What question did this study set out to answer?

The aim is to enhance skin lesion segmentation across different medical imaging modalities while addressing domain shifts.

May 15, 2026Open Access

PA-SACC: pathology-anchored semantic alignment and cross-scale collaboration for cross-modality skin lesion segmentation

Key Points

The aim is to enhance skin lesion segmentation across different medical imaging modalities while addressing domain shifts.
Developed PA-SACC framework focusing on unsupervised cross-modality adaptation.
Utilized pathology-anchored semantic cues and bidirectional cross-scale collaboration.
Applied uncertainty-aware filtering to reduce noise from pseudo-labels.
Achieved a Dice score of 0.9085 ± 0.0057 on the ISIC dataset.
Obtained a Dice score of 0.8976 ± 0.0066 in a zero-shot evaluation on the PH2 dataset.
Demonstrated robust performance in out-of-distribution endoscopy evaluations.

Abstract

Severe cross-modality domain shift poses a major obstacle to reliable medical image segmentation, especially when adapting from heterogeneous multi-source ultrasound to an unlabeled dermoscopy target. Such shifts introduce pronounced appearance variation and scale mismatch, which can aggravate semantic drift, boundary degradation, and miscalibration in unsupervised adaptation. We propose Pathology-Anchored Semantic Alignment and Cross-Scale Collaboration (PA-SACC), a closed-loop framework for multi-source unsupervised cross-modality lesion segmentation. PA-SACC introduces pathology-anchored semantic cues as weak anchors to stabilize alignment across domains, leverages bidirectional cross-scale collaboration to preserve global-to-local structural coherence under resolution mismatch, and employs uncertainty-aware, confidence-adaptive filtering to suppress artifact-induced noisy pseudo-labels and improve probabilistic calibration. Adaptation is performed only on the unlabeled ISIC training split, while the ISIC test split is reserved exclusively for evaluation. PA-SACC achieves a Dice of 0.9085 ± 0.0057 on ISIC and 0.8976 ± 0.0066 under strict zero-shot evaluation on PH2, and further shows promising performance under additional out-of-distribution endoscopy evaluations. Ablation studies further support the complementary roles of the proposed components.

AI से पूछें

Bookmark

View Full Paper