Classification of human scabies skin disease using ConvNeXt
DOI:
https://doi.org/10.21107/kursor.v13i3.490Keywords:
Automated Diagnosis, ConvNeXt, Deep Learning, Image Classification, ScabiesAbstract
Scabies is a contagious skin disease caused by Sarcoptes scabiei and remains a health issue in many countries, including Indonesia. Clinical diagnosis is often difficult due to symptom similarities with other skin conditions. This study evaluates the ConvNeXt architecture for scabies classification from skin images to support automated diagnostic systems. The dataset consisted of 273 images (86 scabies and 187 non-scabies), expanded through cropping to 819 images, divided into 488 scabies and 331 non-scabies images. ConvNeXt was trained with fine-tuning at stage 3, implemented using PyTorch on an A100 GPU with the AdamW optimizer. Evaluation used 70:15:15, 80:10:10, and 5-Fold Cross Validation schemes with accuracy, precision, recall, and F1-score metrics. The best configuration (learning rate 0.0001, batch size 32) achieved 95.97% testing accuracy. Overall, ConvNeXt reached 97.75% average accuracy and an F1-score near 0.98, demonstrating highly competitive performance that slightly exceeds established baselines like ResNet-50 (97.69% accuracy). This shows its potential as an accurate and practical solution for automated scabies diagnosis in resource limited healthcare settings.
Key words: Automated Diagnosis, ConvNeXt, Deep Learning, Image Classification, Scabies.
Downloads
References
[1] P. Baker, C. Huang, R. Radi, S. B. Moll, E. Jules, and J. L. Arbiser, “Skin barrier function: the interplay of physical, chemical, and immunologic properties,” Cells, vol. 12, no. 23, pp. 1–15, 2023, doi: 10.3390/cells12232745.
[2] S. Brito, M. Baek, and B. H. Bin, “Skin structure, physiology, and pathology in topical and transdermal drug delivery,” Pharmaceutics, vol. 16, no. 11, pp. 1–29, 2024, doi: 10.3390/pharmaceutics16111403.
[3] R. Adelia Anhar, S. Maendah Cahyaningsih, V. Aurel Rania, Z. Qurratu Aini Syukur, L. A. Dyah Dwi, and J. K. Samanhudi, “Analisis peran vitamin c pada pigmentasi kulit,” J. Mhs. Ilmu Farm. dan Kesehat., vol. 2, no. 3, 2024. https://doi.org/10.59841/jumkes.v2i3.1209 .
[4] A. D. Parga, B. Ray, and A. Pawletzki, “Climate change and emerging dermatologic diseases in the americas: a review of shifting exposures and vulnerable populations,” J. Environ. Sci. Sustain. Green Innov. Clim., vol. 1, no. 2, pp. 1–17, 2025, doi: 10.63620/MKJESSGI.2025.
[5] L. G. Arlian and M. S. Morgan, “A review of Sarcoptes scabiei: Past, present and future,” Parasites and Vectors, vol. 10, no. 1, pp. 1–22, 2017, doi: 10.1186/s13071-017-2234-1.
[6] Mitha Yunda Pertiwi and Dedianto Hidajat, “Skabies dengan infeksi sekunder pada sindrom down,” Unram Med. J., vol. 10, no. 4, pp. 655–660, 2022, doi: 10.29303/jku.v10i4.625.
[7] J. Park, S. H. Kwon, Y. B. Lee, H. S. Kim, J. H. Jeon, and G. S. Choi, “Clinical practice guidelines for the diagnosis and treatment of scabies in Korea: Part 1. Epidemiology, clinical manifestations, and diagnosis,” Korean J. Dermatology, vol. 61, no. 7, pp. 393–403, 2023. https://doi.org/10.12771/emj.2024.e73 .
[8] E. Mitchell, M. Wallace, J. Marshall, M. Whitfeld, and L. Romani, “Scabies: current knowledge and future directions,” Front. Trop. Dis., vol. 5, no. July, pp. 1–9, 2024, doi: 10.3389/fitd.2024.1429266.
[9] G. Tavoletti et al., “Scabies: An updated review from epidemiology to current controversies and future perspectives,” Travel Med. Infect. Dis., vol. 67, no. July, p. 102878, 2025, doi: 10.1016/j.tmaid.2025.102878.
[10] S. Uzun et al., “Clinical practice guidelines for the diagnosis and treatment of scabies,” Int. J. Dermatol., pp. 1642–1656, 2024, doi: 10.1111/ijd.17327.
