Answers are grounded in this paper and cite their sources.
Melanoma is one of the deadliest forms of skin cancer, and early diagnosis depends on accurate delineation of suspicious lesions in dermoscopic images. This study introduces MaSA-UNet, a U-Net-based segmentation framework augmented with Manhattan Self-Attention (MaSA) for spatial context modeling, self-supervised denoising pretraining for representation learning, and a weighted composed loss (WCL) for overlap-aware optimization. The model is evaluated on four public skin-lesion benchmarks: ISIC 2016, ISIC 2017, ISIC 2018, and PH ² 2 . In response to reviewer concerns, the revised study adds controlled multi-seed experiments, confidence intervals, paired statistical tests, isolated SSL comparisons, WCL sensitivity discussion, inference-time measurements, and a cross-dataset robustness discussion. The results show that MaSA-UNet remains competitive with strong U-Net baselines and can improve Dice and Jaccard on PH ² 2 and ISIC 2016, while additional controlled experiments reveal dataset-dependent behavior on ISIC 2017 and ISIC 2018. These findings support MaSA as a useful contextual refinement mechanism for skin-lesion segmentation, while also clarifying the limitations of the current SSL and loss-weighting strategies. The source code will be made available in a GitHub repository upon publication.
No takes yet. Share an insight, caveat, or question.
Reyes-Angulo et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: