Explainable Deep Learning for Diabetic Foot Ulcer Diagnosis: A Comparative CNN Framework

Rania Kadhim; Ahmad Lateef; Mohammed Kamil

doi:10.46604/aiti.2026.16496

Authors

Rania Kadhim College of Science, Mustansiriyah University, Baghdad, Iraq
Ahmad Lateef College of Science, Mustansiriyah University, Baghdad, Iraq
Mohammed Kamil College of Science, Mustansiriyah University, Baghdad, Iraq

DOI:

https://doi.org/10.46604/aiti.2026.16496

Keywords:

deep learning, convolutional neural networks, transfer learning, explainable AI, medical image analysis

Abstract

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.

References

S. K. Das, P. Roy, P. Singh, M. Diwakar, V. Singh, A. Maurya, et al., “Diabetic Foot Ulcer Identification: A Review,” Diagnostics, vol. 13, no. 12, article no. 1998, 2023.

P. L. Li, Q. F. Xiao, K. L. Yick, Q. L. Liu, and L. Y. Zhang, “A Novel Deep Learning Approach to Classify 3D Foot Types of Diabetic Patients,” Scientific Reports, vol. 15, no. 1, article no. 13819, 2025.

H. Xie, Z. Chen, G. Wu, P. Wei, T. Gong, S. Chen, et al., “Application of Metagenomic Next-Generation Sequencing (mNGS) to Describe the Microbial Characteristics of Diabetic Foot Ulcers at a Tertiary Medical Center in South China,” BMC Endocrine Disorders, vol. 25, no. 1, article no. 18, 2025.

F. Mostafavi, M. R. Amini, Y. Mehrabi, E. Nasli Esfahani, and S. S. H. Nazari, “Machine Learning Insights into Amputation Risk: Evaluating Wound Classification Systems in Diabetic Foot Ulcers,” International Wound Journal, vol. 22, no. 6, article no. e70515, 2025.

P. S. Rathore, A. Kumar, A. Nandal, A. Dhaka, and A. K. Sharma, “A Feature Explainability-Based Deep Learning Technique for Diabetic Foot Ulcer Identification,” Scientific Reports, vol. 15, no. 1, article no. 6758, 2025.

F. Arnia, K. Saddami, R. Roslidar, R. Muharar, and K. Munadi, “Towards Accurate Diabetic Foot Ulcer Image Classification: Leveraging CNN Pre-Trained Features and Extreme Learning Machine,” Smart Health, vol. 33, article no. 100502, 2024.

S. K. Das, P. Roy, and A. K. Mishra, “Recognition of Ischaemia and Infection in Diabetic Foot Ulcer: A Deep Convolutional Neural Network Based Approach,” International Journal of Imaging Systems and Technology, vol. 32, no. 1, pp. 192-208, 2022.

I. Cruz-Vega, D. Hernandez-Contreras, H. Peregrina-Barreto, J. D. J. Rangel-Magdaleno, and J. M. Ramirez-Cortes, “Deep Learning Classification for Diabetic Foot Thermograms,” Sensors, vol. 20, no. 6, article no. 1762, 2020.

A. Khandakar, M. E. H. Chowdhury, M. B. Ibne Reaz, S. H. Md Ali, M. A. Hasan, S. Kiranyaz, et al., “A Machine Learning Model for Early Detection of Diabetic Foot Using Thermogram Images,” Computers in Biology and Medicine, vol. 137, article no. 104838, 2021.

K. Munadi, K. Saddami, M. Oktiana, R. Roslidar, K. Muchtar, M. Melinda, et al., “A Deep Learning Method for Early Detection of Diabetic Foot Using Decision Fusion and Thermal Images,” Applied Sciences, vol. 12, no. 15, article no. 7524, 2022.

M. Goyal, N. D. Reeves, A. K. Davison, S. Rajbhandari, J. Spragg, and M. H. Yap, “DFUNET: Convolutional Neural Networks for Diabetic Foot Ulcer Classification,” IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 4, no. 5, pp. 728-739, 2020.

M. Ahsan, S. Naz, R. Ahmad, H. Ehsan, and A. Sikandar, “A Deep Learning Approach for Diabetic Foot Ulcer Classification and Recognition,” Information, vol. 14, no. 1, article no. 36, 2023.

A. M. Fahmy, “Assessing the Efficacy of AI Models in Medical Imaging Analysis for the Early Identification of Diabetic Foot Ulcers and Gangrene: A Review,” Premier Journal of Science, vol. 12, article no. 100093, 2025.

