A Transfer Learning Approach Using EfficientNetB0 for Automated Eczema Severity Detection

Diana Tri Susetianingtias; Maukar; Rodiah

doi:10.51454/decode.v6i3.1848

Authors

Diana Tri Susetianingtias Computer Systems Universitas Gunadarma
Maukar Master’s in Information Systems Management Universitas Gunadarma
Rodiah Informatics Universitas Gunadarma

DOI:

https://doi.org/10.51454/decode.v6i3.1848

Keywords:

Classification, Dermoscopic images, Eczema, EfficientNetB0, Skin

Abstract

Eczema (atopic dermatitis) is a chronic inflammatory skin condition whose severity can be difficult to assess consistently from images. Although convolutional neural networks have been applied to dermatological classification, evidence on three-class eczema severity classification using a lightweight transfer-learning model and its implementation as a research prototype remains limited. This study developed an EfficientNetB0 classifier for Normal, Mild, and Severe classes using 1,950 source images. The images were processed at 224 × 224 pixels, augmented only in the training set, and trained in two stages: feature extraction and fine-tuning. The generator produced 1,560 training images and 389 development-validation images. The best model was selected by validation AUC and achieved 89.97% validation accuracy and an AUC of 0.9716. Normal had the highest recall (0.99), while Severe had the highest precision (0.95); most errors involved the Mild and Severe classes. The model was integrated into a browser-based prototype using Flask, HTML, Tailwind CSS, and JavaScript. Because the same validation subset was used for early stopping, checkpoint selection, and final reporting, these results should not be interpreted as independent test performance. The prototype is intended for research and educational use and does not replace professional diagnosis.

References

Afshari, M., Kolackova, M., & Rosecka, M. (2024). Unraveling The Skin: A Comprehensive Review Of Atopic Dermatitis, Current Understanding, And Approaches. Frontiers in Immunology, 15, 1361005. https://doi.org/10.3389/fimmu.2024.1361005

Agus, I. P., Hidjah, K., Sulistianingsih, N., Hendro, G., & Syahrir, S. (2025). Implementasi Arsitektur Deep Convolutional Neural Network (CNN) Dengan Transfer Learning Untuk Klasifikasi Penyakit Kulit. JTIM: Jurnal Teknologi Informasi dan Multimedia, 7(3), 461–477. https://doi.org/10.35746/jtim.v7i3.734

Ajani, A. A., Gambo, I., & Faniyi, O. (2026). Artificial Intelligence–Assisted Diagnosis Of Atopic Eczema In Darker Skin Types: A CNN-Based Study. Dermatology Practical & Conceptual, 16(1), 5897. https://doi.org/10.5826/dpc.1601a5897

Alruwaili, M., & Mohamed, M. (2025). An Integrated Deep Learning Model With Efficientnet And Resnet For Accurate Multi-Class Skin Disease Classification. Diagnostics, 15(5), 551. https://doi.org/10.3390/diagnostics15050551

Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021). Review Of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions. Journal of Big Data, 8, 53. https://doi.org/10.1186/s40537-021-00444-8

Ameen, A., Al Dhaheri, A., Reda, A., Alnaeem, A., Marzooqi, F., Albreiki, F., Ali, H., Dayem, H., & Alnaqbi, J. (2024). Consensus Recommendations For The Management Of Atopic Dermatitis In The United Arab Emirates. Dermatology and Therapy, 14(9), 2381–2400. https://doi.org/10.1007/s13555-024-01247-4

Amina, D. E., Bilal, A., & Malik, N. U. R. (2025). Eczema Classification Using Modified Convolutional Neural Network ResNet-50. Spectrum of Engineering Sciences, 3(4), 872–882. https://doi.org/10.5281/zenodo.15286382

Ansari, A. M., Shakeel, L., Bin Qasim, S. M., & Parveen, M. (2026). Multi-Class Skin Disease Image Dataset With Severity Levels (Version 3) [Data set]. Mendeley Data, 3. https://doi.org/10.17632/6sjcrtg54p.3

Burhanuddin, M. I., Syaifullah, A., Putra Jaya, S. A., & Somoal, M. G. (2025). Analisis Komparatif Model MobileNetV1 dan EfficientNetB0 Dalam Klasifikasi Citra Empat Musim Menggunakan Transfer Learning. JEKIN: Jurnal Teknik Informatika, 5(2), 508–521. https://doi.org/10.58794/jekin.v5i2.1378

Chato, L., & Regentova, E. (2023). Survey Of Transfer Learning Approaches In The Machine Learning Of Digital Health Sensing Data. Journal of Personalized Medicine, 13(12), 1703. https://doi.org/10.3390/jpm13121703

Cai, Z. R., Kim, J., Rezaei, S. J., Chen, M. L., Touma, F., Zhu, C., Onyeka, S., Fonjungo, F., Omiye, J. A., Krakowski, I., Nwandu, L., Biossonnette, R., Ko, J. M., & Linos, E. (2025). Assessing The Performance Of Artificial Intelligence Models In Evaluating Inflammatory Skin Disease Severity: A Systematic Review And Meta-Analysis. British Journal of Dermatology, 193(5), 847–855. https://doi.org/10.1093/bjd/ljaf250

Faye, O., Flohr, C., Kabashima, K., Ma, L., & Paller, A. S. (2023). Atopic Dermatitis: A Global Health Perspective. Journal of the European Academy of Dermatology and Venereology, 37(5), 801–811. https://doi.org/10.1111/jdv.19723

