Abstract
Skin cancer is a deadly disease. Skin lesion classification is a critical challenge due to its prevalent and deadly nature. Skin lesions are difficult for dermatologists to detect using eye examination, which is time-consuming and variable. A deep learning model of skin lesions classification has been proposed using a Convolutional Neural Network (CNN) trained on the HAM10000 dataset of 10,015 dermatoscopies. To improve resilience and address the dataset's extreme class imbalance, data augmentation techniques such as geometric transformations, brightness/contrast adjustments, blurring, noise addition, histogram equalization, color space alterations, and elastic deformations are used. With a carefully balanced 10% test set, the model can accurately distinguish seven skin lesions with an overall accuracy of 90.75%, a macro-average F1-score of 0.92, and a good overall Area Under the Curve - Receiver Operating Characteristics (AUC - ROC) score of 0.9911. To show its effectiveness, the model is compared to a trained ResNet50 model. The custom CNN performs better than ResNet50 (87.64% accuracy despite early overfitting). Deep learning models may be highly useful in skin cancer screening, according to the findings. This study could simplify worrisome lesion identification in primary care, mobile health apps, and underserved areas.
Recommended Citation
Mohammed-Ramzi, Mohammed Nawzad and Aladdin, Aso M.
(2026)
"Skin Lesion Classification Using CNN Model and Augmented Dataset,"
Journal of Soft Computing and Computer Applications: Vol. 3:
Iss.
1, Article 1026.
DOI: https://doi.org/10.70403/3008-1084.1026
