Comparative Analysis of ResNet-Based Wagner-Scale Classification for Imbalanced DFU Data

Authors

DOI:

https://doi.org/10.29207/resti.v9i6.7016

Keywords:

class imbalance, deep learning, diabetic foot ulcer,, random oversampling, ResNet-50, Wagner Scale, medical image classification

Abstract

Diabetic Foot Ulcers (DFU) are a serious complication of diabetes mellitus and carry a high risk of lower extremity amputation if not treated in a timely manner. The conventional classification process, which relies on visual inspection by clinicians, tends to be subjective and inconsistent. Therefore, this study proposes a multiclass classification model for DFU based on the Wagner Scale (Grades 0–5) using the ResNet-50 architecture with a transfer learning approach as the core machine learning method. The dataset used in this study consists of 1,415 clinical wound images that were annotated and verified by medical professionals. The dataset is highly imbalanced, with 543 images in Grade 0, 110 in Grade 1, 252 in Grade 2, 145 in Grade 3, 293 in Grade 4, and only 72 images in Grade 5. To address this imbalance, random oversampling (ROS) was applied, in addition to standard preprocessing techniques such as normalization and data augmentation to increase training data diversity.Experimental results demonstrate that the proposed model achieves high classification performance based on accuracy, precision, recall, and F1-score. Specifically, the model obtained a precision of 0.96, recall of 0.95, and F1-score of 0.95, indicating consistent and robust classification performance across all Wagner grades. The best configuration (ResNet-50 + ROS) successfully improved the classification performance across minority grades (e.g., Grade 1 and Grade 5). Moreover, the model consistently identifies minority classes and does not exhibit signs of overfitting. Model optimization using the Adam optimizer and data balancing strategies significantly improves the generalization capability of the classifier. These findings indicate that the proposed model is not only effective for automatic DFU classification, but also has great potential to support objective clinical decision making and accelerate diagnosis, particularly in healthcare facilities with limited resources.

Downloads

Download data is not yet available.

References

International Diabetes Federation, “IDF Diabetes Atlas,” 2021, Brussels, Belgium.

H. Zhang, C. Huang, J. Bai, and J. Wang, “Effect of diabetic foot ulcers and other risk factors on the prevalence of lower extremity amputation: A meta-analysis.,” Int Wound J, vol. 20, no. 8, pp. 3035–3047, Oct. 2023, doi: 10.1111/iwj.14179.

A. S. Hariftyani, H. Novida, and M. Edward, “Profile of Diabetic Foot Ulcer Patients at Tertiary Care Hospital in Surabaya, Indonesia,” Jurnal Berkala Epidemiologi, vol. 9, no. 3, p. 293, Sep. 2021, doi: 10.20473/jbe.V9I32021.293-302.

E. Yunir et al., “Characteristics of Diabetic Foot Ulcer Patients Pre- and During COVID-19 Pandemic: Lessons Learnt From a National Referral Hospital in Indonesia,” J Prim Care Community Health, vol. 13, Jan. 2022, doi: 10.1177/21501319221089767.

L. A. Lavery, D. G. Armstrong, and L. B. Harkless, “Classification of diabetic foot wounds.,” J Foot Ankle Surg, vol. 35, no. 6, pp. 528–31, 1996, doi: 10.1016/s1067-2516(96)80125-6.

P. Shah et al., “Wagner’s Classification as a Tool for Treating Diabetic Foot Ulcers: Our Observations at a Suburban Teaching Hospital,” Cureus, Jan. 2022, doi: 10.7759/cureus.21501.

C. Lauri, A. Leone, M. Cavallini, A. Signore, L. Giurato, and L. Uccioli, “Diabetic Foot Infections: The Diagnostic Challenges.,” J Clin Med, vol. 9, no. 6, Jun. 2020, doi: 10.3390/jcm9061779.

P. Sivakamasundari and G. Niranjana, “An automatic detection and classification of diabetic foot ulcers using chebyshev chaotic ladybug beetle optimized extended swin transformer-inceptionV3 model,” Biomed Signal Process Control, vol. 110, p. 108268, Dec. 2025, doi: 10.1016/j.bspc.2025.108268.

J. Yogapriya, V. Chandran, M. G. Sumithra, B. Elakkiya, A. Shamila Ebenezer, and C. Suresh Gnana Dhas, “Automated Detection of Infection in Diabetic Foot Ulcer Images Using Convolutional Neural Network,” J Healthc Eng, vol. 2022, pp. 1–12, Apr. 2022, doi: 10.1155/2022/2349849.

