{
  "id": 18812,
  "url": "https://arxiv.org/abs/2608.11335v1",
  "title": "Dual-Domain Cross-Modal Decoding for Clinical Text-Guided Medical Image Segmentation",
  "summary": "Clinical text can narrow down what to segment, but recent text-guided designs emphasize spatial alignment while overlooking frequency content that governs texture and boundaries. We propose Dual-Domain Cross-Modal Decoding (DD-CMD) for clinical text-guided pulmonary infection segmentation, integrating two complementary forms of language guidance during decoding. In the spatial domain, Text-Guided Spatial Cross-Attention (TGSA) aligns multi-scale visual tokens with text semantics and updates feat",
  "authors": "Md Maklachur Rahman, Tracy Hammond",
  "category": "research",
  "topics": "safety-alignment,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-11T18:40:52.000Z",
  "fetched_at": "2026-08-13T05:10:37.786Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/18812",
  "original_url": "https://arxiv.org/abs/2608.11335v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}