{
  "id": 878,
  "url": "https://arxiv.org/abs/2606.18063v1",
  "title": "When LLMs Analyze Scars: From Images to Clinically-Meaningful Features",
  "summary": "Medical image classification faces a fundamental dilemma: while deep learning models achieve remarkable performance at scale, real-world clinical scenarios often suffer from severe data scarcity due to annotation costs, privacy constraints, and disease rarity. This challenge is particularly pronounced in pathological scar classification, where differentiating keloids from hypertrophic scars requires subtle expert knowledge and labeled images are extremely limited. We propose a novel paradigm tha",
  "authors": "Ruman Wang, Hangting Ye",
  "category": "research",
  "topics": "privacy-surveillance,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-16T15:38:06.000Z",
  "fetched_at": "2026-07-14T14:14:50.326Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/878",
  "original_url": "https://arxiv.org/abs/2606.18063v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}