C. Wang, Z. Yu, Z. Long, H. Zhao, and Z. Wang, “A few-shot diabetes foot ulcer image classification method based on deep ResNet and transfer learning,” Sci Rep, vol. 14, no. 1, p. 29877, Dec. 2024, doi: 10.1038/s41598-024-80691-w.

C. Shi, J. C. Dumville, H. Juwale, C. Moran, and R. Atkinson, “Evidence assessing the development, evaluation and implementation of digital health technologies in wound care: A rapid scoping review,” J Tissue Viability, vol. 31, no. 4, pp. 567–574, Nov. 2022, doi: 10.1016/j.jtv.2022.09.006.

G. Scebba et al., “Detect-and-segment: A deep learning approach to automate wound image segmentation,” Inform Med Unlocked, vol. 29, Jan. 2022, doi: 10.1016/j.imu.2022.100884.

G. Rangel, J. C. Cuevas-Tello, J. Nunez-Varela, C. Puente, and A. G. Silva-Trujillo, “A Survey on Convolutional Neural Networks and Their Performance Limitations in Image Recognition Tasks,” J Sens, vol. 2024, no. 1, Jan. 2024, doi: 10.1155/2024/2797320.

Q. Teng, Z. Liu, Y. Song, K. Han, and Y. Lu, “A survey on the interpretability of deep learning in medical diagnosis.,” Multimed Syst, vol. 28, no. 6, pp. 2335–2355, 2022, doi: 10.1007/s00530-022-00960-4.

Achmad Naila Muna Ramadhani, Galuh Wilujeng Saraswati, Rama Tri Agung, and Heru Agus Santoso, “Performance Comparison of Convolutional Neural Network and MobileNetV2 for Chili Diseases Classification,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 7, no. 4, pp. 940–946, Aug. 2023, doi: 10.29207/resti.v7i4.5028.

P. N. Thotad, G. R. Bharamagoudar, and B. S. Anami, “Diabetic foot ulcer detection using deep learning approaches,” Sensors International, vol. 4, p. 100210, 2023, doi: 10.1016/j.sintl.2022.100210.

N. F. Almufadi, H. F. Alhasson, and S. S. Alharbi, “E-DFu-Net: An efficient deep convolutional neural network models for Diabetic Foot Ulcer classification,” Biomolecules and Biomedicine, vol. 25, no. 2, pp. 445–460, Jan. 2025, doi: 10.17305/bb.2024.11117.

N. W. Asnake, A. M. Ayalew, and A. A. Engda, “Detection of oral squamous cell carcinoma cancer using AlexNet on histopathological images,” Discover Applied Sciences, vol. 7, no. 3, p. 155, Feb. 2025, doi: 10.1007/s42452-025-06514-3.

D. Theckedath and R. R. Sedamkar, “Detecting Affect States Using VGG16, ResNet50 and SE-ResNet50 Networks,” SN Comput Sci, vol. 1, no. 2, p. 79, Mar. 2020, doi: 10.1007/s42979-020-0114-9.

A. Victor Ikechukwu, S. Murali, R. Deepu, and R. C. Shivamurthy, “ResNet-50 vs VGG-19 vs training from scratch: A comparative analysis of the segmentation and classification of Pneumonia from chest X-ray images,” Global Transitions Proceedings, vol. 2, no. 2, pp. 375–381, Nov. 2021, doi: 10.1016/j.gltp.2021.08.027.

T. Fatima and H. Soliman, “Application of VGG16 Transfer Learning for Breast Cancer Detection,” Information, vol. 16, no. 3, p. 227, Mar. 2025, doi: 10.3390/info16030227.

S. A. Hasanah, A. A. Pravitasari, A. S. Abdullah, I. N. Yulita, and M. H. Asnawi, “A Deep Learning Review of ResNet Architecture for Lung Disease Identification in CXR Image,” Applied Sciences, vol. 13, no. 24, p. 13111, Dec. 2023, doi: 10.3390/app132413111.

D. W. Ayu and G. A. Pradipta, “SqueezeNet Feature Extraction dan Gradient Boosting untuk Klasifikasi Penyakit Monkeypox pada Citra Kulit,” Jurnal Sistem dan Informatika (JSI), vol. 18, no. 2, pp. 177–183, May 2024, doi: 10.30864/jsi.v18i2.612.

A. Jaiswal, N. Gianchandani, D. Singh, V. Kumar, and M. Kaur, “Classification of the COVID-19 infected patients using DenseNet201 based deep transfer learning,” J Biomol Struct Dyn, vol. 39, no. 15, pp. 5682–5689, Oct. 2021, doi: 10.1080/07391102.2020.1788642.

