Review
Open access
Aug 2026
Skin Lesion Classification in Low-Resource Settings Using Lightweight CNNs with Uncertainty Estimation
A computationally efficient skin lesion classification framework for seven classes using EfficientNet-B0, complemented by Monte Carlo (MC) Dropout for uncertainty quantification is introduced, and the only lightweight method in the comparison providing calibrated uncertainty estimates.
Princy Randhawa, S. Suddala, M. Hemal et al.
· BioMedInformatics · 0 citations