Fully Automated AI-Based Lymph Node Measurements in Chest CT: Accuracy and Reproducibility Compared with Multi-Reader Assessment
Diagnostics · 24.03.2026 · 16 (7) · 967
DOI: 10.3390/diagnostics16070967 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 24.03.2026. Verfasst von Andra-Iza Iuga und 20 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50937 Cologne, Germ…. Die Arbeit nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft.
Abstract (Originalsprache)
Background/Objectives: Accurate and reproducible lymph node (LN) measurement is essential for oncologic staging and therapy monitoring but is subject to inter-reader variability. This study evaluated the accuracy and reproducibility of a fully automated artificial intelligence (AI)-based LN measurement workflow in contrast-enhanced chest CT, using multi-reader manual measurements as reference.
Methods
Sixty thoracic LNs from seven patients were independently measured by 13 radiologists in two reading rounds. The median of all measurements served as the ground truth (GT). Automated short- and long-axis diameters were derived from fully automated 3D CNN-based segmentations. Agreement between AI and manual measurements was assessed using Friedman testing, intraclass correlation coefficients (ICCs), and concordance correlation coefficients (CCCs). Measurement stability was evaluated across repeated runs on different hardware systems.
Results
A total of 2280 manual measurements were analyzed. Manual assessment showed significant inter-reader variability (p < 0.01), while intra-reader agreement was high. No significant differences were observed between AI-based measurements and the GT (all p > 0.01). Agreement was good, with CCC values of 0.86 (SAD) and 0.79 (LAD). AI-based measurements were numerically stable across hardware configurations.
Conclusions
Fully automated AI-based LN measurements in chest CT scans provide strong agreement with multi-reader consensus and high numerical stability. Automated measurement may support more standardized and reproducible oncologic imaging assessment.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50937 Cologne, Germany.
- Philips GmbH Innovative Technologies, 22335 Hamburg, Germany.
- Institute of Neuroradiology, Lucerne Cantonal Hospital, 6000 Lucerne, Switzerland.
- Department of Radiology, Hospital of the Augustinians, 50678 Cologne, Germany.
- Department of Diagnostic and Interventional Radiology, University Hospital Würzburg, 97080 Würzburg, Germany.
ORCID-Profile: Andra-Iza Iuga, Heike Carolus, Jonathan Kottlors, Miriam Rinneburger, Mathilda Weisthoff, Fabian Laqua, Thorsten Persigehl
Förderung
- Deutsche Forschungsgemeinschaft
Zitieren
APA
Iuga, A. I., Carolus, H., Caldeira, L. L., Kottlors, J., Rinneburger, M., Weisthoff, M., Fervers, P., Rauen, P., Fichter, F., Goertz, L., Niederau, P., Siedek, F., Heneweer, C., Gietzen, C., Pennig, L., Dobrostal, A., Laqua, F., Woznicki, P., Maintz, D., …, & Persigehl, T. (2026). Fully Automated AI-Based Lymph Node Measurements in Chest CT: Accuracy and Reproducibility Compared with Multi-Reader Assessment. Diagnostics, 16(7), 967. https://doi.org/10.3390/diagnostics16070967
Vancouver
Iuga AI, Carolus H, Caldeira LL, Kottlors J, Rinneburger M, Weisthoff M, et al. Fully Automated AI-Based Lymph Node Measurements in Chest CT: Accuracy and Reproducibility Compared with Multi-Reader Assessment. Diagnostics. 2026;16(7):967. doi:10.3390/diagnostics16070967
BibTeX
@article{Iuga2026,
author = {Iuga, Andra-Iza and Carolus, Heike and Caldeira, Liliana Lourenco and Kottlors, Jonathan and Rinneburger, Miriam and Weisthoff, Mathilda and Fervers, Philipp and Rauen, Philip and Fichter, Florian and Goertz, Lukas and Niederau, Pia and Siedek, Florian and Heneweer, Carola and Gietzen, Carsten and Pennig, Lenhard and Dobrostal, Anja and Laqua, Fabian and Woznicki, Piotr and Maintz, David and Baessler, Bettina and Persigehl, Thorsten},
title = {Fully Automated AI-Based Lymph Node Measurements in Chest CT: Accuracy and Reproducibility Compared with Multi-Reader Assessment},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {7},
pages = {967},
doi = {10.3390/diagnostics16070967}
}
EUVIMED