A Study on Area Assessment of Psoriasis Lesions Using Image Augmentation and Deep Learning: Addressing the Lack of Thai Skin Disease Data
DOI:
https://doi.org/10.59796/jcst.V15N3.2025.119Keywords:
deep learning models, image augmentation, psoriasis classification, skin disease, style transferAbstract
Psoriasis is a chronic skin disease with significant global and regional impacts, including in Thailand, where its burden is compounded by diagnostic challenges and limited dermatological resources. Psoriasis was selected for this study because it develops in distinct phases, requiring ongoing monitoring and treatment. The distribution of skin lesions plays a crucial role in disease identification and assessment, making it an essential factor for AI-based analysis. The development of AI-based diagnostic tools offers a potential solution. However, there is no publicly available skin disease dataset in Thailand, and image annotation is a challenging and time-consuming task for dermatologists. This scarcity of annotated datasets remains a critical barrier to AI development. This study utilizes the Dermnet dataset and enhances it through the application of image augmentation and style transfer techniques to generate a more diverse and representative dataset, particularly reflecting Thai skin tones. It also evaluates how augmentation techniques affect AI performance in psoriasis classification. The results showed that augmentation significantly enhanced model performance, with EfficientNetB4 achieving the highest accuracy (93.00%) and sensitivity (91.19%). Style transfer emerged as a valuable technique, enabling the creation of skin tone representative datasets that improved model generalizability. These findings align with existing literature. They demonstrate that augmentation techniques can overcome data limitations and enhance model robustness. This study introduces a novel use of style transfer techniques. These are applied to generate augmented datasets that represent Thai skin tones, addressing a critical gap in publicly available dermatology data. By enhancing dataset diversity, style transfer significantly improves the generalizability and accuracy of AI-based psoriasis classification models. These advancements have important implications for clinical practice. They are especially relevant in Thailand and other resource-limited regions, where AI-assisted diagnostics can improve dermatological care access and effectiveness.
References
Agarwal, K., Das, A., Das, S., & De, A. (2022). Impact of psoriasis on quality of life. Indian Journal of Dermatology, 67(4), 387-391. https://doi.org/10.4103/ijd.ijd_572_22
Akaraphanth, R., Kwangsukstid, O., Gritiyarangsan, P., & Swanpanyalert, N. (2013). Psoriasis registry in public health hospital. The Journal of the Medical Association of Thailand, 96(8), 960-966.
Alipour, N., Burke, T., & Courtney, J. (2024). Skin type diversity in skin lesion datasets: A review. Current Dermatology Reports, 13(3), 198-210. https://doi.org/10.1007/s13671-024-00440-0
Chaiyamahapurk, S., & Warnnissorn, P. (2021). Prevalence and characteristics of psoriasis patients in a primary care area in Thailand. Journal of the Medical Association of Thailand, 104(4), 610-614. https://doi.org/10.35755/jmedassocthai.2021.04.11913
Charoenying, T., Lomwong, K., Boonkrong, P., & Kruanamkam, W. (2024). Therapeutic potential of topical cannabis for the treatment of psoriasis: A preliminary clinical evaluation of two different formulations. Journal of Current Science and Technology, 14(1), Article 6. https://doi.org/10.59796/jcst.V14N1.2024.6
Dermnet. (2024). We are currently redesigning dermnet skin disease atlas. Retrieved from https://dermnet.com/
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115-118. https://doi.org/10.1038/nature21056
Gupta, V., & Sharma, V. K. (2019). Skin typing: Fitzpatrick grading and others. Clinics in Dermatology, 37(5), 430-436. https://doi.org/10.1016/j.clindermatol.2019.07.010
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. Las Vegas, NV, USA. https://doi.org/10.1109/CVPR.2016.90
Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., ... & Adam, H. (2019). Searching for MobileNetV3. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (pp. xx–xx). Seoul, Korea (South): IEEE. https://doi.org/10.1109/ICCV.2019.00140
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA. IEEE. https://doi.org/10.1109/CVPR.2017.243
Islam, T., Hafiz, M. S., Jim, J. R., Kabir, M. M., & Mridha, M. F. (2024). A systematic review of deep learning data augmentation in medical imaging: Recent advances and future research directions. Healthcare Analytics, 5, Article 100340. https://doi.org/10.1016/j.health.2024.100340
Li, H., Chen, G., Zhang, L., Xu, C., & Wen, J. (2024). A review of psoriasis image analysis based on machine learning. Frontiers in Medicine, 11, Article 1414582. https://doi.org/10.3389/fmed.2024.1414582
Mpofana, N., Makgobole, M., Nxumalo, C. T., & Pillay, P. (2024). Psoriasis: Clinical Features and Its Impact on Quality of Life. Psoriasis-Recent Advances in Diagnosis and Treatment. IntechOpen. https://doi.org/10.5772/intechopen.1005098
Nakpan, K., & Sirinkraporn, S. (2023). Amplituhedron: A bio-melanin fibre synthesized from soil bacteria for the design of innovative sustainable garments. The Design Journal, 26(2), 290-309. https://doi.org/10.1080/14606925.2022.2154782
Neema, S., Sandhu, S., Gupta, A., Jagadeesan, S., & Vasudevan, B. (2022). Unconventional treatment options in psoriasis: A review. Indian Journal of Dermatology, Venereology and Leprology, 88(2), 137-143. https://doi.org/10.25259/IJDVL_22_2021
Pothisat, P., Nadoo, W., Nettippawan, I., Najaikong, T., Yanpaisan, W., & Pongpirul, K. (2021). Psoriasis: Knowledge from Thai traditional medicine. Journal of Thai Traditional & Alternative Medicine, 19(3), 646-58.
