EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Repeatability of AI-quantified incidental findings on lung cancer screening CT scans in the NELSON trial

Stijn Bunk, Thijs Bruins Slot, Edwin Bennink, Grigory Sidorenkov, Nils van der Velden, Niels Schurink, Félix Lades, Markus Sebald, Marjolein A Heuvelmans, Hester A Gietema, Joachim G Aerts, Geertruida H de Bock und 5 weitere

European Radiology · 17.06.2026 · 36 (10) · 7524-7534

DOI: 10.1007/s00330-026-12669-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Radiology, online erschienen am 17.06.2026. Verfasst von Stijn Bunk und 16 weiteren Autor:innen. Beteiligte Einrichtung: University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands. s.a.o.bunk-2@umcutrecht.nl. Hauptthemen laut MEDLINE: Incidental Findings, Tomography, X-Ray Computed, Lung Neoplasms, Artificial Intelligence. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: KWF Kankerbestrijding.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Computed tomography (CT) scans for lung cancer screening provide the opportunity of quantifying incidental findings. We evaluated the repeatability of AI-based measurements of incidental findings using short-term repeat CT scan pairs. Materials and methods AI-Rad Companion Chest CT software was applied to low-dose non-contrast CT scans from the NELSON lung cancer screening trial to measure aorta diameters, coronary artery calcium volume (CACV), vertebral height and radiodensity, and emphysema (low attenuation area percentage, LAA%). Categories (absent/present) of aortic dilatation and osteopenia, and severity (none/mild/moderate/severe) of CACV and emphysema were calculated. We included subjects who had a short-term repeat CT scan pair with a maximum interval of 120 days. We analyzed repeatability with absolute and relative differences, and agreement with the intraclass correlation coefficient (ICC) and Cohen’s kappa.

Results

1436 subjects were included, with age (mean ± SD) 59.7 ± 5.7 years, 86.3% men, 55.9% currently smoking, and scan interval 85 ± 20 days. Mean absolute differences were 0.7 to 1.5 mm for aorta diameters, 26 mm 3 for CACV, 0.3 mm to 0.4 mm for vertebral height, and 7.6 HU for vertebral radiodensity. Median absolute difference was 0.8% for LAA%. Aorta diameters showed good (0.75 < ICC < 0.9) to excellent (ICC > 0.9) agreement. Agreement for the rest was excellent. Categorization Cohen’s kappa between the first and second measurements was 0.68 for aortic dilatation, 0.63 for CACV, 0.84 for osteopenia, and 0.70 for emphysema.

Conclusion

In a lung cancer screening cohort with short-term repeat CT, the repeatability and agreement of automated AI measurements of aortic diameters, coronary calcium, vertebral height and radiodensity, and emphysema was good to excellent. Key Points Question Can AI measurements of incidental findings beyond lung nodules be repeatably performed on pairs of lung cancer screening chest CT scans of the same subject?

Findings

The repeatability and agreement of AI-based measurements of aorta diameter, coronary calcium, vertebrae, and emphysema were generally excellent. Clinical relevance Measurement by radiologists of incidental findings on lung cancer screening chest CT scans imposes a high workload. AI algorithms allow for automatic measurement of incidental findings on lung cancer screening chest CT with high repeatability and agreement.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Incidental FindingsTomography, X-Ray ComputedLung NeoplasmsArtificial IntelligenceHumansMaleFemaleMiddle AgedReproducibility of ResultsEarly Detection of CancerAgedMass Screening

Stichwörter der Autor:innen

Artificial intelligenceCoronary artery diseaseEmphysemaThoracic vertebraeTomography (x-ray computed)

Autor:innen und Institutionen

  • University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands. s.a.o.bunk-2@umcutrecht.nl.
  • University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.
  • University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands.
  • Siemens Healthineers Nederland B.V, Zoetermeer, The Netherlands.
  • Siemens Healthineers AG, Forchheim, Germany.
  • Maastricht University Medical Center, Maastricht University, Maastricht, The Netherlands.

Förderung

  • KWF Kankerbestrijding

Zitieren

APA

Bunk, S., Bruins Slot, T., Bennink, E., Sidorenkov, G., van der Velden, N., Schurink, N., Lades, F., Sebald, M., Heuvelmans, M. A., Gietema, H. A., Aerts, J. G., de Bock, G. H., Schaefer-Prokop, C., de Jong, P. A., Vliegenthart, R., Mohamed Hoesein, F. A. A., & NELSON-POP consortium (2026). Repeatability of AI-quantified incidental findings on lung cancer screening CT scans in the NELSON trial. European Radiology, 36(10), 7524-7534. https://doi.org/10.1007/s00330-026-12669-3

Vancouver

Bunk S, Bruins Slot T, Bennink E, Sidorenkov G, van der Velden N, Schurink N, et al. Repeatability of AI-quantified incidental findings on lung cancer screening CT scans in the NELSON trial. European Radiology. 2026;36(10):7524-7534. doi:10.1007/s00330-026-12669-3

BibTeX
@article{Bunk2026,
  author = {Bunk, Stijn and Bruins Slot, Thijs and Bennink, Edwin and Sidorenkov, Grigory and van der Velden, Nils and Schurink, Niels and Lades, Félix and Sebald, Markus and Heuvelmans, Marjolein A and Gietema, Hester A and Aerts, Joachim G and de Bock, Geertruida H and Schaefer-Prokop, Cornelia and de Jong, Pim A and Vliegenthart, Rozemarijn and Mohamed Hoesein, Firdaus A A and NELSON-POP consortium, NELSON-POP consortium},
  title = {Repeatability of AI-quantified incidental findings on lung cancer screening CT scans in the NELSON trial},
  journal = {European Radiology},
  year = {2026},
  volume = {36},
  number = {10},
  pages = {7524--7534},
  doi = {10.1007/s00330-026-12669-3}
}
Kostenlos starten →