EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Malignancy risk stratification for pulmonary nodules: comparing a deep learning approach to multiparametric statistical models in different disease groups

Lars Piskorski, Manuel Debic, Oyunbileg von Stackelberg, Kai Schlamp, Linn Welzel, Oliver Weinheimer, Alan Arthur Peters, Mark Oliver Wielpütz, Thomas Frauenfelder, Hans-Ulrich Kauczor, Claus Peter Heußel, Jonas Kroschke

European Radiology · 2025

DOI: 10.1007/s00330-024-11256-8 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift European Radiology, 2025. Verfasst von Lars Piskorski und 11 weiteren Autor:innen. Beteiligte Einrichtung: Diagnostic and Interventional Radiology, Heidelberg University Hospital, Heidelberg, Germany. Hauptthemen laut MEDLINE: Deep Learning, Lung Neoplasms, Tomography, X-Ray Computed, Multiple Pulmonary Nodules. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Incidentally detected pulmonary nodules present a challenge in clinical routine with demand for reliable support systems for risk classification. We aimed to evaluate the performance of the lung-cancer-prediction-convolutional-neural-network (LCP-CNN), a deep learning-based approach, in comparison to multiparametric statistical methods (Brock model and Lung-RADS®) for risk classification of nodules in cohorts with different risk profiles and underlying pulmonary diseases. Materials and methods Retrospective analysis was conducted on non-contrast and contrast-enhanced CT scans containing pulmonary nodules measuring 5–30 mm. Ground truth was defined by histology or follow-up stability. The final analysis was performed on 297 patients with 422 eligible nodules, of which 105 nodules were malignant. Classification performance of the LCP-CNN, Brock model, and Lung-RADS® was evaluated in terms of diagnostic accuracy measurements including ROC-analysis for different subcohorts (total, screening, emphysema, and interstitial lung disease).

Results

LCP-CNN demonstrated superior performance compared to the Brock model in total and screening cohorts (AUC 0.92 (95% CI: 0.89–0.94) and 0.93 (95% CI: 0.89–0.96)). Superior sensitivity of LCP-CNN was demonstrated compared to the Brock model and Lung-RADS® in total, screening, and emphysema cohorts for a risk threshold of 5%. Superior sensitivity of LCP-CNN was also shown across all disease groups compared to the Brock model at a threshold of 65%, compared to Lung-RADS® sensitivity was better or equal. No significant differences in the performance of LCP-CNN were found between subcohorts.

Conclusion

This study offers further evidence of the potential to integrate deep learning-based decision support systems into pulmonary nodule classification workflows, irrespective of the individual patient risk profile and underlying pulmonary disease. Key Points Question Is a deep-learning approach (LCP-CNN) superior to multiparametric models (Brock model, Lung-RADS ® ) in classifying pulmonary nodule risk across varied patient profiles ?

Findings

LCP-CNN shows superior performance in risk classification of pulmonary nodules compared to multiparametric models with no significant impact on risk profiles and structural pulmonary diseases . Clinical relevance LCP-CNN offers efficiency and accuracy, addressing limitations of traditional models, such as variations in manual measurements or lack of patient data, while producing robust results. Such approaches may therefore impact clinical work by complementing or even replacing current approaches .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningLung NeoplasmsTomography, X-Ray ComputedMultiple Pulmonary NodulesSolitary Pulmonary NoduleHumansMaleFemaleRetrospective StudiesMiddle AgedAgedRisk AssessmentModels, StatisticalRadiographic Image Interpretation, Computer-AssistedAdult

Stichwörter der Autor:innen

Decision supportEmphysemaInterstitial lung diseaseLung neoplasmRisk assessment

Autor:innen und Institutionen

  • Diagnostic and Interventional Radiology, Heidelberg University Hospital, Heidelberg, Germany.
  • Translational Lung Research Center Heidelberg (TLRC), Member of the German Center for Lung Research (DZL), Heidelberg, Germany.
  • Diagnostic and Interventional Radiology with Nuclear Medicine, Thoraxklinik, Heidelberg University Hospital, Heidelberg, Germany.
  • Department for Diagnostic, Interventional and Pediatric Radiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland.
  • Diagnostic and Interventional Radiology, University Hospital Zurich, Zurich, Switzerland.
  • Diagnostic and Interventional Radiology, Heidelberg University Hospital, Heidelberg, Germany. jonas.kroschke@usz.ch.

Zitieren

APA

Piskorski, L., Debic, M., von Stackelberg, O., Schlamp, K., Welzel, L., Weinheimer, O., Peters, A. A., Wielpütz, M. O., Frauenfelder, T., Kauczor, H. U., Heußel, C. P., & Kroschke, J. (2025). Malignancy risk stratification for pulmonary nodules: comparing a deep learning approach to multiparametric statistical models in different disease groups. European Radiology. https://doi.org/10.1007/s00330-024-11256-8

Vancouver

Piskorski L, Debic M, von Stackelberg O, Schlamp K, Welzel L, Weinheimer O, et al. Malignancy risk stratification for pulmonary nodules: comparing a deep learning approach to multiparametric statistical models in different disease groups. European Radiology. 2025. doi:10.1007/s00330-024-11256-8

BibTeX
@article{Piskorski2025,
  author = {Piskorski, Lars and Debic, Manuel and von Stackelberg, Oyunbileg and Schlamp, Kai and Welzel, Linn and Weinheimer, Oliver and Peters, Alan Arthur and Wielpütz, Mark Oliver and Frauenfelder, Thomas and Kauczor, Hans-Ulrich and Heußel, Claus Peter and Kroschke, Jonas},
  title = {Malignancy risk stratification for pulmonary nodules: comparing a deep learning approach to multiparametric statistical models in different disease groups},
  journal = {European Radiology},
  year = {2025},
  doi = {10.1007/s00330-024-11256-8}
}
Kostenlos starten →