000			02402nam a2200133 4500
008			250624b |||||||| |||| 00| 0 eng d
100			_aP. Rama
245			_aOptimised EfficientNet for multi-class skin cancer diagnosis: integrating chaotic grey wolf algorithms
300			_aP 728-736
520			_aThe 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.
654			_aActinic keratosis _askin cancer detection _asegmentation _a deep convolutional neural networks _aclassification _abasal cell carcinoma
773	0		_0125299 _9112524 _tCurrent Science _x 0011-3891
942			_cJA
999			_c131787 _d131787