Related Experiment Video
Updated: Jul 10, 2026
Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
Published on: August 18, 2022
Adaptive class rebalancing and spatial-aware metadata fusion for long-tailed skin lesion classification
Tianming Ma1, Xianwei Han2, Guijun Liu3
1The Second Affiliated Hospital of Heilongjiang University of Chinese Medicine, Harbin, China.
Introduction:
Dermoscopic skin lesion classification is challenged by class imbalance and the underutilization of clinical metadata, limiting the diagnostic reliability of existing deep learning systems.
Methods:
Building upon a Vision Transformer baseline that fuses dermoscopic images with patient metadata via cross-modal attention, we introduce three complementary improvements: class-balanced focal loss with square-root effective-number sampling, a patch-level cross-attention metadata-guided attention module, and supervised contrastive regularization. The extended model is evaluated on the ISIC 2019 and BCN 20000 datasets.
Results:
Ablation studies demonstrate consistent improvements. On the ISIC 2019 validation set, the full model achieves a Macro AUC of 0.9613 and a Macro balanced accuracy of 0.8426, with strong performance on rare categories such as dermatofibroma (AUC = 0.991) and vascular lesions (AUC = 0.999).
Discussion:
Principled loss design, spatially aware fusion, and representation-level regularization jointly improve the robustness of skin lesion classification under extreme class imbalance.