Related Experiment Video
Updated: Jan 13, 2026
Using Micro-computed Tomography for the Assessment of Tumor Development and Follow-up of Response to Treatment in a Mouse Model of Lung Cancer
Published on: May 20, 2016
Computed tomography-based texture analysis for predicting adjuvant therapy response in postoperative patients with
Dawei Wang1, Min Wang2, Jianxia Song2
1Department of Thoracic Surgery, the First Affiliated Hospital of Hebei North University, Zhangjiakou, China.
Background:
Emerging research suggests that epidermal growth factor receptor (EGFR)-tyrosine kinase inhibitor (TKI) agents are not universally effective in patients with EGFR-mutant non-small cell lung cancer (NSCLC), with many developing varying degrees of acquired resistance. Studies have found that such resistance is significantly associated with certain imaging features. Therefore, this study aimed to examine the application value of combining texture analysis techniques with computed tomography (CT) images in predicting the efficacy of targeted adjuvant therapy in patients with EGFR-mutant NSCLC following surgery.
Methods:
The basic clinical data of patients with EGFR-mutant NSCLC who underwent surgery followed by targeted therapy with first-generation EGFR-TKIs at the First Affiliated Hospital of Hebei North University between January 2019 and September 2024 were retrospectively collected. Texture features of the tumor were extracted from chest CT images via 3D Slicer software, and after standardization, feature dimensionality reduction and selection were performed through correlation analysis and the least absolute shrinkage and selection operator (LASSO) algorithm. Univariate and multivariate logistic regression analyses were then conducted on clinical and texture features to identify independent prognostic factors. A clinical model, a radiomics texture model, and a joint model were developed with R software (The R Foundation for Statistical Computing). Model performance was assessed with the area under the curve (AUC), calibration curves, and decision curve analysis (DCA). A nomogram was constructed based on the combined model.
Results:
In this study, 150 texture features were extracted, and dimensionality reduction was conducted with the LASSO algorithm. At the optimal l-value of 0.0753, three candidate features were preliminarily selected. These three features were then subjected to univariate and multivariate logistic regression analyses, ultimately yielding one significant texture feature. Smoking was found to be an independent prognostic factor for patients with EGFR-mutant NSCLC (P<0.05). The AUC for predicting poor prognosis in patients with EGFR-mutant NSCLC was 0.756 for the clinical model, 0.771 for the texture-analysis model, and 0.90 for the combined model. The combined model demonstrated significantly better predictive performance than the individual models (P<0.05). DCA further confirmed the superior clinical utility of the combined model. A nomogram was constructed to provide an intuitive and quantitative tool for evaluating treatment efficacy in individual patients.
Conclusions:
CT texture-based analysis demonstrated favorable predictive performance in assessing the efficacy of postoperative adjuvant targeted therapy in patients with EGFR-mutant NSCLC. The proposed model offers an intuitive and reliable reference for individualized treatment planning.
Insights
Computed tomography texture analysis combined with clinical data predicts treatment efficacy in EGFR-mutant non-small cell lung cancer (NSCLC). This radiomics approach improves prediction of targeted therapy response after surgery.
Area of Science:
- Oncology
- Radiology
- Medical Imaging
Background:
- Epidermal growth factor receptor (EGFR)-tyrosine kinase inhibitors (TKIs) show variable effectiveness in EGFR-mutant non-small cell lung cancer (NSCLC).
- Acquired resistance to EGFR-TKI therapy is a significant clinical challenge in NSCLC management.
- Specific imaging features on computed tomography (CT) scans are associated with resistance to targeted therapies.
Purpose of the Study:
- To evaluate the utility of combining CT texture analysis with clinical data for predicting the efficacy of adjuvant targeted therapy in postsurgical EGFR-mutant NSCLC patients.
- To develop and validate predictive models for treatment response in this patient cohort.
Main Methods:
- Retrospective collection of clinical data from EGFR-mutant NSCLC patients treated with first-generation EGFR-TKIs post-surgery.
- Extraction and analysis of tumor texture features from CT images using 3D Slicer and LASSO algorithm for dimensionality reduction.
- Development of clinical, radiomics texture, and combined models using logistic regression and R software.
- Assessment of model performance using Area Under the Curve (AUC), calibration curves, and Decision Curve Analysis (DCA).
Main Results:
- A single significant texture feature and smoking as an independent prognostic factor were identified.
- The combined model achieved a superior AUC of 0.90 for predicting poor prognosis, outperforming individual clinical (0.756) and texture (0.771) models.
- Decision Curve Analysis confirmed the enhanced clinical utility of the combined model.
Conclusions:
- CT texture analysis shows promise in predicting the efficacy of postoperative adjuvant targeted therapy for EGFR-mutant NSCLC.
- The developed combined model provides a reliable tool for personalized treatment planning and predicting therapy response.
More Related Videos
12:24Computed Tomography-guided Time-domain Diffuse Fluorescence Tomography in Small Animals for Localization of Cancer Biomarkers
Published on: July 17, 2012
10:28Gene Regulation and Targeted Therapy in Gastric Cancer Peritoneal Metastasis: Radiological Findings from Dual Energy CT and PET/CT
Published on: January 22, 2018