Khairunnisa, P., Putra, W. E., Yitong, W., Jufrizal, A., & Makmum, M. N. A. (2025). Convolutional Neural Networks Using EfficientNetB0 Architecture And Hyperparameters On Skin Disease Classification. Public Research Journal of Engineering, Data Technology and Computer Science, 2(2), 127–137. https://doi.org/10.57152/predatecs.v2i2.1569

Inthiyaz, S., Altahan, B. R., Ahammad, S. H., Rajesh, V., Kalangi, R. R., Smirani, L. K., Hossain, M. A., &Rashed, A. N. Z. (2023). Skin Disease Detection Using Deep Learning. Advances in Engineering Software, 175, 103361. https://doi.org/10.1016/j.advengsoft.2022.103361

Krichen, M. (2023). Convolutional Neural Networks: A Survey. Computers, 12(8), 151. https://doi.org/10.3390/computers12080151

Li, Z., Gu, J., Tang, T., Huang, X., Wu, Y., Li, Y., Dou, X., Yu, B., Li, C., & Zhang, H. (2025). The Global Burden Of Atopic Dermatitis In Elderly Populations: Trends, Disparities, And Future Projections. Healthcare, 13(7), 788. https://doi.org/10.3390/healthcare13070788

Maulana, A., Noviandy, T. R., Suhendra, R., Earlia, N., Bulqiah, M., Idroes, G. M., Niode, N. J., Sofyan, H., Subianto, M., & Idroes, R. (2023). Evaluation Of Atopic Dermatitis Severity Using Artificial Intelligence. Narra J, 3(3), e511. https://doi.org/10.52225/narra.v3i3.511

Mukhlif, A. A., Al-Khateeb, B., & Mohammed, A. (2022). An Extensive Review Of State-Of-The-Art Transfer Learning Techniques Used In Medical Imaging: Open Issues And Challenges. Journal of Intelligent Systems, 31(1), 1085–1111. https://doi.org/10.1515/jisys-2022-0198

Medela, A., Mac Carthy, T., Aguilar Robles, S. A., Chiesa-Estomba, C. M., et al. (2022). Automatic SCOring of Atopic Dermatitis Using Deep Learning: A Pilot Study. JID Innovations, 2(3), 100107. https://doi.org/10.1016/j.xjidi.2022.100107

Purwono, Ma’arif, A., Rahmaniar, W., Fathurrahman, H. I. K., Frisky, A. Z. K., & Haq, Q. M. ul. (2022). Understanding of Convolutional Neural Network (CNN): A review. International Journal of Robotics and Control Systems, 2(4), 739–748. https://doi.org/10.31763/ijrcs.v2i4.888

Saeki, H., Ohya, Y., Arakawa, H., Ichiyama, S., Katsunuma, T., Katoh, N., Tanaka, A., & Tanizaki, H. (2024). English Version Of Clinical Practice Guidelines For The Management Of Atopic Dermatitis 2024. The Journal of Dermatology, 52(1), 70–142. https://doi.org/10.1111/1346-8138.17544

Rasheed, A., Umar, A. I., Shirazi, S. H., Khan, Z., Nawaz, S., & Shahzad, M. (2022). Automatic Eczema Classification In Clinical Images Based On Hybrid Deep Neural Network. Computers in Biology and Medicine, 147, 105807. https://doi.org/10.1016/j.compbiomed.2022.105807

Rafay, A., & Hussain, W. (2023). EfficientSkinDis: An EfficientNet-based Classification Model For A Large Manually Curated Dataset Of 31 Skin Diseases. Biomedical Signal Processing and Control, 85, 104869. https://doi.org/10.1016/j.bspc.2023.104869

Salehin, I., & Kang, D.-K. (2023). A Review On Dropout Regularization Approaches For Deep Neural Networks Within The Scholarly Domain. Electronics, 12(14), 3106. https://doi.org/10.3390/electronics12143106

Spiewak, R. (2023). Diseases From The Spectrum Of Dermatitis And Eczema: Can “Omics” Sciences Help With Better Systematics And More Accurate Differential Diagnosis?. International Journal of Molecular Sciences, 24(13), 10468. https://doi.org/10.3390/ijms241310468

Terven, J. R., Cordova-Esparza, D. M., Romero-González, J. A., Ramírez-Pedraza, A., & Chávez-Urbiola, E. A. (2025). A Comprehensive Survey Of Loss Functions And Metrics In Deep Learning. Artificial Intelligence Review, 58, 195. https://doi.org/10.1007/s10462-025-11198-7

Tokura, Y., Yunoki, M., Kondo, S., & Otsuka, M. (2024). What is “Eczema”?. The Journal of Dermatology, 51(8), 192–203. https://doi.org/10.1111/1346-8138.17439

Venkatesh, J., Vijayalakshmi, R. A. K., Krishnan, D., & Partheeban, P. (2026). EfficientNet-based Soft Computing Techniques For Dermatological Condition Detection. Discover Artificial Intelligence, 6, 384. https://doi.org/10.1007/s44163-026-01147-w

Yadav, K. K., & Gajanan, A. (2026). Transfer Learning For Image Processing: A Review And Practical Considerations. Asian Journal of Research in Computer Science, 19(2), 192–203. https://doi.org/10.9734/ajrcos/2026/v19i2831

Zou, Q., Cheng, J., & Liang, Z. (2023). Automatic Diagnosis Of Melanoma Based On Efficientnet And Patch Strategy. International Journal of Computational Intelligence Systems, 16, 87. https://doi.org/10.1007/s44196-023-00246-1

Zhao, X., Wang, L., Zhang, Y., Han, X., & Deveci, M. (2024). A Review Of Convolutional Neural Networks In Computer Vision. Artificial Intelligence Review, 57(4), 96. https://doi.org/10.1007/s10462-024-10721-6