L. Wang, P. C. Pedersen, E. Agu, D. M. Strong, and B. Tulu, “Area Determination of Diabetic Foot Ulcer Images Using a Cascaded Two-Stage SVM-Based Classification,” IEEE Transactions on Biomedical Engineering, vol. 64, no. 9, pp. 2098-2109, 2017.

R. Niri, H. Douzi, Y. Lucas, and S. Treuillet, “A Superpixel-Wise Fully Convolutional Neural Network Approach for Diabetic Foot Ulcer Tissue Classification,” Proceedings of Pattern Recognition. ICPR International Workshops and Challenges, pp. 308-320, 2021.

J. Amin, M. Sharif, M. A. Anjum, H. U. Khan, M. S. A. Malik, and S. Kadry, “An Integrated Design for Classification and Localization of Diabetic Foot Ulcer Based on CNN and YOLOv2-DFU Models,” IEEE Access, vol. 8, pp. 228586-228597, 2020.

J. Hyun, Y. Lee, H. M. Son, S. H. Lee, V. Pham, J. U. Park, et al., “Synthetic Data Generation System for AI-Based Diabetic Foot Diagnosis,” SN Computer Science, vol. 2, no. 5, article no. 345, 2021.

J. J. van Netten, D. Clark, P. A. Lazzarini, M. Janda, and L. F. Reed, “The Validity and Reliability of Remote Diabetic Foot Ulcer Assessment Using Mobile Phone Images,” Scientific Reports, vol. 7, no. 1, article no. 9480, 2017.

L. Alzubaidi, M. A. Fadhel, S. R. Oleiwi, O. Al-Shamma, and J. Zhang, “DFU_QUTNet: Diabetic Foot Ulcer Classification Using Novel Deep Convolutional Neural Network,” Multimedia Tools and Applications, vol. 79, pp. 15655-15677, 2019.

S. K. Das, S. Namasudra, and A. K. Sangaiah, “HCNNet: Hybrid Convolution Neural Network for Automatic Identification of Ischaemia in Diabetic Foot Ulcer Wounds,” Multimedia Systems, vol. 30, no. 1, article no. 36, 2024.

S. Alkhalefah, I. AlTuraiki, and N. Altwaijry, “Advancing Diabetic Foot Ulcer Care: AI and Generative AI Approaches for Classification, Prediction, Segmentation, and Detection,” Healthcare, vol. 13, no. 6, article no. 648, 2025.

M. R. Naeemah and M. Y. Kamil, “SkinVGG-Net: A Modified and Fine-Tuned VGG19-Based Deep Learning Architecture for Skin Cancer Classification,” International Journal of Advances in Signal and Image Sciences, vol. 11, no. 1, pp. 169-179, 2025.

A. K. C. Huong, J. M. Sukki, and X. T. K. Ngu, “MOBILEDFU: Classification of Diabetic Foot Ulcer Infection on the Edge,” Journal of Engineering Science and Technology, vol. 20, no. 2, pp. 577-589, 2025.

S. Biswas, R. Mostafiz, B. K. Paul, K. M. M. Uddin, M. A. Hadi, F. Khanom, “DFU_XAI: A Deep Learning-Based Approach to Diabetic Foot Ulcer Detection Using Feature Explainability,” Biomedical Materials & Devices, vol. 2, no. 3, pp. 1225-1245, 2024.

R. R. Kadhim and M. Y. Kamil, “Advancing Dermatological Image Classification: GLCM-Based Machine Learning Insights,” Advance Sustainable Science, Engineering and Technology (ASSET), vol. 7, no. 1, article no. 0250116, 2025.

N. Almufadi and H. F. Alhasson, “Classification of Diabetic Foot Ulcers from Images Using Machine Learning Approach,” Diagnostics, vol. 14, no. 16, article no. 1807, 2024.

N. K. I. S. Anggreni, H. Kristianto, D. Handayani, Y. Yueniwati, P. L. T. Irawan, R. Rosandi, et al., “Artificial Intelligence for Diabetic Foot Screening Based on Digital Image Analysis: A Systematic Review,” Journal of Diabetes Science and Technology, vol. 20, no. 4, pp. 1381-1388, 2026.

T. Zhao, J. Yu, R. Deng, L. Ding, X. Li, and J. Mi, "Accuracy of Deep Learning for Risk Prediction and Screening of Diabetic Foot Ulcers: A Systematic Review and Meta-Analysis," Diabetes Research and Clinical Practice, vol. 236, article no. 113262, 2026.