ConvNeXt with Transfer learning for Microscopic Canine Skin Disease Classification
DOI:
https://doi.org/10.30871/jaic.v10i3.12792Keywords:
ConvNeXt, Microscopic Image Classification, Transfer LearningAbstract
Canine skin diseases represent a significant health concern in veterinary practice, with accurate diagnosis often requiring specialized expertise and microscopic examination. This study presents an implementation and evaluation of the ConvNeXt architecture for classifying microscopic images of four canine skin diseases: Demodex, Kokus, Malassezia, and Scabies. The dataset consists of microscopic images obtained from skin scraping preparations photographed under 400× digital microscopy and annotated by a certified veterinary. Two dataset scenarios were evaluated: a small dataset (356 images; Demodex: 104, Kokus: 47, Malassezia: 102, Scabies: 103) and a large dataset (2,963 images with near-balanced class distribution). Using transfer learning with pre-trained weights from ImageNet, the ConvNeXt model was evaluated across three input sizes (224×224, 180×180, 150×150). Augmentation balancing, including rotation, flipping, zoom, translation, shear, and color jitter, was applied to address class imbalance while preserving biological validity of morphological features Augmentation balancing was applied to address class imbalance, ensuring equal representation across all classes. Experimental results demonstrate that ConvNeXt with 224×224 input size trained on the large dataset achieved the best overall performance with 97.22% test accuracy, 0.9524 F1-score, 0.9624 Matthews Correlation Coefficient (MCC), and a perfect Area Under Curve (AUC) of 1.0000. Analysis of input size effects revealed that 224×224 is optimal for detecting small pathogens like Malassezia (3-8 μm) and Kokus (0.5-1 μm), while 150×150 better preserves spatial context for large pathogens such as Demodex (300 μm) and Scabies (200-400 μm). Visualization of feature maps provided insights into how the architecture extracts diagnostic features, producing dense, hierarchical feature representations that benefit from abundant data. This research demonstrates that transfer learning with the ConvNeXt architecture, combined with appropriate augmentation balancing, can achieve high classification accuracy for automated diagnosis support of canine skin diseases. However, clinical deployment requires further validation by veterinary and prospective clinical studies before these results can be considered clinically applicable.
Downloads
References
[1] W. H. Miller, C. E. Griffin, and K. L. Campbell, Muller and Kirk’s Small Animal Dermatology, 7th ed. St. Louis, Missouri: Elsevier, 2020.
[2] D. W. Scott and W. H. Miller, Small Animal Dermatology: A Color Atlas and Therapeutic Guide, 4th ed. Philadelphia, PA: Elsevier Saunders, 2021.
[3] S. Paterson and J. Bryan, “Skin diseases of the dog and cat,” In Pract., vol. 41, no. 7, pp. 316–324, 2019, doi: 10.1136/inp.l5222.
[4] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. doi: 10.1109/CVPR.2016.90.
[5] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4700–4708. doi: 10.1109/CVPR.2017.243.
[6] M. Tan and Q. Le, “{EfficientNet}: Rethinking model scaling for convolutional neural networks,” in International Conference on Machine Learning (ICML), PMLR, 2019, pp. 6105–6114.
[7] A. Esteva et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, no. 7639, pp. 115–118, 2017, doi: 10.1038/nature21056.
[8] A. Dosovitskiy et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” Int. Conf. Learn. Represent., 2021, [Online]. Available: https://arxiv.org/abs/2010.11929
[9] H. Touvron, M. Cord, M. Douze, F. Massa, A. Sablayrolles, and H. Jégou, “Training data-efficient image transformers & distillation through attention,” Int. Conf. Mach. Learn., pp. 10347–10357, 2021.
[10] A. Vaswani et al., “Attention is all you need,” in Advances in Neural Information Processing Systems (NeurIPS), 2017. [Online]. Available: https://arxiv.org/abs/1706.03762
[11] I. G. N. Sentana Putra, A. L. Najih, U. DA Resiloy, R. B. Yudhianto, Erfiani, and A. Fitrianto, “Classification Of Cardiovascular And Chronic Respiratory Diseases Utilizing Ensemble Models With Data Exploration Techniques,” vol. 10, no. 4, pp. 3772–3786, 2025.
[12] R. Kim and A. Kim, “Analysis of Modern Computer Vision Models for Blood Cell Classification,” 2024.
[13] Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell, and S. Xie, “A ConvNet for the 2020s,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 11976–11986. doi: 10.1109/CVPR52688.2022.01167.
[14] K. A. Moriello and E. Bensignor, Feline Dermatology. Philadelphia, PA: Veterinary Clinics of North America: Small Animal Practice, 2020.
[15] S. J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Trans. Knowl. Data Eng., vol. 22, no. 10, pp. 1345–1359, 2010, doi: 10.1109/TKDE.2009.191.
[16] I. G. N. Sentana Putra, M. Yusran, J. R. Sari, and G. A. Dito, “Evaluasi Sentimen Publik terhadap Fenomena Gambar {AI} Bergaya {Ghibli}: Perbandingan Dua Metode Static Word Embedding,” [Nama J. — sesuaikan dengan Publ. resmi], 2025.
[17] T. Mustaqim, C. Fatichah, and N. Suciati, “Deep Learning for the Detection of Acute Lymphoblastic Leukemia Subtypes on Microscopic Images: A Systematic Literature Review,” IEEE Access, vol. 11, pp. 16108–16127, 2023, doi: 10.1109/ACCESS.2023.3245128.
[18] P. Rajpurkar et al., “Deep learning for chest radiograph diagnosis,” PLOS Med., vol. 15, no. 11, p. e1002686, 2018, doi: 10.1371/journal.pmed.1002686.
[19] A. Saez and others, “Transfer learning for veterinary dermatology: applying deep learning to canine skin disease classification,” Vet. Dermatol., 2021.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Made Ardika Mertha Putra Vaikuntha, I Gusti Ngurah Lanang Wijayakusuma
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
