MaSA-UNet: Manhattan Self-Attention U-Net for skin lesion segmentation

Abstract 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.

Authors

Institutions

Publication Details

Journal
Signal Image and Video Processing
Published
2026-11-16
DOI
https://doi.org/10.1007/s11760-026-05882-6
Citations
1
Primary Topic
Cutaneous Melanoma Detection and Management
Type
article
Field-Weighted Citation Impact
2.17
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

MaSA-UNet: Manhattan Self-Attention U-Net for skin lesion segmentation

Abel A. Reyes-Angulo, Sidike Paheding
1 citations
Signal Image and Video Processing
Cutaneous Melanoma Detection and Management
2.17
article

MaSA-UNet: Manhattan Self-Attention U-Net for skin lesion segmentation

Abel A. Reyes-Angulo, Sidike Paheding
article en
1 citations

Abstract

Abstract 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.

Signal Image and Video ProcessingVol. 20(18)
Michigan Technological University (US), Fairfield University (US)
Good health and well-being
Openalex Percentile: Top 18%
Cutaneous Melanoma Detection and Management
2.17
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon