Machine Learning Based Classification of Skin Lesions for Early Melanoma Detection
DOI:
https://doi.org/10.70356/jafotik.v4i1.99Keywords:
Melanoma Detection, Skin Lesion Classification, Deep LearningAbstract
Early detection of melanoma is essential to reduce skin cancer related mortality. This study proposes a machine learning based framework for automatic classification of dermoscopic skin lesion images into melanoma and benign categories. The methodology integrates image preprocessing, deep convolutional feature extraction, and an attention mechanism to enhance clinically relevant patterns such as asymmetry, border irregularity, and color variation. The model was trained and evaluated using a labeled dermoscopy dataset with a structured train validation test split. Experimental results demonstrate strong diagnostic performance, achieving 92.8% accuracy, 94.1% sensitivity, 91.3% specificity, and an AUC of 0.96. The high sensitivity indicates effective identification of malignant cases, which is critical for early intervention. Overall, the proposed framework shows promising potential as a computer aided diagnostic tool to support dermatologists in improving consistency, efficiency, and reliability in melanoma detection.
Downloads
References
C. Liang, P. Wang, M. Li, R. Li, K. Po, and J. Chen, “Heliyon Anti-cancer mechanisms of natural isoflavones against melanoma,” Heliyon, vol. 10, no. 7, p. e28616, 2024, doi: https://doi.org/10.1016/j.heliyon.2024.e28616.
B. M. Lengyel et al., “The melanoma MEGA-study : Integrating proteogenomics , digital pathology , and AI-analytics for precision oncology ☆,” vol. 319, no. June, 2025.
Z. Sadat, S. Sadat, and G. Farahavar, “Heliyon Gold nanostructures in melanoma : Advances in treatment , diagnosis , and theranostic applications,” Heliyon, vol. 10, no. 15, p. e35655, 2024, doi: https://doi.org/10.1016/j.heliyon.2024.e35655.
S. M. Selvan and R. Kavitha, “Intelligence-Based Medicine Transformer-enhanced hybrid feature fusion for accurate and interpretable melanoma detection,” Intell. Med., vol. 12, no. October, p. 100321, 2025, doi: 1 https://doi.org/0.1016/j.ibmed.2025.100321.
Y. Liu, A. C. Rokohl, Y. Guo, K. Yao, W. Fan, and L. M. Heindl, “Advances in Ophthalmology Practice and Research Personalized treatment approaches in intraocular cancer,” Adv. Ophthalmol. Pract. Res., vol. 4, no. 3, pp. 112–119, 2024, doi: https://doi.org/10.1016/j.aopr.2024.03.005.
R. Lamba, “ScienceDirect Advances in AI for Medical Imaging : A Review of Machine and Deep Learning in Disease Detection,” Procedia Comput. Sci., vol. 260, pp. 262–273, 2025, doi: https://doi.org/10.1016/j.procs.2025.03.201.
H. Elmekki et al., “CACTUS : An open dataset and framework for automated Cardiac Assessment and Classification of Ultrasound images using deep transfer learning,” Comput. Biol. Med., vol. 190, no. August 2024, p. 110003, 2025, doi: https://doi.org/10.1016/j.compbiomed.2025.110003.
S. M. Balsabti et al., “Neuroscience Informatics Advances in deep learning for multimodal brain imaging : A comprehensive survey,” Neurosci. Informatics, vol. 6, no. 1, p. 100252, 2026, doi: https://doi.org/10.1016/j.neuri.2025.100252.
T. Ahmed and F. Binte, “Brain tumor detection , classification and segmentation by deep learning models from MRI images : Recent approaches , challenges and future directions,” Array, vol. 28, no. August, p. 100571, 2025, doi: https://doi.org/10.1016/j.array.2025.100571.
J. H. Chin et al., “Developmental Cognitive Neuroscience Deep learning in fetal , infant , and toddler neuroimaging research,” vol. 78, no. October 2025, 2026, doi: https://doi.org/10.1016/j.dcn.2026.101680.
L. Zhenyi and Y. Cun, “Neuroscience Informatics Feature analysis of depression patients ’ house-tree-person drawings using convolutional neural networks,” Neurosci. Informatics, vol. 5, no. 4, p. 100239, 2025, doi: https://doi.org/10.1016/j.neuri.2025.100239.
S. Gowthaman and A. Das, “A Phase Preserving Dual Tree Complex Wavelet Convolutional Neural Network Framework for Texture Classification,” Results Eng., p. 109643, 2026, doi: https://doi.org/10.1016/j.rineng.2026.109643.
C. Fan, “Heliyon Deep neural networks for automated damage classification in image-based visual data of reinforced concrete structures,” Heliyon, vol. 10, no. 19, p. e38104, 2024, doi: https://doi.org/10.1016/j.heliyon.2024.e38104.
A. Merdasa et al., “Photoacoustics Advancing non-invasive melanoma diagnostics with deep learning and multispectral photoacoustic imaging,” vol. 45, no. June, 2025, doi: https://doi.org/10.1016/j.pacs.2025.100743.
O. Albabele, H. Malik, N. Jabeur, R. W. Anwar, and D. Dampier, “ScienceDirect ScienceDirect Deep Learning for Melanoma and Skin Cancer Detection : ResNet – Deep Learning for Melanoma and Skin Cancer Detection : ResNet – EfficientNet Comparison with Ensemble and Decider Framework EfficientNet Comparison with Ensemble and Decider Framework,” Procedia Comput. Sci., vol. 272, pp. 303–310, 2025, doi: https://doi.org/10.1016/j.procs.2025.10.209.
P. Thapar, M. Rakhra, M. Alsaadi, A. Quraishi, and A. Deka, “Healthcare Analytics A hybrid Grasshopper optimization algorithm for skin lesion segmentation and melanoma classification using deep learning,” Healthc. Anal., vol. 5, no. April, p. 100326, 2024, doi: https://doi.org/10.1016/j.health.2024.100326.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Fitrah Karimah, Amirah Ahmad
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
