EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GIT-CXR: End-to-End Transformer for Chest X-Ray Report Generation

Iustin Sîrbu, Iulia-Renata Sîrbu, Jasmina Bogojeska, Traian Rebedea

Information · 23.06.2025 · 16 (7) · 524

DOI: 10.3390/info16070524 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 23.06.2025. Verfasst von Iustin Sîrbu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: “Romanian Hub for Artificial Intelligence-HRIA”, Smart Growth, Digitization and Financial Instruments Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Medical imaging is crucial for diagnosing, monitoring, and treating medical conditions. The medical reports of radiology images are the primary medium through which medical professionals can attest to their findings, but their writing is time-consuming and requires specialized clinical expertise. Therefore, the automated generation of radiography reports has the potential to improve and standardize patient care and significantly reduce the workload of clinicians. Through our work, we have designed and evaluated an end-to-end transformer-based method to generate accurate and factually complete radiology reports for X-ray images. Additionally, we are the first to introduce curriculum learning for end-to-end transformers in medical imaging and demonstrate its impact in obtaining improved performance. The experiments were conducted using the MIMIC-CXR-JPG database, the largest available chest X-ray dataset. The results obtained are comparable with the current state of the art on the natural language generation (NLG) metrics BLEU and ROUGE-L, while setting new state-of-the-art results on F1 examples-averaged F1-macro and F1-micro metrics for clinical accuracy and on the METEOR metric widely used for NLG.

Förderung

  • “Romanian Hub for Artificial Intelligence-HRIA”, Smart Growth, Digitization and Financial Instruments Program

Zitieren

APA

Sîrbu, I., Sîrbu, I., Bogojeska, J., & Rebedea, T. (2025). GIT-CXR: End-to-End Transformer for Chest X-Ray Report Generation. Information, 16(7), 524. https://doi.org/10.3390/info16070524

Vancouver

Sîrbu I, Sîrbu I, Bogojeska J, Rebedea T. GIT-CXR: End-to-End Transformer for Chest X-Ray Report Generation. Information. 2025;16(7):524. doi:10.3390/info16070524

BibTeX
@article{Srbu2025,
  author = {Sîrbu, Iustin and Sîrbu, Iulia-Renata and Bogojeska, Jasmina and Rebedea, Traian},
  title = {GIT-CXR: End-to-End Transformer for Chest X-Ray Report Generation},
  journal = {Information},
  year = {2025},
  volume = {16},
  number = {7},
  pages = {524},
  doi = {10.3390/info16070524}
}
Kostenlos starten →