Foundation model-enhanced multimodal radiomics for predicting response to chemo-immunotherapy in advanced lung squamous cell carcinoma - Takeaways - MDSpire

Enhanced Multimodal Radiomics Utilizing Foundation Models for Anticipating Chemo-Immunotherapy Outcomes in Advanced Lung Squamous Cell Carcinoma

  • By

  • Zhichao Wang

  • Yang Zhang

  • Chuchu He

  • Meng Wang

  • Jun Cai

  • July 20, 2026

Share

  • 1

    A foundation model-driven multimodal fusion framework was developed for predicting treatment response to chemo-immunotherapy in advanced lung squamous cell carcinoma.

  • 2

    The study utilized baseline CT images and clinical data from 304 patients with advanced LUSC to construct a multi-source features fusion model.

  • 3

    The multi-source features fusion model achieved an AUC of 0.903 and accuracy of 0.885 in the training cohort, outperforming single-modality models.

  • 4

    SHAP analysis indicated that deep learning features were the dominant contributors to the model, with radiomics and clinical variables providing complementary information.

  • 5

    The foundation model-driven approach demonstrated strong discriminative performance and potential as a non-invasive tool for individualized treatment stratification.

Original Source(s)

Foundation model-enhanced multimodal radiomics for predicting response to chemo-immunotherapy in advanced lung squamous cell carcinoma

  • by Zhichao Wang, Yang Zhang, Chuchu He, Meng Wang, Jun Cai

  • July 20, 2026

Related Content

Disproportionality analysis of drug-related interstitial lung disease in patients with head and neck squamous cell carcinoma: a signal mining study

Correction: Fine needle assisted puncture positioning technique for CT-guided percutaneous interventions

Multimodal salvage therapy for locally advanced esophageal cancer recurrence after failed post-ESD surveillance: a case report