Prasitpuriprecha, N., Santaweesuk, S., Boonkert, P., & Chamnan, P. (2022). Prevalence and DALYs of skin diseases in Ubonratchathani based on real-world national healthcare service data. Scientific Reports, 12(1), Article 16931. https://doi.org/10.1038/s41598-022-20237-0
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, Article 104869. https://doi.org/10.1016/j.bspc.2023.104869
Raharja, A., Mahil, S. K., & Barker, J. N. (2021). Psoriasis: a brief overview. Clinical Medicine, 21(3), 170-173. https://doi.org/10.7861/clinmed.2021-0257
Rajatanavin, N., Wongpraparut, C., Rattanakaemakorn, P., Chularojanamontri, L., Pongcharoen, P., Pattamadilok, B., ... & Asawanonda, P. (2022). Expert opinion on psoriasis management, 2020 and beyond. Thai Journal of Dermatology, 38(1), 1-16.
Rezk, E., Eltorki, M., & El-Dakhakhni, W. (2022). Improving skin color diversity in cancer detection: deep learning approach. JMIR Dermatology, 5(3), Article e39143. https://doi.org/10.2196/39143
Roboflow. (2024). Dermnet computer vision project. Retrieved from https://universe.roboflow.com/class-l9lh0/dermnet
Sharma, A. A., Rakshita, M., Pradhan, P. P., Prasad, K. D., Mishra, S., Jayanthi, K., & Haranath, D. (2023). Noninvasive treatment of psoriasis and skin rejuvenation using an akermanite‐type narrowband emitting phosphor. Luminescence, 38(9), 1668-1677. https://doi.org/10.1002/bio.4554
Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6(1), 1-48. https://doi.org/10.1186/s40537-019-0197-0
Smith, P., Johnson, C. E., Haran, K., Orcales, F., Kranyak, A., Bhutani, T., ... & Liao, W. (2024). Advancing psoriasis care through artificial intelligence: a comprehensive review. Current Dermatology Reports, 13(3), 141-147. https://doi.org/10.1007/s13671-024-00434-y
Srivastava, A., Rastogi, A., Rao, A., Shoeb, A. A. M., Abid, A., Fisch, A., ... & Wang, G. (2022). Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. arXiv preprint arXiv:2206.04615. https://doi.org/10.48550/arXiv.2206.04615
Tan, M., & Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, Long Beach, California.
Tanantong, T., Chalarak, N., Pandecha, P., Tanantong, K., & Srijiranon, K. (2024a). Mobile-Based Deep Learning Framework for Classifying Common Skin Diseases in Thailand. In ICIC Express Letters Part B: Applications, 15(05), 495-503. https://doi.org/10.24507/icicelb.15.05.495
Tanantong, T., La-or-on, P., & Srijiranon, K. (2024b). Improving AI-based skin disease classification with StyleGAN3 for minority skin tone generation. In 2024 16th Biomedical Engineering International Conference (BMEiCON) (pp. 1–5). IEEE. https://doi.org/10.1109/BMEiCON64021.2024.10896290
Tanantong, T., Nantajeewarawat, E., & Thiemjarus, S. (2015). False alarm reduction in BSN-based cardiac monitoring using signal quality and activity type information. Sensors, 15(2), 3952-3974. https://doi.org/10.3390/s150203952
Tschandl, P., Rinner, C., Apalla, Z., Argenziano, G., Codella, N., Halpern, A., ... & Kittler, H. (2020). Human–computer collaboration for skin cancer recognition. Nature Medicine, 26(8), 1229-1234. https://doi.org/10.1038/s41591-020-0942-0
Wang, J., & Perez, L. (2017). The effectiveness of data augmentation in image classification using deep learning. Convolutional Neural Networks Vis. Recognit, 11(2017), 1-8.
Willemink, M. J., Koszek, W. A., Hardell, C., Wu, J., Fleischmann, D., Harvey, H., ... & Lungren, M. P. (2020). Preparing medical imaging data for machine learning. Radiology, 295(1), 4-15. https://doi.org/10.1148/radiol.2020192224
Xing, Y., Zhong, S., Aronson, S. L., Rausa, F. M., Webster, D. E., Crouthamel, M. H., & Wang, L. (2024). Deep learning-based psoriasis assessment: harnessing clinical trial imaging for accurate psoriasis area severity index prediction. Digital Biomarkers, 8(1), 13-21. https://doi.org/10.1159/000536499
Yélamos, O., Alejo, B., Ertekin, S. S., Villa‐Crespo, L., Zamora‐Barquero, S., Martinez, N., ... & Puig, S. (2021). Non‐invasive clinical and microscopic evaluation of the response to treatment with clobetasol cream vs. calcipotriol/betamethasone dipropionate foam in mild to moderate plaque psoriasis: an investigator‐initiated, phase IV, unicentric, open, randomized clinical trial. Journal of the European Academy of Dermatology and Venereology, 35(1), 143-149. https://doi.org/10.1111/jdv.16559
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2025 Journal of Current Science and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
