3D intratumoral heterogeneity-based quantitative score from chest CT for preoperative prediction of visceral pleural invasion in lung adenocarcinoma: a multicenter study - Takeaways - MDSpire

3D intratumoral heterogeneity-based quantitative score from chest CT for preoperative prediction of visceral pleural invasion in lung adenocarcinoma: a multicenter study

  • By

  • Qunzhi Ouyang

  • Yanping Wu

  • Liuhan Zhou

  • Wanyin Qi

  • Sanhong Zhang

  • Yan Zhao

  • Jingyi Zuo

  • May 12, 2026

  • 0 min

Share

  • 1

    Visceral pleural invasion (VPI) is a significant prognostic factor in lung adenocarcinoma (LUAD) affecting treatment and survival outcomes.

  • 2

    A multicenter study involving 1,301 LUAD patients developed a stacking ensemble model to predict VPI using 3D intratumoral heterogeneity (ITH) scores.

  • 3

    The stacking ensemble classifier achieved an AUC of 0.878, outperforming conventional radiomics and clinicoradiologic models in predicting VPI.

  • 4

    SHAP analysis indicated that the 3D ITH score was the most influential predictor of VPI, followed by nodule size and CT density.

  • 5

    This study highlights the potential of integrating 3D ITH scores with clinical features for improved preoperative risk stratification in LUAD.

Original Source(s)

Related Content