Multi-Class Facial Acne Classification using the EfficientNetV2-S Deep Learning Model

Abstract

Acne vulgaris is a common dermatological condition that significantly impacts psychosocial well-being, particularly among adolescents and young adults. Accurate identification of acne lesion types is crucial for effective treatment planning, yet manual assessment by dermatologists is subjective and resource-intensive. This study proposes a Convolutional Neural Network (CNN)-based approach using EfficientNetV2-S with transfer learning and data augmentation to perform multi-class classification of five acne lesion types: blackheads, whiteheads, papules, pustules, and cysts. The model was trained and evaluated on 4,673 annotated facial images, achieving an accuracy of 96.66%, outperforming conventional lightweight CNNs and achieving comparable results to heavier ensemble architectures. Statistical validation using p-values and effect sizes confirms the model’s robustness. The scientific contribution of this research lies in the integration of EfficientNetV2-S with a customized classification head optimized for multi-class acne recognition—an area underexplored in dermatological AI research. Unlike previous works focusing on binary classification or ensemble models, our approach offers a lightweight, accurate, and scalable solution for real-world teledermatology, thus establishing a novel benchmark in multi-class acne classification.

Keywords

Deep learning; convolutional neural network; EfficientNetV2-S; acne classification; transfer learning; data augmentation.

Full Text:

PDF

References

Y. M. Awaloei, N. A. Prastowo, and R. Regina, “The correlation between skin type and acne scar severity in young adults,” Jurnal Kedokteran dan Kesehatan Indonesia (JKKI), 2021. https://doi.org/10.20885/JKKI.Vol12.Iss1.art9 (In indonesia)

J. Arifianto and I. Muhimmah, “Aplikasi web pendeteksi jerawat pada wajah menggunakan algoritma deep learning dengan TensorFlow [Web application for acne detection using deep learning algorithm with TensorFlow],” AUTOMATA, vol. 2, no. 1, pp. 14–21, 2021. https://journal.uii.ac.id/AUTOMATA/article/view/19504 (In Indonesian)

I. A. Pardosi, R. Yunis, and A. Halim, “Skin Lesion Diagnosis through Deep Learning and Hybrid Texture Feature Augmentation,” vol. 14, no. July, pp. 264–269, 2025. https://doi.org/10.34148/teknika.v14i2.1253

P. Garg and M. K. Sharma, “Transparency in diagnosis: Unveiling the power of deep learning and explainable AI for medical image interpretation,” Arab J Sci Eng, 2025. https://doi.org/10.1038/s41598-024-84670-z

H. A. Faudyta and J. T. Sinaga, “Implementation of MobileNet architecture for skin cancer disease classification,” JAIC, vol. 5, no. 2, pp. 88–95, 2024. https://doi.org/10.30871/jaic.v8i2.8771

L. Hakim, Z. Sari, and H. Handhajani, “Klasifikasi citra pigmen kanker kulit menggunakan CNN [Classification of skin cancer pigment images using CNN],” Jurnal RESTI, vol. 5, no. 5, pp. 1033–1040, 2021. https://doi.org/10.29207/resti.v5i2.3001 (In Indonesian)

R. H. Hridoy, F. Akter, and A. Rakshit, “Computer vision based skin disorder recognition using EfficientNet: A transfer learning approach,” in IEEE ICREST, 2021. https://doi.org/10.1109/ICIT52682.2021.9491776

N. Gao et al., “Evaluation of an acne lesion detection and severity grading model for Chinese population in online and offline healthcare scenarios,” Sci Rep, vol. 15, no. 1, pp. 1–11, 2025. https://doi.org/10.1038/s41598-024-84670-z

N. Gessert, M. Nielsen, M. Shaikh, R. Werner, and A. Schlaefer, “Skin lesion classification using ensembles of multi-resolution EfficientNets with meta data,” MethodsX, vol. 7, p. 100864, 2020. https://doi.org/10.1016/j.mex.2020.100864

P. Gupta and S. Mishra, “Assessment of deep learning models for skin disease classification,” in Intelligent Computing and Communication Systems, 2025. https://doi.org/10.1201/9781003635680-83

M. O. Oyedeji, E. Okafor, and H. Samma, “Interpretable deep learning for classifying skin lesions,” International Journal of Intelligent Systems, 2025. https://doi.org/10.1155/int/2751767

K. Nawaz, A. Zanib, I. Shabir, J. Li, and Y. Wang, “Skin cancer detection using dermoscopic images with convolutional neural network,” Sci Rep, vol. 15, 2025. https://doi.org/10.1038/s41598-025-91446-6

