Optimized Multi-Resolution Attention-Based Architecture for Effective Diabetic Skin Lesion Classification
Abstract
Early and reliable identification of diabetic skin complications, including ischemia and infection, is essential for timely clinical intervention and prevention of severe outcomes. Nevertheless, traditional deep learning models often exhibit limited generalization capability and high computational demands, particularly when distinguishing between visually subtle infection types. To overcome these challenges, this study introduces an end-to-end deep learning architecture termed the Enhanced Multi-Resolution Multi-Path Attention Network (EMRMP-Net), specifically designed for robust diabetic lesion classification. A key contribution of this work is the introduction of a trainable attention-based fusion mechanism that adaptively learns to weight and integrate multi-resolution feature maps, enhancing contextual understanding and discriminative performance. To address the prevalent issue of class imbalance in medical imaging datasets, EMRMP-Net utilizes focal loss and domain-tailored data augmentation, thereby promoting stable learning and improved representation of minority classes. Additionally, a shared classification head across multiple resolution pathways enables joint feature optimization, reducing computational redundancy and improving learning efficiency compared to traditional MRMP models. Comprehensive experiments on the publicly available Diabetic Foot Ulcer (DFU) dataset demonstrate that EMRMP-Net surpasses existing state-of-the-art-methods, achieving 98.12% accuracy and 98.14% F1-score for ischemia detection, and 95.27% accuracy with 93.68% F1-score for infection classification. Overall, EMRMP-Net provides a highly effective, computationally efficient, and generalizable framework for automated diabetic skin lesion analysis, demonstrating strong potential for real-world clinical applications. EMRMP-Net is designed as a general framework for diabetic skin lesion analysis, capable of handling diverse lesion characteristics through multi-resolution and attention-based feature learning. However, in this work, the model is explicitly formulated, trained, and evaluated for the clinically critical binary classification task of distinguishing ischemic ulcers from infected ulcers within DFU imagery.
Downloads
References
Alkhalefah, S., AlTuraiki, I., & Altwaijry, N. (2025, March). Advancing Diabetic Foot Ulcer Care: AI and Generative AI Approaches for Classification, Prediction, Segmentation, and Detection. In Healthcare (Vol. 13, No. 6, p. 648). MDPI
Lin, P. C., Li, T. C., Huang, T. H., Hsu, Y. L., Ho, W. C., Hsieh, C. L., & Xu, J. L. (2025). Machine Learning for Diabetic Foot Care: Accuracy Trends and Emerging Directions in Healthcare AI. Frontiers in Public Health, 13, 1613946.
Ramakrishnan, J. (2025). Synergizing IoT and machine learning for diabetic foot ulcer detection and management. International Journal of System Assurance Engineering and Management, 1-12.
Brüngel, R., Kendrick, C., Cassidy, B., Bracke, B., Friedrich, C. M., Reeves, N. D., ... & Yap, M. H. (2024). Diabetic foot ulcer grand challenge 2024: overview and baseline methods. Diabetic Foot Ulcers Grand Challenge, 109-124.
Zhou, G. X., Tao, Y. K., Hou, J. Z., Zhu, H. J., Xiao, L., Zhao, N., ... & Zhang, D. (2025). Construction and validation of a deep learning-based diagnostic model for segmentation and classification of diabetic foot. Frontiers in Endocrinology, 16, 1543192.
Wang, Z., Tan, X., Xue, Y. et al. (2024). Smart diabetic foot ulcer scoring system. Sci Rep 14, 11588.
Amjad, K., Asif, S., Waheed, Z., Khalid, M. A., & Guo, Y. (2025). A weighted Gompertz fuzzy ranking-based ensemble model for diabetic foot ulcer detection in skin and thermal imagery. Computers and Electrical Engineering, 126, 110475.
Ahsan, M., Naz, S., Ahmad, R., Ehsan, H., & Sikandar, A. (2023). A deep learning approach for diabetic foot ulcer classification and recognition. Information, 14(1), 36.
MG, S., & Venkatesan, C. (2025). SwinDFU-Net: Deep learning transformer network for infection identification in diabetic foot ulcer. Technology and Health Care, 33(1), 601-618.