L. Wen, Z. Xiao, X. Xu, and B. Liu, “Disaster Recognition and Classification Based on Improved ResNet-50 Neural Network,” Applied Sciences, vol. 15, no. 9, p. 5143, May 2025, doi: 10.3390/app15095143.

M. N. Musa, “MRI-Based Brain Tumor Classification using ResNet-50 and Optimized Softmax Regression,” JURNAL INFOTEL, vol. 16, no. 3, Sep. 2024, doi: 10.20895/infotel.v16i3.1175.

L. Zhang, Y. Bian, P. Jiang, and F. Zhang, “A Transfer Residual Neural Network Based on ResNet-50 for Detection of Steel Surface Defects,” Applied Sciences, vol. 13, no. 9, p. 5260, Apr. 2023, doi: 10.3390/app13095260.

T. A. Sugiarto, M. A. Soeleman, and P. Pujiono, “Enhancing Augmentation-Based ResNet50 for Car Brand Classification,” Journal of Applied Intelligent System, vol. 8, no. 3, pp. 400–412, 2023.

S. R. Klomp, R. G. J. Wijnhoven, and P. H. N. de With, “Performance-Efficiency Comparisons of Channel Attention Modules for ResNets,” Neural Process Lett, vol. 55, no. 5, pp. 6797–6813, Oct. 2023, doi: 10.1007/s11063-023-11161-z.

C. Raptis, E. Karavasilis, G. Anastasopoulos, and A. Adamopoulos, “Comparative Analysis of Conventional CNN v’s ImageNet Pretrained ResNet in Medical Image Classification,” Information, vol. 15, no. 12, p. 806, Dec. 2024, doi: 10.3390/info15120806.

S. Hayou, E. Clerico, B. He, G. Deligiannidis, A. Doucet, and J. Rousseau, “Stable ResNet,” Mar. 2021.

T. Wongvorachan, S. He, and O. Bulut, “A Comparison of Undersampling, Oversampling, and SMOTE Methods for Dealing with Imbalanced Classification in Educational Data Mining,” Information, vol. 14, no. 1, p. 54, Jan. 2023, doi: 10.3390/info14010054.

W. Chen, K. Yang, Z. Yu, Y. Shi, and C. L. P. Chen, “A survey on imbalanced learning: latest research, applications and future directions,” Artif Intell Rev, vol. 57, no. 6, p. 137, May 2024, doi: 10.1007/s10462-024-10759-6.

C. de Alvis and S. Seneviratne, “A Survey of Deep Long-Tail Classification Advancements,” Apr. 2024.

M. Carvalho, A. J. Pinho, and S. Brás, “Resampling approaches to handle class imbalance: a review from a data perspective,” J Big Data, vol. 12, no. 1, p. 71, Mar. 2025, doi: 10.1186/s40537-025-01119-4.

A. Riyandi, Mahazam Afrad, M Yoka Fathoni, and Yogo Dwi Prasetyo, “Obesity Status Prediction Through Artificial Intelligence and Balanced Label Distribution Using SMOTE,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 9, no. 3, pp. 519–524, Jun. 2025, doi: 10.29207/resti.v9i3.6204.

“A Hybrid Sampling Approach for Improving the Classification of Imbalanced Data Using ROS and NCL Methods,” International Journal of Intelligent Engineering and Systems, vol. 16, no. 3, pp. 345–361, Jun. 2023, doi: 10.22266/ijies2023.0630.28.

G.-X. Zhou et al., “Construction and validation of a deep learning-based diagnostic model for segmentation and classification of diabetic foot,” Front Endocrinol (Lausanne), vol. 16, Apr. 2025, doi: 10.3389/fendo.2025.1543192.

C.-L. Lin and K.-C. Wu, “Development of revised ResNet-50 for diabetic retinopathy detection,” BMC Bioinformatics, vol. 24, no. 1, p. 157, Apr. 2023, doi: 10.1186/s12859-023-05293-1.

O. Elharrouss, Y. Akbari, N. Almaadeed, and S. Al-Maadeed, “Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches,” Jun. 2022, doi: 10.1016/j.cosrev.2024.100645.

B. Mahaur, K. K. Mishra, and N. Singh, “Improved Residual Network based on norm-preservation for visual recognition,” Neural Networks, vol. 157, pp. 305–322, Jan. 2023, doi: 10.1016/j.neunet.2022.10.023.

Aulia Afifah, E. R. Arumi, M. Maimunah, and Setiya Nugroho, “Comparative Evaluation of Preprocessing Methods for MobileNetV1 and V2 in Waste Classification,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 9, no. 3, pp. 444–452, May 2025, doi: 10.29207/resti.v9i3.6211.

