{
  "abstract": "Objective Dermoscopic skin lesion segmentation suffers from low contrast, artifacts, and blurred boundaries in lightweight models due to lossy downsampling and rigid tokenization. We propose Structure-Preserving Representation Learning (SP-RL), a lightweight framework designed to preserve geometric topology and continuity for stronger representation learning. Methods SP-RL integrates four components: 1) Structure-Preserving Sampling Strategy (SPSS) using a bijective pixel-folding mechanism to redistribute spatial details into channel dimensions; 2) Lite Multi-Scale Aggregation Block (LMA-Block) to expand receptive fields at high resolutions; 3) Dual-Resolution Attention (DR-Atn) maintaining high-resolution queries while compressing keys/values via hierarchical pooling; and 4) Dual-Gated Multi-Scale Fusion (DG-MSF) to suppress low-level artifacts and inject noise-resilient Sobel gradient priors into progressive deconvolution paths. Results Evaluations across 23 models show SP-RL achieves a 0.8976 Dice score and the lowest HD95 (15.1829) on ISIC2018 among lightweight alternatives. It exhibits superior robustness across four public datasets (ISIC 2016/2017/2018, PH 2 ) and unseen domains like HAM10000 under severe noise and focus blur. Conclusion SP-RL offers an optimal trade-off between boundary accuracy, reliability, and efficiency. By retaining high-frequency energy and domain-invariant morphology, it provides a dependable solution for resource-constrained diagnosis.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "name": "Xu Yang"
    },
    {
      "name": "Duwei Dai"
    },
    {
      "name": "Caixia Dong"
    },
    {
      "name": "Liang Wang"
    },
    {
      "name": "Pengyu Ren"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0sxd856m59mks.bib",
  "cited_by": 0,
  "doi": "10.1177/20552076261502184",
  "fulltext_url": "https://doi.org/10.1177/20552076261502184",
  "id": "0sxd856m59mks",
  "issns": [
    "2055-2076"
  ],
  "landing_url": "https://doi.org/10.1177/20552076261502184",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "R858-859.7"
    ],
    [
      "openalex",
      "2730|Cutaneous Melanoma Detection and Management"
    ]
  ],
  "openalex": "W7224116282",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-29",
  "publisher": "SAGE Publishing",
  "ris": "https://research.draconitic.com/paper/0sxd856m59mks.ris",
  "sources": [
    {
      "first_seen": "2026-10-31T14:22:24Z",
      "native_id": "6ae8202c3f11409ca320aaeb6da6af56",
      "source": "doaj",
      "url": "https://doi.org/10.1177/20552076261502184"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2730|Cutaneous Melanoma Detection and Management",
      "subfield": "oncology"
    }
  ],
  "title": "Structure-preserving lightweight skin lesion segmentation with dual-resolution attention and boundary-aware fusion",
  "title_text": "Structure-preserving lightweight skin lesion segmentation with dual-resolution attention and boundary-aware fusion",
  "type": "peer-reviewed",
  "updated_at": "2026-10-31T14:22:24Z",
  "url": "https://research.draconitic.com/paper/0sxd856m59mks",
  "venue": "Digital Health",
  "versions": []
}