Dos Santos, E. S., Veras, R. D. M. S., Dos Santos, F. D. C. T., Ito, M., Bianchi, A. G. C., Aires, K. R. T., & Tavares, J. M. R. (2025). Enhancing Diabetic Foot Ulcer Classification through Fine-Tuned Multilevel CNN. IEEE Access.
Toofanee, M. S. A., Dowlut, S., Hamroun, M., Tamine, K., Duong, A. K., Petit, V., & Sauveron, D. (2023). DFU-Helper: an innovative framework for longitudinal diabetic foot ulcer diseases evaluation using deep learning. Applied Sciences, 13(18), 10310.
Khalil, M., Naeem, A., Naqvi, R. A., Zahra, K., Muqarib, S. A., & Lee, S. W. (2023). Deep learning-based classification of abrasion and ischemic diabetic foot sores using camera-captured images. Mathematics, 11(17), 3793.
Alqahtani, A., Alsubai, S., Rahamathulla, M. P., Gumaei, A., Sha, M., Zhang, Y. D., & Khan, M. A. (2023). Empowering foot health: Harnessing the adaptive weighted sub-gradient convolutional neural network for diabetic foot ulcer classification. Diagnostics, 13(17), 2831.
Karthik, R., Ajay, A., Jhalani, A., Ballari, K., & K, S. (2025). An explainable deep learning model for diabetic foot ulcer classification using swin transformer and efficient multi-scale attention-driven network. Scientific Reports, 15(1), 4057.
Biswas, S., Mostafiz, R., Uddin, M. S., & Paul, B. K. (2024). XAI-FusionNet: Diabetic foot ulcer detection based on multi-scale feature fusion with explainable artificial intelligence. Heliyon, 10(10).
Sait, A. R. W., & Nagaraj, R. (2025). Diabetic foot ulcers detection model using a hybrid convolutional neural networks–vision transformers. Diagnostics, 15(6), 736.
Suganyadevi, S., Pershiya, A. S., Balasamy, K., et al. “Deep learning based alzheimer disease diagnosis: A comprehensive review”. SN Computer Science, Vol.5 no.4, pp.391, 2024, doi:10.1007/s42979-024-02743-2
Balasamy, K., Krishnaraj, N., & Vijayalakshmi, K. “An adaptive neuro-fuzzy based region selection and authenticating medical image through watermarking for secure communication”, Wireless Personal Communications, Vol.122, no.3, pp. 2817–2837, 2021, doi:10.1007/s11277-021-09031-9.
Suganyadevi, S., & Seethalakshmi, V. “CVD-HNet: Classifying Pneumonia and COVID-19 in Chest X-ray Images Using Deep Network”. Wireless Personal Communications, Vol.126, no. 4, pp.3279–3303, 2022, doi: 10.1007/s11277-022-09864-y
Balasamy, K., & Suganyadevi, S. “Multi-dimensional fuzzy based diabetic retinopathy detection in retinal images through deep CNN method”. Multimedia Tools and Applications, Vol 83, no. 5, pp.1–23. 2024, doi: 10.1007/s11042-024-19798-1
Shamia, D., Balasamy, K., and Suganyadevi, S. “A secure framework for medical image by integrating watermarking and encryption through fuzzy based roi selection”, Journal of Intelligent & Fuzzy systems, 2023, Vol. 44, no.5, pp.7449-7457, doi: 10.3233/JIFS-222618.
Balasamy, K., Seethalakshmi, V. & Suganyadevi, S. Medical Image Analysis Through Deep Learning Techniques: A Comprehensive Survey. Wireless Pers Commun 137, 1685–1714 (2024). https://doi.org/10.1007/s11277-024-11428-1.
Suganyadevi, S., Seethalakshmi, V. Deep recurrent learning based qualified sequence segment analytical model (QS2AM) for infectious disease detection using CT images. Evolving Systems 15, 505–521 (2024). https://doi.org/10.1007/s12530-023-09554-5.
J. Fayyad, Out-Of-Distribution Detection Using Inter-Level Features of Deep Neural Networks (Ph.D. thesis), University of British Columbia, 2023.
F.C. Ghesu, B. Georgescu, A. Mansoor, Y. Yoo, E. Gibson, R. Vishwanath, A. Balachandran, J.M. Balter, Y. Cao, R. Singh, et al., Quantifying and leveraging predictive uncertainty for medical image assessment, Med. Image Anal. 68 (2021) 101855.
