Anatomy-Guided Radiology Report Generation With Pathology-Aware Regional Prompts
IEEE Open Journal of Engineering in Medicine and Biology · 2026 · 7 · 165-171
DOI: 10.1109/ojemb.2026.3687122 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Open Journal of Engineering in Medicine and Biology, 2026. Verfasst von Yijian Gao und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of ComputingImperial College London SW7 2AZ London U.K. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MRC Clinical Research Training Fellowship, Mittal Fund at Cleveland Clinic Philanthropy, ERC IMI.
Abstract (Originalsprache)
Goal: Radiology report generation holds significant potential to alleviate clinical workloads and streamline medical care. However, achieving high clinical accuracy remains challenging, as radiographs often feature intricate structures and subtle pathologies.
Methods
To address these challenges, this work introduces an innovative approach that explicitly integrates anatomical and pathological information into report decoding by leveraging pathology-aware regional prompts. Specifically, we develop an anatomical region detector that extracts structured visual features from distinct anatomical areas, coupled with a novel multi-label pathology detector that identifies global abnormalities.
Results
Our model demonstrates superior report generation performance in natural language generation and clinical efficacy, surpassing previous state-of-the-art methods. It achieved scores of 0.394 in BLEU-1, 0.302 in ROUGE-L, and 0.470 in F1, reflecting substantial improvements in both linguistic fluency and medical accuracy. Formal expert evaluations further affirmed the model's potential to elevate radiology practice.
Conclusion
By integrating anatomical and pathological insights to emulate radiologists' workflow, our model achieves superior accuracy and clinical coherence of radiology reporting. It offers remarkable promise to support clinical decision-making and transform patient management.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of ComputingImperial College London SW7 2AZ London U.K.
- Department of Surgery and CancerImperial College London SW7 2AZ London U.K.
- Bioengineering Department and Imperial-XImperial College London W12 7SL London U.K.
- Archimedes UnitAthena Research Centre 15125 Athens Greece.
- National Heart and Lung InstituteImperial College London SW7 2AZ London U.K.
- Cardiovascular Research CentreRoyal Brompton Hospital SW3 6NP London U.K.
ORCID-Profile: Dominic Marshall, Xiaodan Xing, Giorgos Papanastasiou, Guang Yang
Förderung
- MRC Clinical Research Training Fellowship
- Mittal Fund at Cleveland Clinic Philanthropy
- ERC IMI
- Horizon 2020 Framework Programme
- MRC
- Royal Society
- NVIDIA Academic Hardware
- NIHR Imperial Biomedical Research Centre
Zitieren
APA
Gao, Y., Marshall, D., Xing, X., Ning, J., Dai, C., Papanastasiou, G., Yang, G., & Komorowski, M. (2026). Anatomy-Guided Radiology Report Generation With Pathology-Aware Regional Prompts. IEEE Open Journal of Engineering in Medicine and Biology, 7, 165-171. https://doi.org/10.1109/ojemb.2026.3687122
Vancouver
Gao Y, Marshall D, Xing X, Ning J, Dai C, Papanastasiou G, et al. Anatomy-Guided Radiology Report Generation With Pathology-Aware Regional Prompts. IEEE Open Journal of Engineering in Medicine and Biology. 2026;7:165-171. doi:10.1109/ojemb.2026.3687122
BibTeX
@article{Gao2026,
author = {Gao, Yijian and Marshall, Dominic and Xing, Xiaodan and Ning, Junzhi and Dai, Congren and Papanastasiou, Giorgos and Yang, Guang and Komorowski, Matthieu},
title = {Anatomy-Guided Radiology Report Generation With Pathology-Aware Regional Prompts},
journal = {IEEE Open Journal of Engineering in Medicine and Biology},
year = {2026},
volume = {7},
pages = {165--171},
doi = {10.1109/ojemb.2026.3687122}
}
EUVIMED