Automatic Diagnosis of Skin Diseases with Convolutional Neural Networks on Multi-Class Visual Data

Year 2025, Volume: 15 Issue: 2, 171 - 194, 31.12.2025

Hilal Biyik , Duygu Kaya , Ayhan Akbal

https://doi.org/10.17678/beuscitech.1754394

Abstract

The automatic diagnosis of skin diseases is of great importance, especially in cases requiring early detection, as it accelerates clinical processes and reduces the margin of error. In this study, a classification model based on Convolutional Neural Network (CNN) architectures was developed on a multi-class visual dataset containing three different skin disease categories. To enhance the model’s performance, data augmentation techniques were applied, and the images were resized to 224×224 pixels. Using a transfer learning approach, the model was trained with preprocessing ResNet-18, AlexNet, and DenseNet-201 architectures. The hyperparameters used during the training process were carefully selected, and the model's training and validation accuracies were monitored. According to the results obtained, the ResNet-18 model demonstrated strong performance with an accuracy of 87.19% on the test set. These findings indicate that deep learning-based architectures can be effectively applied in the multi-class diagnosis of skin diseases.

Keywords

Skin diseases , AlexNet , ResNet-18 , DenseNet-201 , Deep Learning

Ethical Statement

The study is complied with research and publication ethics.

