RABC-Net: Reliability-Aware Annotation-Free Skin Lesion Segmentation for Low-Resource Dermoscopy

TL;DR

RABC-Net is a novel skin lesion segmentation system that operates without manual annotations, using reliability-aware learning and boundary calibration to achieve high accuracy and efficiency in low-resource dermoscopy settings.

Contribution

The paper introduces RABC-Net, a new annotation-free segmentation approach combining reliability learning, domain adaptation, and boundary calibration, with minimal parameter updates and fast inference.

Findings

Achieves macro-average DICE of 86.58% and JAC of 79.47% across datasets.

Operates at 87.4 FPS with only 3.50% of model parameters updated.

Effectively calibrates boundary confidence, uncertainty, and foreground probability without manual masks.

Abstract

Pixel-level annotation is costly in low-resource dermoscopy. We present RABC-Net, a reliability-aware annotation-free segmentation system that combines pseudo-label reliability learning, restricted target-domain adaptation, and Reliability-Adaptive Boundary Calibration (RABC). The system decouples reliability learning from deployment: uncertainty-aware pseudo-label interaction shapes robust representations during training, while the image-only inference path is preserved and RABC performs local logit-space calibration from boundary confidence, uncertainty, and foreground probability. No manual masks are used for training or target-domain adaptation; validation labels, when available, are used only for final operating-point selection. Across ISIC-2017, ISIC-2018, and PH2, RABC-Net achieves macro-average DICE/JAC of 86.58\%/79.47\% and consistent matched-protocol results. Controlled within-study analyses show that RABC provides localized gains over nonlearned boundary correction, while the overall result comes from the full reliability-aware system. Adaptation updates only 3.50\% of model parameters, image-only inference runs at 87.4 FPS, and the selected operating points use $\sigma=0$ on all three datasets, indicating that learned calibration avoids extra smoothing at deployment.