The detection of skin cancer holds paramount importance worldwide due to its impact on global health.
While deep convolutional neural networks (DCNNs)
have shown potential in this domain, current approaches often struggle with fine-grained variability in
skin lesion features, imbalanced datasets and inadequate
augmentation. The objectives of our study encompass
building a model that not only enhances accuracy but
also reduces training time and cost, improves dimensionality reduction during classification and segmentation, and is evaluated on larger datasets for robustness.
We enhance the learning process using an improved
nature-inspired optimisation algorithm tailored specifically for skin cancer classification tasks. This algorithm
optimises model parameters to maximise classification
accuracy while minimising computational overhead.
Our proposed architecture leverages a gold standard
dermatological image dataset meticulously curated and
validated by experts. This dataset spans eight distinct
classes, including actinic keratosis, basal cell carcinoma, melanoma, nevus, and others, ensuring a diverse
representation of skin conditions. The balanced class distribution in the training and test sets enables fair evaluation and robustness assessment of our deep learning
models. The developed algorithm showcases novelty in its
approach, contributing to advancements in early skin
cancer detection technologies. This study introduces an
optimised deep learning model designed for the early
detection of skin cancer, achieving a notable accuracy of
97.48%. Our study aims to contribute significantly to the
medical field by providing a reliable and efficient tool
for dermatologists and healthcare practitioners to assist
in diagnosing skin conditions accurately and promptly,
ultimately improving patient outcomes and healthcare
efficiency.