Back to all papers

Development and Validation of an Artificial Intelligence Surgical Video Analysis Model for Predicting Visceral Pleural Invasion in Lung Cancer Surgery: A Multicenter Study.

December 22, 2025pubmed logopapers

Authors

Wu Y,Xu H,Cheng X,Li P,Li J,Jiang R,Li F,Zhao S,Wang Y,Zhang S,Sun Z,Cheng S,Guan T,Li H,Chen X,Yang F,Jiang G,Li S,Wang J,Li Y,Yang F,Tian J,Mu W,Zhou J

Affiliations (22)

  • School of Engineering Medicine, Beihang University, Beijing, China.
  • Key Laboratory of Big Data-Based Precision Medicine (Beihang University), Ministry of Industry and Information Technology of the People's Republic of China, Beijing, China.
  • Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China.
  • Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China.
  • Research Unit of Intelligence Diagnosis and Treatment in Early Non-Small Cell Lung Cancer, Chinese Academy of Medical Sciences, 2021RU002, Peking University People's Hospital, Beijing, China.
  • Institute of Advanced Clinical Medicine, Peking University, Beijing, China.
  • Shanghai Chest Hospital, Shanghai, China.
  • Department of Thoracic Surgery, Beijing Aerospace General Hospital, Beijing, China.
  • Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, China.
  • Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China. [email protected].
  • Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China. [email protected].
  • Research Unit of Intelligence Diagnosis and Treatment in Early Non-Small Cell Lung Cancer, Chinese Academy of Medical Sciences, 2021RU002, Peking University People's Hospital, Beijing, China. [email protected].
  • Institute of Advanced Clinical Medicine, Peking University, Beijing, China. [email protected].
  • School of Engineering Medicine, Beihang University, Beijing, China. [email protected].
  • Key Laboratory of Big Data-Based Precision Medicine (Beihang University), Ministry of Industry and Information Technology of the People's Republic of China, Beijing, China. [email protected].
  • CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China. [email protected].
  • School of Engineering Medicine, Beihang University, Beijing, China. [email protected].
  • Key Laboratory of Big Data-Based Precision Medicine (Beihang University), Ministry of Industry and Information Technology of the People's Republic of China, Beijing, China. [email protected].
  • Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China. [email protected].
  • Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China. [email protected].
  • Research Unit of Intelligence Diagnosis and Treatment in Early Non-Small Cell Lung Cancer, Chinese Academy of Medical Sciences, 2021RU002, Peking University People's Hospital, Beijing, China. [email protected].
  • Institute of Advanced Clinical Medicine, Peking University, Beijing, China. [email protected].

Abstract

Intraoperative diagnosis of visceral pleural invasion (VPI) during video-assisted thoracoscopic surgery (VATS) remains challenging. This study aimed to develop and validate a deep learning-based model to improve diagnostic accuracy and guide surgical decision-making. Thoracoscopic videos and clinical data from 346 patients (3367 images, 2015-2024) in one hospital were divided into training, validation, and internal-test sets (7:2:1), whereas data from 53 patients (1274 images) in two other hospitals formed the external-test set. A spatial dropout-based Residual Convolutional Neural Network (VPI-Net) was developed for estimating patients' VPI status and VPI risk score (VPIscore). The model's performance was compared against intraoperative estimations by surgeons and preoperative assessments by radiologists. The VPI-Net model demonstrated significantly higher area under the curve (AUC, 0.84-0.94) and accuracy (79.67-88.68%,) than two surgeons and one radiologist across all cohorts (p < 0.05). Additionally, the VPI-Net model outperformed human experts in sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) across all cohorts. A lower VPIscore (VPIscoreL) was significantly correlated with longer overall survival (OS), relapse-free survival (RFS), and time to progression (TTP) than a higher VPIscore (VPIscoreH) (all p < 0.001). Similar results were observed in patients who had small tumors, with those who had VPIscoreH exhibiting significantly worse RFS and TTP than those with VPIscoreL (RFS [p = 0.012], TTP [p = 0.035]). The VPIscoreL patients had a significantly longer TTP (p = 0.03) than the VPIscoreH patients after sublobectomy. The proposed model enables satisfactory intraoperative identification of VPI, potentially improving patient outcomes during VATS.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 7,500+ 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.