EUVIMEDEUVIMED entdecken
Systematische ÜbersichtMetaanalyseOpen Access · CC BY 4.0

Imaging based artificial intelligence for predicting lymph node metastasis in cervical cancer patients: a systematic review and meta-analysis

Bildbasierte künstliche Intelligenz zur Vorhersage von Lymphknotenmetastasen bei Patient:innen mit Zervixkarzinom: systematische Übersicht und Metaanalyse

Chu-Qian Jiang, Xiu-Juan Li, Zhi-Yi Zhou, Qing Xin, Lin Yu

Frontiers in Oncology · 28.02.2025 · 15

DOI: 10.3389/fonc.2025.1532698 ↗

Auf einen Blick

Die Metaanalyse zeigt für bildbasierte KI eine höhere diagnostische Leistung als für Radiolog:innen beim Nachweis von Lymphknotenmetastasen bei Zervixkarzinom.

Fragestellung

Wie gut erkennt bildbasierte KI Lymphknotenmetastasen bei Zervixkarzinom und wie schneidet sie im Vergleich zu Radiolog:innen ab?

Methode

Systematische Übersicht und Metaanalyse nach PRISMA-DTA; Suche in PubMed, Embase und Web of Science bis Oktober 2024. Referenzstandard war Pathologie; Pooling mit bivariatem Random-Effects-Modell.

Ergebnisse

23 Studien. Intern: Sensitivität 0,83 (95 %-KI 0,78–0,87), Spezifität 0,78 (95 %-KI 0,74–0,82), AUC 0,87 (95 %-KI 0,84–0,90). Extern: 0,70 (95 %-KI 0,56–0,81), 0,85 (95 %-KI 0,66–0,95), AUC 0,76 (95 %-KI 0,72–0,79). Radiolog:innen: 0,54, 0,79, AUC 0,65.

Einschränkungen

Es bestand eine erhebliche Heterogenität zwischen den eingeschlossenen Studien.

Schlussfolgerung der Autor:innen

Bildbasierte KI zeigte eine höhere diagnostische Leistung als Radiolog:innen. Prospektive Studien mit strenger Standardisierung und externe Validierung sind notwendig.

Kernaussagen

  • Intern: Sensitivität 0,83 und Spezifität 0,78
  • Radiolog:innen: Sensitivität 0,54 und AUC 0,65
  • Externe Validierung: Sensitivität 0,70, Spezifität 0,85

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Systematische Übersicht in der Zeitschrift Frontiers in Oncology, online erschienen am 28.02.2025. Verfasst von Chu-Qian Jiang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Obstetrics, Guangdong Provincial Key Laboratory of Major Obstetric Diseases, Guangdong Provincial Clinical Research Center for Obstetri…. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

This meta-analysis was conducted to assess the diagnostic performance of artificial intelligence (AI) based on imaging for detecting lymph node metastasis (LNM) among cervical cancer patients and to compare its performance with that of radiologists.

Methods

A comprehensive literature search was conducted across PubMed, Embase, and Web of Science to identify relevant studies published up to October 2024. The search followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses of Diagnostic Test Accuracy (PRISMA-DTA) guidelines. Studies evaluating the accuracy of AI models in detecting LNM in cervical cancer through computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography/computed tomography (PET/CT) were included. Pathology served as the reference standard for validation. A bivariate random-effects model was employed to estimate pooled sensitivity and specificity, both presented alongside 95% confidence intervals (CIs). Bias was assessed with the revised Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. Study heterogeneity was examined through the I 2 statistic. Meta-regression was conducted when significant heterogeneity (I 2 > 50%) was observed.

Results

A total of 23 studies were included in this meta-analysis. The quality and bias of the included studies were acceptable. However, substantial heterogeneity was observed among the included studies. Internal validation sets comprised 23 studies and 1,490 patients. The pooled sensitivity, specificity, and the area under the curve (AUC) for detecting LNM in cervical cancer were 0.83 (95% CI: 0.78-0.87), 0.78 (95% CI: 0.74-0.82) and 0.87 (95% CI: 0.84-0.90), respectively. External validation sets comprised six studies and 298 patients. The pooled sensitivity, specificity, and AUC for detecting LNM were 0.70 (95% CI: 0.56-0.81), 0.85 (95% CI: 0.66-0.95) and 0.76 (95% CI: 0.72-0.79), respectively. For radiologists, eight studies and 644 patients were included; the pooled sensitivity, specificity, and AUC for detecting LNM were 0.54 (95% CI: 0.42-0.66), 0.79 (95% CI: 0.59-0.91) and 0.65 (95% CI: 0.60-0.69), respectively.

Conclusions

Imaging-based AI demonstrates higher diagnostic performance than radiologists. Prospective studies with rigorous standardization as well as further research with external validation datasets, are necessary to confirm the results and assess their practical clinical applicability. Systematic Review Registration https://www.crd.york.ac.uk/PROSPERO , identifier CRD42024607074.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencecervical cancerlymph node metastasismeta-analysisradiomic

Autor:innen und Institutionen

  • Department of Obstetrics, Guangdong Provincial Key Laboratory of Major Obstetric Diseases, Guangdong Provincial Clinical Research Center for Obstetrics and Gynecology, Guangdong-Hong Kong-Macao Greater Bay Area Higher E…
  • Department of Obstetrics and Gynecology, Guangdong Provincial Key Laboratory of Major Obstetric Diseases, Guangdong Provincial Clinical Research Center for Obstetrics and Gynecology, Guangdong-Hong Kong-Macao Greater Ba…
  • Department of Clinical Medicine, The Third Clinical School of Guangzhou Medical University, Guangzhou, China.

Zitieren

APA

Jiang, C. Q., Li, X. J., Zhou, Z. Y., Xin, Q., & Yu, L. (2025). Imaging based artificial intelligence for predicting lymph node metastasis in cervical cancer patients: a systematic review and meta-analysis. Frontiers in Oncology, 15. https://doi.org/10.3389/fonc.2025.1532698

Vancouver

Jiang CQ, Li XJ, Zhou ZY, Xin Q, Yu L. Imaging based artificial intelligence for predicting lymph node metastasis in cervical cancer patients: a systematic review and meta-analysis. Frontiers in Oncology. 2025;15. doi:10.3389/fonc.2025.1532698

BibTeX
@article{Jiang2025,
  author = {Jiang, Chu-Qian and Li, Xiu-Juan and Zhou, Zhi-Yi and Xin, Qing and Yu, Lin},
  title = {Imaging based artificial intelligence for predicting lymph node metastasis in cervical cancer patients: a systematic review and meta-analysis},
  journal = {Frontiers in Oncology},
  year = {2025},
  volume = {15},
  doi = {10.3389/fonc.2025.1532698}
}
Kostenlos starten →