EUVIMEDEUVIMED entdecken
Crossref

Towards Automated FIGO Staging in Radiology: The Role of LLMs in Cervical and Endometrial Cancer

Teodoro Martín-Noguerol, Pilar López-Úbeda, Ernesto A Barrientos-Manrique, Manuel García-Ferrer, Antonio Luna

Academic Radiology · 2026-04 · 33 (4) · 1545-1555

DOI: 10.1016/j.acra.2026.01.024 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Academic Radiology, 2026-04. Verfasst von Teodoro Martín-Noguerol und 4 weiteren Autor:innen. Beteiligte Einrichtung: MRI Unit, Radiology Department, HT medica, Carmelo Torres 2, 23007 Jaén, Spain (T.M.-N., A.L.). Electronic address: t.martin.f@htime.org. Hauptthemen laut MEDLINE: Large Language Models, Endometrial Neoplasms, Uterine Cervical Neoplasms, Magnetic Resonance Imaging. Die Arbeit nennt 26 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RATIONALE AND OBJECTIVES: Staging gynecological malignancies is a complex process, and radiologists should be familiar with the evolution of FIGO staging criteria. Large Language Models (LLMs) offer potential to support radiologists by automating classification tasks from free-text MRI reports. MATERIALS AND METHODS: We conducted a retrospective study using two curated datasets of pelvic MRI reports from patients with cervical (n = 261, FIGO 2018) and endometrial cancer (n = 555, FIGO 2023). A general-purpose LLM (Cohere Command-A) was evaluated under three prompting strategies (zero-shot, guided, and chain-of-thought [CoT]), using exact stage accuracy, an ordinal FIGO distance metric, and the rate of severe errors. The Cohere Command-A model was chosen for its long-context reasoning, instruction-following capabilities, reproducible fixed version, and secure handling of sensitive clinical data. While alternative LLMs (eg, GPT-4o, Gemini, Llama-3, DeepSeek) could offer complementary insights, access, resources, and compliance constraints limited broader comparisons. RESULTS: For cervical cancer, CoT prompting achieved the highest accuracy (80.5%) and the lowest FIGO distance, with 23 severe misclassifications (≥2-stage deviation), outperforming guided and zero-shot prompting. For endometrial cancer, all strategies performed appropriately, with CoT again yielding the best results (accuracy, 90.6%) and the lowest number of severe misclassifications (37 cases), compared with guided and zero-shot prompting. In a small subset of cases with no agreement between any prompting strategy and the reference label, manual review showed that only a minority presented potentially suboptimal annotations, suggesting that CoT-based predictions may also help flag doubtful reports. CONCLUSION: The LLMs used demonstrated strong performance in automatically assigning FIGO stages for cervical and endometrial cancers from MRI reports. Their integration could reduce workload and improve consistency in staging. Further validation is needed before clinical implementation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsEndometrial NeoplasmsUterine Cervical NeoplasmsMagnetic Resonance ImagingFemaleHumansNeoplasm StagingRetrospective Studies

Stichwörter der Autor:innen

Cervical cancerEndometrial cancerFIGOLLMsStaging

Autor:innen und Institutionen

  • MRI Unit, Radiology Department, HT medica, Carmelo Torres 2, 23007 Jaén, Spain (T.M.-N., A.L.). Electronic address: t.martin.f@htime.org.
  • NLP Unit, HT medica, Jaén, Spain (P.L.-Ú.).
  • Radiology Department, HT medica, Sevilla, Spain (E.A.B.-M., M.G.-F.).
  • MRI Unit, Radiology Department, HT medica, Carmelo Torres 2, 23007 Jaén, Spain (T.M.-N., A.L.).

Zitieren

APA

Martín-Noguerol, T., López-Úbeda, P., Barrientos-Manrique, E. A., García-Ferrer, M., & Luna, A. (2026). Towards Automated FIGO Staging in Radiology: The Role of LLMs in Cervical and Endometrial Cancer. Academic Radiology, 33(4), 1545-1555. https://doi.org/10.1016/j.acra.2026.01.024

Vancouver

Martín-Noguerol T, López-Úbeda P, Barrientos-Manrique EA, García-Ferrer M, Luna A. Towards Automated FIGO Staging in Radiology: The Role of LLMs in Cervical and Endometrial Cancer. Academic Radiology. 2026;33(4):1545-1555. doi:10.1016/j.acra.2026.01.024

BibTeX
@article{MartnNoguerol2026,
  author = {Martín-Noguerol, Teodoro and López-Úbeda, Pilar and Barrientos-Manrique, Ernesto A and García-Ferrer, Manuel and Luna, Antonio},
  title = {Towards Automated FIGO Staging in Radiology: The Role of LLMs in Cervical and Endometrial Cancer},
  journal = {Academic Radiology},
  year = {2026},
  volume = {33},
  number = {4},
  pages = {1545--1555},
  doi = {10.1016/j.acra.2026.01.024}
}
Kostenlos starten →