Abstract: Accurate skin cancer diagnosis is vital for early treatment and improved patient outcomes. Deep learning models have shown promise in automating skin cancer classification, yet challenges remain due to data scarcity and limited uncertainty awareness. This study presents a comprehensive evaluation of deep learning-based skin lesion classification with transfer learning and UQ on the HAM10000 dataset. We benchmark several pre-trained feature extractors (including Contrastive Language-Image Pre-training (CLIP) variants, ResNet50, DenseNet121, VGG16, EfficientNet-V2-Large, and ConvNeXt Large) combined with traditional classifiers such as SVM, XGBoost, and logistic regression. Multiple PCA settings (64, 128, 256, 512) are explored, with LAION CLIP ViT-H/14 and ViT-L/14 at PCA-256 achieving the strongest baseline results. In the UQ phase, Monte Carlo Dropout (MCD), Ensemble, and Ensemble Monte Carlo Dropout (EMCD) are applied and evaluated using uncertainty-aware metrics (UAcc, USen, USpe, UPre). Ensemble methods with PCA-256 provide the best balance between accuracy and reliability. Further improvements are obtained through feature fusion of top-performing extractors at PCA-256. Finally, we propose a feature-fusion–based model trained with a Predictive Entropy (PE) loss function, which outperforms all prior configurations across both standard and uncertainty-aware evaluations, advancing trustworthy deep learning-based skin cancer diagnosis.

Key words: Deep learning')">Deep learning, Machine learning, Classification, Uncertainty quantification, Skin cancer