References

• J. Sun et al., “Machine Learning Methods in Skin Disease Recognition: A Systematic Review,” Processes, vol. 11, no. 4, pp. 1–16, 2023, doi: 10.3390/pr11041003.
• M. A. Richard et al., “Prevalence of most common skin diseases in Europe: a population-based study,” J. Eur. Acad. Dermatology Venereol., vol. 36, no. 7, pp. 1088–1096, 2022, doi: 10.1111/jdv.18050.
• J. Chen et al., “Pigmented skin disease classification via deep learning with an attention mechanism,” Appl. Soft Comput., vol. 170, no. December 2024, p. 112571, 2025, doi: 10.1016/j.asoc.2024.112571.
• M. S. C. Foundation, “Skin caancer facts & statistics.” [Online]. Available: https://www.skincancer.org/skin-cancer-information/skin-cancer-facts/
• R. Sabir and T. Mehmood, “Classification of melanoma skin Cancer based on Image Data Set using different neural networks,” Sci. Rep., vol. 14, no. 1, pp. 1–9, 2024, doi: 10.1038/s41598-024-75143-4.
• Y. Dogan, “An innovative approach for parkinson’s disease diagnosis using CNN, NCA, and SVM,” Neural Comput. Appl., vol. 36, pp. 20089–20110, 2024.
• ISIC, “ISIC Archive-Collections.” [Online]. Available: https://api.isic-archive.com/collections/
• S. Bhadula*, S. Sharma, P. Juyal, and C. Kulshrestha, “Machine Learning Algorithms based Skin Disease Detection,” Int. J. Innov. Technol. Explor. Eng., vol. 9, no. 2, pp. 4044–4049, 2019, doi: 10.35940/ijitee.b7686.129219.
• E. Öter and Y. Doğan, “A Comparative Study on Data Balancing Methods for Alzheimer’s Disease Classification,” Çukurova Üniversitesi Mühendislik Fakültesi Derg., vol. 39, no. 2, pp. 489–501, 2024, doi: 10.21605/cukurovaumfd.1514553.
• N. Hameed, “Multi-Class Skin Diseases Classification Using Deep Convolutional Neural Network and Support Vector Machine,” 2018 12th Int. Conf. Software, Knowledge, Inf. Manag. Appl., pp. 1–7.
• S. S. Vellela, D. Roja, C. Sowjanya, K. B. S. K, L. Dalavai, and K. K. Kumar, “Multi-Class Skin Diseases Classification with Color and Texture Features Using Convolution Neural Network,” 2023 6th Int. Conf. Contemp. Comput. Informatics, vol. 6, pp. 1682–1687, 2023, doi: 10.1109/IC3I59117.2023.10398028.
• I. Lihacova et al., “Multi-Class CNN for Classification of Multispectral and Autofluorescence Skin Lesion Clinical Images,” 2022.
• Y. Dogan, “A novel pruning-enhanced hybrid approach for efficient and accurate brain tumor diagnosis,” Biomed. Signal Process. Control, vol. 108466, 2026.
• H. Alam, “20 Skin Diseases Dataset,” Kaggle. [Online]. Available: https://www.kaggle.com/datasets/haroonalam16/20-skin-diseases-dataset
• MathWorks Deep Learning Toolbox Team, “Deep Learning Toolbox Model for ResNet-18 Network.” [Online]. Available: https://www.mathworks.com/matlabcentral/fileexchange/68261-deep-learning-toolbox-model-for-resnet-18-network?s_tid=srchtitle
• M. E. Atik and Z. Duran, “Deep Learning-Based 3D Face Recognition Using Derived Features from Point Cloud,” Lect. Notes Networks Syst., vol. 183, pp. 797–808, 2021, doi: 10.1007/978-3-030-66840-2_60.
• K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., pp. 1–14, 2015.
• F. Ramzan et al., “A Deep Learning Approach for Automated Diagnosis and Multi-Class Classification of Alzheimer’s Disease Stages Using Resting-State fMRI and Residual Neural Networks,” J. Med. Syst., vol. 44, no. 2, 2020, doi: 10.1007/s10916-019-1475-2.
• Y. Dogan, “AutoEffFusionNet: A New Approach for Cervical Cancer Diagnosis Using ResNet-Based Autoencoder With Attention Mechanism and Genetic Feature Selection,” IEEE Access, vol. 13, no. March, pp. 44107–44122, 2025, doi: 10.1109/ACCESS.2025.3543850.
• S. Kumar, V. P. Singh, S. Pal, and P. Jaiswal, “Energy-efficient model ‘denseNet201 based on deep convolutional neural network’ using cloud platform for detection of COVID-19 infected patients,” Epidemiol. Method., vol. 12, no. 1, 2023, doi: 10.1515/em-2021-0047.
• R. A. Charisma and F. D. Adhinata, “Transfer Learning with Densenet201 Architecture Model for Potato Leaf Disease Classification,” ICCoSITE 2023 - Int. Conf. Comput. Sci. Inf. Technol. Eng. Digit. Transform. Strateg. Facing VUCA TUNA Era, pp. 738–743, 2023, doi: 10.1109/ICCoSITE57641.2023.10127772.
• J. C. Teo, I. Mohd Khairuddin, M. A. Mohd Razman, A. P. P. Abdul Majeed, and W. H. Mohd Isa, “Automated Detection of Knee Cartilage Region in X-ray Image,” Mekatronika, vol. 4, no. 1, pp. 104–109, 2022, doi: 10.15282/mekatronika.v4i1.8627.
• E. Pramesti, A. B. Mutiara, and R. Refianti, “Implementation of Deep Learning Using Convolutional Neural Network for Skin Disease Classification with DenseNet-201 Architecture,” 2023 8th Int. Conf. Informatics Comput. ICIC 2023, pp. 1–6, 2023, doi: 10.1109/ICIC60109.2023.10381915.
• “Deep Learning Toolbox Model for AlexNet Network,” Team, MathWorks Deep Learning Toolbox. [Online]. Available: https://www.mathworks.com/matlabcentral/fileexchange/59133-deep-learning-toolbox-model-for-alexnet-network?s_tid=srchtitle_site_search_2_alexnet+
• K. M. Hosny, M. A. Kassem, and M. M. Fouad, “Classification of Skin Lesions into Seven Classes Using Transfer Learning with AlexNet,” J. Digit. Imaging, vol. 33, no. 5, pp. 1325–1334, 2020, doi: 10.1007/s10278-020-00371-9.
• L. Putzu, L. Piras, and G. Giacinto, “Convolutional neural networks for relevance feedback in content based image retrieval: A Content based image retrieval system that exploits convolutional neural networks both for feature extraction and for relevance feedback,” Multimed. Tools Appl., vol. 79, no. 37–38, pp. 26995–27021, 2020, doi: 10.1007/s11042-020-09292-9.
• T. Schlosser, M. Friedrich, T. Meyer, and D. Kowerko, “A Consolidated Overview of Evaluation and Performance Metrics for Machine Learning and Computer Vision,” (Preprint), no. July, pp. 1–42, 2023, doi: 10.13140/RG.2.2.14331.69928.
• S. G. Malik, S. S. Jamil, A. Aziz, S. Ullah, I. Ullah, and M. Abohashrh, “High-Precision Skin Disease Diagnosis through Deep Learning on Dermoscopic Images,” Bioengineering, vol. 11, no. 9, p. 867, 2024, doi: 10.3390/bioengineering11090867.
• D. Sharma, V. Parashar, and G. S. Tomar, “Comparative Analysis of Skin Cancer Detection Using Classification Algorithms,” Proc. - 2023 15th IEEE Int. Conf. Comput. Intell. Commun. Networks, CICN 2023, pp. 531–539, 2023, doi: 10.1109/CICN59264.2023.10402216.
• R. Agarwal and D. Godavarthi, “Skin Disease Classification Using CNN Algorithms,” EAI Endorsed Trans. Pervasive Heal. Technol., vol. 9, no. 1, pp. 1–8, 2023, doi: 10.4108/eetpht.9.4039.