J. Yan, S. Cai, X. Cai, G. Zhu, W. Zhou, R. Guo, H. Yan, Y. Wang, Uncertainty quantification of microcirculatory characteristic parameters for recognition of cardiovascular diseases, Comput. Methods Programs Biomed. (2023) 107674.
V. Jahmunah, E. Ng, R.-S. Tan, S.L. Oh, U.R. Acharya, Uncertainty quantification in DenseNet model using myocardial infarction ECG signals, Comput. Methods Programs Biomed. 229 (2023) 107308.
M. Abdar, F. Pourpanah, S. Hussain, D. Rezazadegan, L. Liu, M. Ghavamzadeh, P. Fieguth, X. Cao, A. Khosravi, U.R. Acharya, et al., A review of uncertainty quantification in deep learning: Techniques, applications and challenges, Inf. Fusion 76 (2021) 243–297.
H. Wei, R. Xie, H. Cheng, L. Feng, B. An, Y. Li, Mitigating neural network overconfidence with logit normalization, in: International Conference on Machine Learning, PMLR, 2022, pp. 23631–23644.
C. Guo, G. Pleiss, Y. Sun, K.Q. Weinberger, On calibration of modern neural networks, in: International Conference on Machine Learning, PMLR, 2017, pp. 1321–1330.
M. Sensoy, L. Kaplan, M. Kandemir, Evidential deep learning to quantify classification uncertainty, Adv. Neural Inf. Process. Syst. 31 (2018).
T. Gopalakrishnan, S. Ramakrishnan, K. Balasamy and A. S. Muthananda Murugavel, "Semi fragile watermarking using Gaussian mixture model for malicious image attacks," 2011 World Congress on Information and Communication Technologies, Mumbai, India, 2011, pp. 120-125, doi: 10.1109/WICT.2011.6141229.
M. Feng, K. Xu, N. Wu, W. Huang, Y. Bai, Y. Wang, C. Wang, H. Wang, Trusted multi-scale classification frameworN. Chafai, I. Hayah, I. Houaga, B. Badaoui, A review of machine learning models applied to genomic prediction in animal breeding, Front. Genet. 14 (2023) 1150596.
G. Naidu, T. Zuva, E.M. Sibanda, A review of evaluation metrics in machine learning algorithms, in: Computer Science on-Line Conference, Springer, 2023, pp. 15–25.
Renuka Devi, K., Suganyadevi, S and Balasamy, K.. “Healthcare Data Analysis U sing Deep Learning Paradigm ”. Deep Learning for Cognitive Computing Systems: Technological Advancements and Applications, edited by M.G. Sumithra, Rajesh Kumar Dhanaraj, Celestine Iwendi and Anto Merline Manoharan, Berlin, Boston:De Gruyter, 2023, pp. 129–148. https://doi.org/10.1515/9783110750584–008.
M. Hossin, M.N. Sulaiman, A review on evaluation metrics for data classification evaluations, Int. J. Data Min. Knowl. Manag. Process. 5 (2) (2015) 1.
S.A. Khan, K. Iqbal, N. Mohammad, R. Akbar, S.S.A. Ali, A.A. Siddiqui, A novel fuzzy-logic-based multi-criteria metric for performance evaluation of spam email detection algorithms, Appl. Sci. 12 (14) (2022) 7043.
L. Ballerini, R.B. Fisher, B. Aldridge, J. Rees, A color and texture based hierarchical K-NN approach to the classification of non-melanoma skin lesions, Color Med. Image Anal. (2013) 63–86.
K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770–778
Toofanee, Mohammud Shaad Ally, Sabeena Dowlut, Mohamed Hamroun, Karim Tamine, Vincent Petit, Anh Kiet Duong, and Damien Sauveron. "Dfu-siam a novel diabetic foot ulcer classification with deep learning." IEEE Access 11 (2023): 98315-98332.
Kairys, Arturas, and Vidas Raudonis. 2023. "Analysis of Training Data Augmentation for Diabetic Foot Ulcer Semantic Segmentation" Electronics 12, no. 22: 4624. https://doi.org/10.3390/electronics12224624
Copyright (c) 2026 B. K. Jaleesha, R. Suganthi ,N. K. Priyadharsini, Yuvaraj S, M. Pyingkodi, and M. Vallikkannu
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
