Back to all papers

Deep learning for visceral pleural invasion in non-small cell lung cancer.

May 22, 2026pubmed logopapers

Authors

Liu Y,Shi H,Wu Y,Xu C,Xie Z,Wang J,Zhu J,Liang B

Affiliations (6)

  • Department of Radiology, Anqing Medical Center of Anhui Medical University, Anqing, Anhui Province, 246000, China.
  • Wannan Medical College, Wuhu, Anhui Province, 241000, China; Department of Radiology, Anqing Medical Center of Anhui Medical University, Anqing, Anhui Province, 246000, China.
  • Anhui Medical University, Hefei, Anhui Province, 230000, China; Department of Radiology, Anqing Medical Center of Anhui Medical University, Anqing, Anhui Province, 246000, China.
  • Department of Radiology, The First Affiliated Hospital of Bengbu Medical College, Bengbu, Anhui, 233000, China.
  • Department of Radiology, Tongde Hospital of Zhejiang Province, Hangzhou, Zhejiang Province, 310000, China.
  • Anqing Medical College, Anqing, Anhui Province, 246052, China. Electronic address: [email protected].

Abstract

To evaluate and compare the diagnostic performance of several commonly used deep learning (DL) models and a conventional clinical-radiological feature model based on preoperative computed tomography (CT) for predicting visceral pleural invasion (VPI) in non-small cell lung cancer (NSCLC). A retrospective cohort of 3,406 patients from four hospitals was analyzed. Data were split into training, validation, and test sets. A logistic regression model using clinical-radiological features was compared against five DL architectures (including Res2Net_3D8F and ResNet variants). Performance was evaluated via AUC, sensitivity, specificity, PPV, and NPV. In the independent test set, the clinical-radiological feature model achieved the highest AUC (0.875), but with low sensitivity (0.21) and high specificity (0.96). The best-performing DL model (Res2Net_3D8F) achieved an AUC of 0.835, with sensitivity of 0.83, specificity of 0.74, PPV of 0.36, and NPV of 0.96. All DL models demonstrated higher sensitivity (0.71-0.83) but lower PPV (0.29-0.36) compared to the clinical model. There was no statistically significant difference in AUC between the Res2Net_3D8F model and the clinical-radiological model in the test set (P = .123, DeLong test). Although both clinical and DL models based on CT imaging showed moderate discriminatory ability for preoperative VPI prediction, neither approach achieved optimal clinical utility. The clinical model had high specificity but very low sensitivity, while DL models had improved sensitivity but low PPV and did not outperform the clinical model. Noninvasive VPI prediction remains a significant challenge, highlighting the need for further methodological advancements and validation.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.