Integrative radiomics and habitat imaging models for predicting PD-L1 expression in non-small cell lung cancer - Takeaways - MDSpire

Integrative radiomics and habitat imaging models for predicting PD-L1 expression in non-small cell lung cancer

  • By

  • Hao Fang

  • Huadong Chen

  • Wei Tan

  • Peijun Liu

  • July 6, 2026

  • 0 min

Share

  • 1

    The study evaluated an arterial-phase CT-based model for predicting PD-L1 expression in non-small cell lung cancer (NSCLC).

  • 2

    A total of 246 patients with confirmed NSCLC were included, divided into training and validation cohorts for model assessment.

  • 3

    The habitat imaging model outperformed the whole-tumor radiomics model, achieving AUCs of 0.774 and 0.758 in training and validation cohorts.

  • 4

    The combined model, integrating radiomics and clinical features, demonstrated the best performance with AUCs of 0.840 and 0.828.

  • 5

    The study highlights the potential of noninvasive imaging approaches for pre-immunotherapy evaluation in NSCLC.

Original Source(s)

Integrative radiomics and habitat imaging models for predicting PD-L1 expression in non-small cell lung cancer

  • by Hao Fang, Huadong Chen, Wei Tan, Peijun Liu

  • July 6, 2026

Related Content

A prediction model for urological tumor metastasis using liquid biopsy-derived biomarkers

Modular delivery of co-stimulatory signals through a PD-1-based immunoswitch receptor improves the functionality of Hepatitis B Virus-specific engineered T cells

Advances in the multimodal management of central nervous system solitary fibrous tumors