Evaluating Radiomics, Deep Learning, and Hybrid Models for Forecasting Hidden Pleural Spread in Non-Small Cell Lung Cancer Patients: A Retrospective Multicenter Analysis - Takeaways - MDSpire

Evaluating Radiomics, Deep Learning, and Hybrid Models for Forecasting Hidden Pleural Spread in Non-Small Cell Lung Cancer Patients: A Retrospective Multicenter Analysis

  • By

  • Tao Bao

  • Xiaoguang Li

  • Yuanlin Deng

  • Liang Chen

  • Weijie Sun

  • Mingjian Ge

  • Jigang Dai

  • Xiaolong Zhao

  • Xu Chen

  • Liang Zhang

  • Lei Bao

  • Wei Guo

  • October 29, 2025

  • 0 min

Share

  • 1

    Non-small cell lung cancer with pleural dissemination is classified as stage M1a, with a median survival time of 4–11.5 months.

  • 2

    Occult pleural dissemination occurs in 0.9–6.2% of operable NSCLC patients, often diagnosed unexpectedly during surgery.

  • 3

    The study aims to develop a noninvasive tool for preoperative identification of occult pleural dissemination in high-risk NSCLC patients.

  • 4

    A hybrid model combining radiomics and deep learning is hypothesized to outperform single-modality strategies in predicting occult pleural dissemination.

  • 5

    The study enrolled 163 NSCLC patients with confirmed occult pleural dissemination and utilized data from three high-volume centers in China.

Original Source(s)

Evaluating Radiomics, Deep Learning, and Hybrid Models for Forecasting Hidden Pleural Spread in Non-Small Cell Lung Cancer Patients: A Retrospective Multicenter Analysis

  • by Tao Bao, Xiaoguang Li, Yuanlin Deng, Liang Chen, Weijie Sun, Mingjian Ge, Jigang Dai, Xiaolong Zhao, Xu Chen, Liang Zhang, Lei Bao, Wei Guo

  • October 29, 2025

Related Content

Editorial: The role of circular RNAs and MicroRNAs in non-small cell lung cancer: from mechanisms to therapeutic potential

Editorial: Artificial intelligence advancing lung cancer screening and treatment

Lung Cancer Screening Prevalence and Changes in 2024