EUVIMEDEUVIMED entdecken
Open Access

A Disease-Aware Dual-Stage Framework for Chest X-ray Report Generation

Puzhen Wu, Hexin Dong, Yi Lin, Yihao Ding, Yifan Peng

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (40) · 33953-33961

DOI: 10.1609/aaai.v40i40.40688 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Puzhen Wu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Population Health Sciences, Weill Cornell Medicine, New York, NY, USA. Die Arbeit wurde bisher 4-mal zitiert (Crossref). Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NLM NIH HHS.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Radiology report generation from chest X-rays is an important task in artificial intelligence with the potential to greatly reduce radiologists' workload and shorten patient wait times. Despite recent advances, existing approaches often lack sufficient disease-awareness in visual representations and adequate vision-language alignment to meet the specialized requirements of medical image analysis. As a result, these models usually overlook critical pathological features on chest X-rays and struggle to generate clinically accurate reports. To address these limitations, we propose a novel dual-stage disease-aware framework for chest X-ray report generation. In Stage~1, our model learns Disease-Aware Semantic Tokens (DASTs) corresponding to specific pathology categories through cross-attention mechanisms and multi-label classification, while simultaneously aligning vision and language representations via contrastive learning. In Stage~2, we introduce a Disease-Visual Attention Fusion (DVAF) module to integrate disease-aware representations with visual features, along with a Dual-Modal Similarity Retrieval (DMSR) mechanism that combines visual and disease-specific similarities to retrieve relevant exemplars, providing contextual guidance during report generation. Extensive experiments on benchmark datasets (i.e., CheXpert Plus, IU X-ray, and MIMIC-CXR) demonstrate that our disease-aware framework achieves state-of-the-art performance in chest X-ray report generation, with significant improvements in clinical accuracy and linguistic quality.

Autor:innen und Institutionen

  • Population Health Sciences, Weill Cornell Medicine, New York, NY, USA.
  • School of Physics, Mathematics and Computing, University of Western Australia, Crawley, Australia.

Förderung

  • NLM NIH HHS

Zitieren

APA

Wu, P., Dong, H., Lin, Y., Ding, Y., & Peng, Y. (2026). A Disease-Aware Dual-Stage Framework for Chest X-ray Report Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(40), 33953-33961. https://doi.org/10.1609/aaai.v40i40.40688

Vancouver

Wu P, Dong H, Lin Y, Ding Y, Peng Y. A Disease-Aware Dual-Stage Framework for Chest X-ray Report Generation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(40):33953-33961. doi:10.1609/aaai.v40i40.40688

BibTeX
@article{Wu2026,
  author = {Wu, Puzhen and Dong, Hexin and Lin, Yi and Ding, Yihao and Peng, Yifan},
  title = {A Disease-Aware Dual-Stage Framework for Chest X-ray Report Generation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {40},
  pages = {33953--33961},
  doi = {10.1609/aaai.v40i40.40688}
}
Kostenlos starten →