A. N. Toprak and I. Aruk, “A hybrid convolutional neural network model for the classification of multi‐class skin cancer,” Int J Imaging Syst Technol, vol. 34, 2024. https://doi.org/10.1002/ima.23180

K. Kusnawi, J. Ipmawati, and D. P. Prabowo, “Enhancing quality measurement for visible and invisible watermarking based on M-SVD and DCT,” Bulletin of Electrical Engineering and Informatics, vol. 13, no. 4, pp. 2537–2546, Aug. 2024. https://doi.org/10.11591/eei.v13i4.7884

S. Chaturvedi, P. Kaur, and U. Ghosh, “EfficientNet-based ensemble learning for skin disease classification,” Comput Biol Med, vol. 157, 2023. https://doi.org/10.1016/j.compbiomed.2023.106762

M. Tan and Q. V. Le, “EfficientNetV2: Smaller Models and Faster Training,” Proc Mach Learn Res, vol. 139, pp. 10096–10106, 2021. https://doi.org/10.48550/arXiv.2104.00298

U. K. Lilhore et al., “SkinEHDLF a hybrid deep learning approach for accurate skin cancer classification in complex systems,” Sci Rep, vol. 15, no. 1, pp. 1–32, 2025. https://doi.org/10.1038/s41598-025-98205-7

S. Basut, Y. Kurtbas, N. Guler, and E. Okur, “A comparative study on skin cancer detection: Multi-class vs. binary using EfficientNet-B0,” in IEEE Medical Technologies Conference, 2024. https://doi.org/10.1109/TIPTEKNO63488.2024.10755241

F. Mahmood, W. Li, and N. Rajpoot, “Transfer learning with EfficientNet for skin lesion classification,” Biomed Signal Process Control, vol. 68, 2021. https://doi.org/10.1016/j.bspc.2021.102624

M. Arshad, M. A. Khan, N. A. Almujally, A. Alasiry, and M. Marzougui, “Multiclass skin lesion classification and localziation from dermoscopic images using a novel network-level fused deep architecture and explainable artificial intelligence,” vol. 2, 2025. https://doi.org/10.1186/s12911-025-03051-2

Y. Zhang et al., “A Novel Perspective for Multi-Modal Multi-Label Skin Lesion Classification,” in 2025 IEEE Winter Conference on Applications of Computer Vision (WACV), 2025, pp. 3549–3558. https://doi.org/10.1109/WACV61041.2025.00350.

P. P. Mascarenhas et al., “Improving acne severity detection: a GAN framework with contour accentuation for image deblurring,” Front. Bioinform., vol. 5, art. 1485797, Mar. 2025. https://doi.org/10.3389/fbinf.2025.1485797.

M. Alruwaili and M. Mohamed, “An Integrated Deep Learning Model with EfficientNet and ResNet for Accurate Multi-Class Skin Disease Classification,” Diagnostics, vol. 15, no. 5, p. 551, Feb. 2025. https://doi.org/10.3390/diagnostics15050551.

Traini, D. O., Palmisano, G., Guerriero, C., & Peris, K.. Artificial intelligence in the assessment and grading of acne vulgaris: A systematic review. Journal of Personalized Medicine, 15(6), 238, 2025. https://doi.org/10.3390/jpm15060238

K. Prokhorov and A. A. Kalinin, “Improving Acne Image Grading with Label Distribution Smoothing,” in Proceedings of the 2024 IEEE International Symposium on Biomedical Imaging (ISBI), Athens, Greece, 2024, pp. 1-5. https://arxiv.org/abs/2403.00268.

S. Sharmin et al., “A Hybrid CNN Framework DLI-Net for Acne Detection with XAI,” J. Imaging, vol. 11, no. 4, p. 115, Apr. 2025. https://doi.org/10.3390/jimaging11040115.

X. Wei et al., “Towards Accurate Acne Detection via Decoupled Sequential Detection Head,” Knowledge-Based Systems, vol. 284, p. 111305, 2023. https://doi.org/10.1016/j.knosys.2023.111305.

U. Khalid et al., “A smart facial acne disease monitoring for automate severity assessment using AI-enabled cloud-based internet of things,” Discover Computing, vol. 28, no. 12, Feb. 2025. https://doi.org/10.1007/s10791-025-09503-7.

http://dx.doi.org/10.28989/avitec.v7i3.3157

Article Metrics

Abstract view: 135 times
Download     : 25   times

This work is licensed under a Creative Commons Attribution 4.0 International License.

Refbacks

• There are currently no refbacks.