Beyond Accuracy: Uncertainty-Guided Boundary Refinement for Reliable Biomedical Image Segmentation
Anima Kujur
原文摘要
Accurate biomedical image segmentation requires not only high global overlap but also reliable delineation of clinically meaningful boundaries. In blood-smear microscopy, cytoplasm and nucleus contours provide the structural basis for downstream morphology analysis; however, deep segmentation models may remain uncertain or overconfident near ambiguous boundary regions even when achieving strong Dice scores. This work proposes a Reliability-Aware Boundary Refinement Network (RABR-Net), a two-stage framework for reliability-aware biomedical image segmentation. A strong UNet++ EfficientNet-B4 base segmenter first produces initial class probabilities and logits. Predictive entropy, test-time augmentation variance, margin uncertainty, foreground probability gradients, and foreground soft-boundary cues are combined with the multiclass probabilities into a reliability-aware representation. This representation guides a gated residual refiner that selectively corrects uncertain boundary regions while preserving confident regions of the base prediction. The framework is evaluated using overlap accuracy, class-wise Dice, Boundary Dice, HD95/ASSD, expected calibration error, risk-coverage analysis, qualitative correction maps, and paired statistical testing. As a separate diagnostic analysis, we additionally characterize the sensitivity of the selected base segmenter to deterministic microscopy image perturbations.
cs.CV · cs.LG