EUVIMEDEUVIMED entdecken
Systematische ÜbersichtMetaanalyseOpen Access · CC BY 4.0

Diagnostic accuracy of radiomics and artificial intelligence models in diagnosing lymph node metastasis in head and neck cancers: a systematic review and meta-analysis

Diagnostische Genauigkeit von Radiomics- und KI-Modellen zur Diagnose von Lymphknotenmetastasen bei Kopf-Hals-Krebs: systematische Übersicht und Metaanalyse

Parya Valizadeh, Payam Jannatdoust, Mohammad-Taha Pahlevan-Fallahy, Amir Hassankhani, Melika Amoukhteh, Sara Bagherieh, Delaram J Ghadimi, Ali Gholamrezanezhad

Neuroradiology · 2025-02 · 67 (2) · 449-467

DOI: 10.1007/s00234-024-03485-x ↗

Auf einen Blick

23 Arbeiten zeigen für Radiomics- und Deep-Learning-Modelle eine hohe diagnostische Genauigkeit zur Erkennung von Lymphknotenmetastasen bei Kopf-Hals-Krebs, am höchsten bei PET/CT-basierten Modellen.

Fragestellung

Wie genau erkennen KI- und Radiomics-Modelle Lymphknotenmetastasen bei Kopf-Hals-Krebs?

Methode

Systematische Suche in 4 Datenbanken; diagnostische Studien zu AI-Modellen bei Kopf-Hals-Krebs und Lymphknotenmetastasen; Qualitätsbewertung mit METRICS; Metaanalyse mit bivariatem Modell in R.

Ergebnisse

23 Artikel. Pooled AUC: 91% für CT-Radiomics, 84% für MRT-Radiomics, 92% für PET/CT-Radiomics. AUC: 92% für Deep Learning, 91% für handgefertigte Radiomics; 92% für Lymphknoten-Features, 89% für Primärtumor-Features.

Einschränkungen

In den meisten Studien fehlte externe Validierung; Analysen beschränkten sich auf interne Validierungssets.

Schlussfolgerung der Autor:innen

Radiomics- und Deep-Learning-Modelle zeigen eine vielversprechende Genauigkeit zur Diagnose von Lymphknotenmetastasen bei Kopf-Hals-Krebs, besonders mit PET/CT.

Kernaussagen

  • PET/CT-basierte Radiomics erreichten die höchste AUC.
  • Kein signifikanter Unterschied zwischen Deep Learning und handgefertigten Radiomics.
  • Die meisten Studien hatten keine externe Validierung.

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 Neuroradiology, online erschienen am 11.11.2024. Verfasst von Parya Valizadeh und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Medicine, Tehran University of Medical Sciences, Tehran, Iran. Hauptthemen laut MEDLINE: Head and Neck Neoplasms, Lymphatic Metastasis, Artificial Intelligence. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Southern California.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Head and neck cancers are the seventh most common globally, with lymph node metastasis (LNM) being a critical prognostic factor, significantly reducing survival rates. Traditional imaging methods have limitations in accurately diagnosing LNM. This meta-analysis aims to estimate the diagnostic accuracy of Artificial Intelligence (AI) models in detecting LNM in head and neck cancers.

Methods

A systematic search was performed on four databases, looking for studies reporting the diagnostic accuracy of AI models in detecting LNM in head and neck cancers. Methodological quality was assessed using the METRICS tool and meta-analysis was performed using bivariate model in R environment.

Results

23 articles met the inclusion criteria. Due to the absence of external validation in most studies, all analyses were confined to internal validation sets. The meta-analysis revealed a pooled AUC of 91% for CT-based radiomics, 84% for MRI-based radiomics, and 92% for PET/CT-based radiomics. Sensitivity and specificity were highest for PET/CT-based models. The pooled AUC was 92% for deep learning models and 91% for hand-crafted radiomics models. Models based on lymph node features had a pooled AUC of 92%, while those based on primary tumor features had an AUC of 89%. No significant differences were found between deep learning and hand-crafted radiomics models or between lymph node and primary tumor feature-based models.

Conclusion

Radiomics and deep learning models exhibit promising accuracy in diagnosing LNM in head and neck cancers, particularly with PET/CT. Future research should prioritize multicenter studies with external validation to confirm these results and enhance clinical applicability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Head and Neck NeoplasmsLymphatic MetastasisArtificial IntelligenceHumansSensitivity and SpecificityPositron Emission Tomography Computed TomographyMagnetic Resonance ImagingRadiomics

Stichwörter der Autor:innen

Deep learningHead and neck cancerLymph node metastasisPET/CT imagingRadiomics

Autor:innen und Institutionen

  • School of Medicine, Tehran University of Medical Sciences, Tehran, Iran.
  • Department of Radiology, Keck School of Medicine, University of Southern California (USC), 1441 Eastlake Ave Ste 2315, Los Angeles, CA, 90089, USA.
  • Department of Radiology, Mayo Clinic, Rochester, MN, USA.
  • School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran.
  • School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
  • Department of Radiology, Los Angeles General Hospital, Los Angeles, CA, USA. a.gholamrezanezhad@yahoo.com.

Förderung

  • University of Southern California

Zitieren

APA

Valizadeh, P., Jannatdoust, P., Pahlevan-Fallahy, M. T., Hassankhani, A., Amoukhteh, M., Bagherieh, S., Ghadimi, D. J., & Gholamrezanezhad, A. (2025). Diagnostic accuracy of radiomics and artificial intelligence models in diagnosing lymph node metastasis in head and neck cancers: a systematic review and meta-analysis. Neuroradiology, 67(2), 449-467. https://doi.org/10.1007/s00234-024-03485-x

Vancouver

Valizadeh P, Jannatdoust P, Pahlevan-Fallahy MT, Hassankhani A, Amoukhteh M, Bagherieh S, et al. Diagnostic accuracy of radiomics and artificial intelligence models in diagnosing lymph node metastasis in head and neck cancers: a systematic review and meta-analysis. Neuroradiology. 2025;67(2):449-467. doi:10.1007/s00234-024-03485-x

BibTeX
@article{Valizadeh2025,
  author = {Valizadeh, Parya and Jannatdoust, Payam and Pahlevan-Fallahy, Mohammad-Taha and Hassankhani, Amir and Amoukhteh, Melika and Bagherieh, Sara and Ghadimi, Delaram J and Gholamrezanezhad, Ali},
  title = {Diagnostic accuracy of radiomics and artificial intelligence models in diagnosing lymph node metastasis in head and neck cancers: a systematic review and meta-analysis},
  journal = {Neuroradiology},
  year = {2025},
  volume = {67},
  number = {2},
  pages = {449--467},
  doi = {10.1007/s00234-024-03485-x}
}
Kostenlos starten →