{
  "id": 5176,
  "url": "https://arxiv.org/abs/2604.27559v1",
  "title": "RIHA: Report-Image Hierarchical Alignment for Radiology Report Generation",
  "summary": "Radiology report generation (RRG) has emerged as a promising approach to alleviate radiologists' workload and reduce human errors by automatically generating diagnostic reports from medical images. A key challenge in RRG is achieving fine-grained alignment between complex visual features and the hierarchical structure of long-form radiology reports. Although recent methods have improved image-text representation learning, they often treat reports as flat sequences, overlooking their structured s",
  "authors": "Yucheng Chen, Yang Yu, Yufei Shi, Conghao Xiong, Xulei Yang, Si Yong Yeo",
  "category": "research",
  "topics": "safety-alignment,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-30T08:08:46.000Z",
  "fetched_at": "2026-07-14T16:31:35.572Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5176",
  "original_url": "https://arxiv.org/abs/2604.27559v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}