[11] R. Efendi, A. A. Adriansyah, and M. Ibad, “Hubungan personal hygiene dengan kejadian scabies pada santri di pondok pesantren,” J. Kesehat. Masy. Indones., vol. 15, no. 2, p. 25, 2020, doi: 10.26714/jkmi.15.2.2020.25-28.
[12] S. F. Walton and B. J. Currie, “Problems in diagnosing scabies, a global disease in human and animal populations,” Clin. Microbiol. Rev., vol. 20, no. 2, pp. 268–279, 2007, doi: 10.1128/CMR.00042-06.
[13] L. Lugović-Mihić, M. D. Aždajić, and I. Bešlić, “Scabies cases misdiagnosed and treated as allergic diseases: Itch as alarm,” Acta Clin. Croat., vol. 61, no. 2, pp. 349–353, 2022, doi: 10.20471/acc.2022.61.02.22.
[14] K. Y. Gunardi, S. Sungkar, Y. Irawan, S. Widaty, and J. Cipto Mangunkusumo, “Level of evidence diagnosis skabies berdasarkan Oxford centre for evidence-based medicine departemen dermatologi dan venereologi fakultas kedokteran Universitas Indonesia-RSUPN dr,” eJournal Kedokt. Indones. , vol. 10, no. 3, pp. 1–8, 2022, [Online]. Available: https://doi.org/10.23886/ejki.10.224.276.
[15] F. Badri, M. Taqijuddin Alawiy, and E. M. Yuniarno, “Deep learning architecture based on Convolutional Neural Network (Cnn) on animal image classification,” J. Ilm. KURSOR, vol. 12, no. 2, pp. 83–92, 2023. https://doi.org/10.21107/kursor.v12i2.349.
[16] R. Anantama, “Application of cost-sensitive Convolutional Neural Network for Pneumonia detection,” J. Ilm. Kursor, vol. 11, no. 3, p. 101, 2022, doi: 10.21107/kursor.v11i3.264.
[17] F. N. Riyana Putri, R. R. Isnanto, and A. Sugiharto, “Skin rash classification system using modified Densenet201 through random search for hyperparameter tuning,” J. Ilm. Kursor, vol. 12, no. 4, pp. 179–190, 2024, doi: 10.21107/kursor.v12i4.418.
[18] F. G. Waldamichael, S. R. Kebede, Y. M. Ayano, M.T. Demissie, and T. G. Debelee, “A multi-input architecture for the classification of skin lesions using ResNets and metadata,” Commun.Comput. Inf. Sci., vol. 1800 CCIS, no. May, pp. 27–49, 2023, doi: 10.1007/978-3-031-31327-1_2.
[19] Z. Liu, H. Mao, C. Y. Wu, C. Feichtenhofer, T. Darrell, and S. Xie, “A ConvNet for the 2020s,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2022-June, pp. 11966–11976, 2022, doi: 10.1109/CVPR52688.2022.01167.
[20] O. P. Mmileng, A. Whata, M. Olusanya, and S. Mhlongo, “Application of ConvNeXt with transfer learning and data augmentation for malaria parasite detection in resource-limited settings using microscopic images,” PLoS One, vol. 20, no. 6 June, pp. 1–39, 2025, doi: 10.1371/journal.pone.0313734.
[21] Yasar Mehmood and Usama Ijaz Bajwa, “Brain tumor grade classification using the ConvNext architecture,” Digit. Heal., vol. 10, p. 20552076241284920, Sep. 2024, doi: 10.1177/20552076241284920.
[22] M. Wu et al., “Classification of dry and wet macular degeneration based on the ConvNeXT model.,” Front. Comput. Neurosci., vol. 16, p. 1079155, 2022, doi: 10.3389/fncom.2022.1079155.
[23] A. Kumar, R. Shen, S. Bubeck, and S. Gunasekar, “How to fine-tune vision models with Sgd,” 12th Int. Conf. Learn. Represent. ICLR 2024, pp. 1–26, 2024.
[24] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-Decem, pp. 770–778, 2016, doi: 10.1109/CVPR.2016.90.
[25] D. Wang, L. Feng, and M. Zhang, “Rethinking calibration of deep neural networks : Do not be afraid of overconfidence,” no. NeurIPS, pp. 1–12, 2021.
Downloads
Published
Issue
Section
Citation Check
License
Copyright (c) 2026 Mochammad Zaky Zamroni, Muhammad Afif Hendrawan, Agwin Fahmi Fahanani, Dhelya Widasmara, Cahya Rahmad
This work is licensed under a Creative Commons Attribution 4.0 International License.
+62-858-5000-1918
