VICCA: Visual Interpretation and Comprehension of Chest X-ray Anomalies in Generated Report Without Human Feedback

Documenti analoghi

• Semantic Textual Similarity Assessment in Chest X-ray Reports Using a Domain-Specific Cosine-Based Metric
  di: Picha, Sayeh Gholipour, et al.
  Pubblicazione: (2024)
• Grounding Chest X-Ray Visual Question Answering with Generated Radiology Reports
  di: Serra, Francesco Dalla, et al.
  Pubblicazione: (2025)
• PadChest-GR: A Bilingual Chest X-ray Dataset for Grounded Radiology Report Generation
  di: Castro, Daniel C., et al.
  Pubblicazione: (2024)
• A Vision-Language Foundation Model to Enhance Efficiency of Chest X-ray Interpretation
  di: Chen, Zhihong, et al.
  Pubblicazione: (2024)
• Pretraining Vision-Language Model for Difference Visual Question Answering in Longitudinal Chest X-rays
  di: Cho, Yeongjae, et al.
  Pubblicazione: (2024)