I. Corley, C. Robinson, R. Dodhia, J. M. L. Ferres, and P. Najafirad, “Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matters,” May 2023.

X. Pei et al., “Robustness of machine learning to color, size change, normalization, and image enhancement on micrograph datasets with large sample differences,” Mater Des, vol. 232, p. 112086, Aug. 2023, doi: 10.1016/j.matdes.2023.112086.

F. Garcea, A. Serra, F. Lamberti, and L. Morra, “Data augmentation for medical imaging: A systematic literature review.,” Comput Biol Med, vol. 152, p. 106391, Jan. 2023, doi: 10.1016/j.compbiomed.2022.106391.

A. Kebaili, J. Lapuyade-Lahorgue, and S. Ruan, “Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review,” J Imaging, vol. 9, no. 4, p. 81, Apr. 2023, doi: 10.3390/jimaging9040081.

G. Eom and H. Byeon, “Searching for Optimal Oversampling to Process Imbalanced Data: Generative Adversarial Networks and Synthetic Minority Over-Sampling Technique,” Mathematics, vol. 11, no. 16, p. 3605, Aug. 2023, doi: 10.3390/math11163605.

Y. Yang, H. A. Khorshidi, and U. Aickelin, “A review on over-sampling techniques in classification of multi-class imbalanced datasets: insights for medical problems,” Front Digit Health, vol. 6, Jul. 2024, doi: 10.3389/fdgth.2024.1430245.

I. Bello et al., “Revisiting ResNets: Improved Training and Scaling Strategies,” Mar. 2021.

D. Sarwinda, R. H. Paradisa, A. Bustamam, and P. Anggia, “Deep Learning in Image Classification using Residual Network (ResNet) Variants for Detection of Colorectal Cancer,” Procedia Comput Sci, vol. 179, pp. 423–431, 2021, doi: 10.1016/j.procs.2021.01.025.

A. Thakur, H. Chauhan, and N. Gupta, “Efficient ResNets: Residual Network Design,” Jun. 2023.

L. Ma, R. Shuai, X. Ran, W. Liu, and C. Ye, “Combining DC-GAN with ResNet for blood cell image classification,” Med Biol Eng Comput, vol. 58, no. 6, pp. 1251–1264, Jun. 2020, doi: 10.1007/s11517-020-02163-3.

L. C. Ribas, W. Casaca, and R. T. Fares, “Conditional Generative Adversarial Networks and Deep Learning Data Augmentation: A Multi-Perspective Data-Driven Survey Across Multiple Application Fields and Classification Architectures,” AI, vol. 6, no. 2, p. 32, Feb. 2025, doi: 10.3390/ai6020032.

W. M. Thuzar and M. Moe Htay, “Ensemble Learning for Breast Cancer Image Classification Using Pre-trained CNNs and Random Oversampling Method,” in 2024 5th International Conference on Advanced Information Technologies (ICAIT), 2024, pp. 1–6. doi: 10.1109/ICAIT65209.2024.10754947.

E. Y. Puspaningrum, R. R. Wahid, R. P. Amaliyah, and C. Nisa’, “Alzheimer’s Disease Stage Classification using Deep Convolutional Neural Networks on Oversampled Imbalance Data,” in 2020 6th Information Technology International Seminar (ITIS), 2020, pp. 57–62. doi: 10.1109/ITIS50118.2020.9321061.

D. M. W. Powers, “Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation,” Oct. 2020.

M. Uppal et al., “Enhancing accuracy in brain stroke detection: Multi-layer perceptron with Adadelta, RMSProp and AdaMax optimizers,” Front Bioeng Biotechnol, vol. 11, Sep. 2023, doi: 10.3389/fbioe.2023.1257591.

S. Shedriko and M. Firdaus, “Perbandingan Optimizer Adagrad, Adadelta dan Adam dalam Klasifikasi Gambar Menggunakan Deep Learning,” STRING (Satuan Tulisan Riset dan Inovasi Teknologi), vol. 8, no. 1, p. 103, Aug. 2023, doi: 10.30998/string.v8i1.16564.

Downloads

Published

2025-12-30

Issue

Section

Computer Vision and Pattern Recognition

How to Cite

Ramadhan, A. W. ., Pulung Nurtantio Andono, & M. Arief Soeleman. (2025). Comparative Analysis of ResNet-Based Wagner-Scale Classification for Imbalanced DFU Data. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 9(6), 1428-1438. https://doi.org/10.29207/resti.v9i6.7016