract (Originalsprache)
Background/Objectives: Diabetic foot ulcers (DFUs) remain a critical complication of diabetes, with high rates of amputation when not diagnosed early. Despite advancements in medical imaging, current DFU detection methods are often limited by their computational complexity, poor generalizability, and delayed diagnostic performance. This study presents a novel hybrid diagnostic framework that integrates traditional feature extraction methods with deep learning (DL) to improve the early real-time computer-aided detection (CAD) of DFUs.
Methods
The proposed model leverages plantar thermograms to detect early thermal asymmetries associated with DFUs. It uniquely combines the oriented FAST and rotated BRIEF (ORB) algorithm with the Bag of Features (BOF) method to extract robust handcrafted features while also incorporating deep features from pretrained convolutional neural networks (ResNet50, AlexNet, and EfficientNet). These features were fused and input into a lightweight deep neural network (DNN) classifier designed for binary classification.
Results
Our model demonstrated an accuracy of 98.51%, precision of 100%, sensitivity of 98.98%, and AUC of 1.00 in a publicly available plantar thermogram dataset (n = 1670 images). An ablation study confirmed the superiority of ORB + DL fusion over standalone approaches. Unlike previous DFU detection models that rely solely on either handcrafted or deep features, our study presents the first lightweight hybrid framework that integrates ORB-based descriptors with deep CNN representations (e.g., ResNet50 and EfficientNet). Compared with recent state-of-the-art models, such as DFU_VIRNet and DFU_QUTNet, our approach achieved a higher diagnostic performance (accuracy = 98.51%, AUC = 1.00) while maintaining real-time capability and a lower computational overhead, making it highly suitable for clinical deployment.
Conclusions
This study proposes the first integration of ORB-based handcrafted features with deep neural representations for DFU detection from thermal images. The model delivers high accuracy, robustness to noise, and real-time capabilities, outperforming existing state-of-the-art approaches and demonstrating strong potential for clinical deployment.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Information and Decision Support Systems, Faculty of Information Technology and Computer Science, Sinai University, Arish 16020, Egypt.
- Department of Information Systems, Faculty of Computers and AI, Helwan University, Cairo 11795, Egypt.
- Department of Information Technology, Faculty of Information Technology and Computer Science, Sinai University, Arish 16020, Egypt.
- Department of Information Technology, Faculty of Computers and Informatics, Zagazig University, Zagazig 44519, Egypt.
- Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia.
ORCID-Profile: A Sharaf Eldin, Asmaa S Ahmoud, Hanaa M Hamza, Hanin Ardah
Förderung
- This research was funded by Princess Nourah bint Abdulrahman University.
- Princess Nourah bint Abdulrahman University Researchers
Zitieren
APA
Eldin, A. S., Ahmoud, A. S., Hamza, H. M., & Ardah, H. (2025). Enhancing Early Detection of Diabetic Foot Ulcers Using Deep Neural Networks. Diagnostics, 15(16), 1996. https://doi.org/10.3390/diagnostics15161996
Vancouver
Eldin AS, Ahmoud AS, Hamza HM, Ardah H. Enhancing Early Detection of Diabetic Foot Ulcers Using Deep Neural Networks. Diagnostics. 2025;15(16):1996. doi:10.3390/diagnostics15161996
BibTeX
@article{Eldin2025,
author = {Eldin, A Sharaf and Ahmoud, Asmaa S and Hamza, Hanaa M and Ardah, Hanin},
title = {Enhancing Early Detection of Diabetic Foot Ulcers Using Deep Neural Networks},
journal = {Diagnostics},
year = {2025},
volume = {15},
number = {16},
pages = {1996},
doi = {10.3390/diagnostics15161996}
}
EUVIMED