{
  "abstract": "BackgroundSelf-supervised learning may improve segmentation when labelled data are limited, but its benefit may depend on model and initialisation strategy. This study evaluated in-domain masked-reconstruction pretraining across limited annotation budgets.\n\nMethodsThe International Skin Imaging Collaboration (ISIC) 2016 development set was partitioned into 765 images for self-supervised pretraining, 94 for fine-tuning and 41 for validation. Five nested annotation budgets (12-94 images) and five seeds were evaluated on the 379-image test set. A custom U-Net compared random and in-domain self-supervised initialisation; a ResNet-34 U-Net compared random, ImageNet, in-domain self-supervised and sequential ImageNet-to-self-supervised initialisation. Models trained with 94 labelled images were evaluated without adaptation on ISIC 2017. A separate experiment examined restoration-based pretraining.\n\nResultsIn the custom U-Net, self-supervised pretraining achieved higher mean Dice than random initialisation at all five budgets, including 0.664 versus 0.615 with 12 labels and 0.811 versus 0.768 with 94 labels. Seed-level 95% confidence intervals for paired differences excluded zero at 47 and 94 labels but not at the other budgets. With 47 labels, the self-supervised model achieved mean Dice of 0.789, compared with 0.768 for random initialisation with 94 labels. In ResNet-34, ImageNet initialisation achieved higher mean Dice than in-domain self-supervised pretraining at all five budgets, and adding self-supervised pretraining after ImageNet reduced mean Dice at four of five budgets. All six 94-label configurations achieved lower mean Dice on ISIC 2017 than ISIC 2016. In the restoration experiment, mean Dice was 0.686 with random initialisation and 0.638-0.642 following pretraining.\n\nConclusionsIn-domain masked-reconstruction pretraining improved mean Dice relative to random initialisation in the custom U-Net, but not consistently in the ResNet-34 U-Net, where ImageNet initialisation performed better at every budget. Adding self-supervised pretraining after ImageNet provided no consistent gain. These findings are specific to the dermoscopic lesion-segmentation experiments and do not establish melanoma-specific diagnostic or clinical performance.",
  "abstract_shown": true,
  "affiliations": [
    "University of Cambridge"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "name": "H. K. H. Hamda"
    },
    {
      "name": "S. Mustafa"
    },
    {
      "affs": [
        0
      ],
      "name": "G. Khalili Moghaddam"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/01zsxnvenzx9d.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.14.26365443",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.10.14.26365443v1.full",
  "id": "01zsxnvenzx9d",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.10.14.26365443v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "dermatology"
    ],
    [
      "openalex",
      "2730|Cutaneous Melanoma Detection and Management"
    ]
  ],
  "openalex": "W7222042228",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.10.14.26365443v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-14",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/01zsxnvenzx9d.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:57Z",
      "native_id": "10.64898/2026.10.14.26365443",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.10.14.26365443v2"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2730|Cutaneous Melanoma Detection and Management",
      "subfield": "oncology"
    }
  ],
  "title": "Self-supervised pretraining for dermoscopic lesion segmentation with limited labels: A controlled comparison of initialisation strategies",
  "title_text": "Self-supervised pretraining for dermoscopic lesion segmentation with limited labels: A controlled comparison of initialisation strategies",
  "type": "preprint",
  "updated_at": "2026-11-06T00:20:52Z",
  "url": "https://research.draconitic.com/paper/01zsxnvenzx9d",
  "venue": "medRxiv",
  "versions": []
}