Related Experiment Video
Updated: Jun 30, 2026

Endobronchial Ultrasound-guided Intratumoral Injection of Cisplatin for the Treatment of Isolated Mediastinal Recurrence of Lung Cancer
Published on: February 12, 2017
A pathomics model for predicting response to chemo-immunotherapy in lung squamous cell carcinoma: A multicenter study
Dongying Wang1, Shuai Mu2, Minghui Zhang3
1Department of Respiratory and Critical Care Medicine, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200030, China; Shanghai Key Laboratory of Thoracic Tumor Biotherapy, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200030, China.
A new pathomics model accurately predicts T cell-inflamed gene-expression profile (GEP) status in lung squamous cell carcinoma (LUSC). This model identifies patients who benefit from chemo-immunotherapy (CIT), improving survival outcomes.
Area of Science:
- Oncology
- Computational Pathology
- Genomics
Background:
- Identifying lung squamous cell carcinoma (LUSC) patients benefiting from first-line chemo-immunotherapy (CIT) is challenging.
- Predicting treatment response requires robust biomarkers.
Purpose of the Study:
- Develop a pathomics model to predict T cell-inflamed gene-expression profile (GEP) status in LUSC.
- Validate the model's utility in identifying patients who benefit from CIT.
Main Methods:
- Whole-slide images and RNA-sequencing data from TCGA LUSC cohort (n=334) were used to develop the pathomics model and pathomics score (PS).
- Model's predictive value was validated in a prospective multicenter trial (AK105-302, n=267) and two independent cohorts (n=82, n=50).
- Interaction between PS and treatment (CIT vs. chemotherapy) was assessed for progression-free survival (PFS) and overall survival (OS).
Main Results:
- The pathomics model achieved AUCs of 0.80 (training) and 0.71 (validation) for GEP status prediction.
- Significant interactions between PS and treatment were found for PFS (p=0.011) and OS (p<0.001).
- High PS patients receiving CIT showed significantly prolonged PFS (HR: 0.31) and OS (HR: 0.30) compared to high PS patients receiving chemotherapy; low PS patients did not show this benefit.
- High PS was associated with an immune-hot tumor microenvironment.
Conclusions:
- A GEP-based pathomics model was developed.
- This model offers a practical, cost-effective strategy to identify LUSC patients likely to gain superior survival benefit from first-line CIT over chemotherapy alone.
Related Concept Videos
Mouse Models of Cancer Study
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
Treatment Resistant Cancers
Mouse Models of Cancer Study
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
Treatment Resistent Cancers
Tumor Immunotherapy

