FOSSIL: Regret-Minimizing Curriculum Learning for Metadata-Free and Low-Data Mpox Diagnosis
This addresses data scarcity and instability in medical imaging for Mpox diagnosis, though it is incremental as it adapts an existing framework to a new domain.
The paper tackled the problem of deep learning in small, imbalanced biomedical datasets by implementing FOSSIL, a regret-minimizing curriculum learning framework, for Mpox skin lesion diagnosis, achieving an AUC of 0.9573 and ECE of 0.053.
Deep learning in small and imbalanced biomedical datasets remains fundamentally constrained by unstable optimization and poor generalization. We present the first biomedical implementation of FOSSIL (Flexible Optimization via Sample-Sensitive Importance Learning), a regret-minimizing weighting framework that adaptively balances training emphasis according to sample difficulty. Using softmax-based uncertainty as a continuous measure of difficulty, we construct a four-stage curriculum (Easy-Very Hard) and integrate FOSSIL into both convolutional and transformer-based architectures for Mpox skin lesion diagnosis. Across all settings, FOSSIL substantially improves discrimination (AUC = 0.9573), calibration (ECE = 0.053), and robustness under real-world perturbations, outperforming conventional baselines without metadata, manual curation, or synthetic augmentation. The results position FOSSIL as a generalizable, data-efficient, and interpretable framework for difficulty-aware learning in medical imaging under data scarcity.