Integration of intratumoral and peritumoral CT radiomic features with machine learning algorithms for predicting induction therapy response in locally advanced non-small cell lung cancer

Abstract

Objectives: To extract intratumoral, peritumoral, and integrated intratumoral-peritumoral CT radiomic features, develop multi-source radiomic models using various machine learning algorithms to identify the optimal model, and integrate clinical factors to establish a nomogram for predicting the therapeutic response to induction therapy(IT) in locally advanced non-small cell lung cancer.

Methods: This study included 209 patients with locally advanced non-small cell lung cancer (LA-NSCLC) who received IT as the training cohort, and an external validation cohort comprising 50 patients from another center. Radiomic features were extracted from intratumoral, peritumoral, and integrated intratumoral-peritumoral regions by manually delineating the gross tumor volume (GTV) and an additional 3 mm surrounding area. Three machine learning algorithms-Support Vector Machine (SVM), XGBoost, and Gradient Boosting-were employed to construct radiomic models for each region. Model performance was evaluated in the external validation cohort using metrics such as Area Under the Curve (AUC), confusion matrix, accuracy, precision, recall, and F1 score. Finally, a comprehensive nomogram integrating the optimal radiomic model with independent clinical predictors was developed.

Results: Through a comparison of optimal machine learning algorithms, INTRAPERI, INTRA, and PERI achieved the best performance with Gradient Boosting, SVM, and XGBoost, respectively. Compared to the INTRA_SVM and PERI_XGBoost INTRA models, the fusion model that integrates INTRA and peritumoral regions within a 3 mm margin around the tumor (INTRAPERI_GradientBoosting) showed better predictive performance in the training set, with AUCs of 93.7%, 82.5%, and 89.4%, respectively. In the clinical model, the PS score was identified as an independent predictive factor. The nomogram combining clinical factors with the INTRAPERI_GradientBoosting score demonstrated clinical predictive value.

Conclusion: The INTRAPERI_GradientBoosting model, which integrates intra-tumoral and peritumoral features, performs better than the INTRA intra-tumoral and PERI peritumoral radiomics models in predicting the efficacy of IT therapy in LA-NSCLC. Additionally, the nomogram based on INTRAPERI intra-tumoral and peritumoral features combined with independent clinical predictors has clinical predictive value.

Keywords: CT imaging; Induction therapy; Intra-tumoral features; Locally advanced; Machine learning; Nomogram; Non-small cell lung cancer (NSCLC); Peritumoral features; Predictive model; Radiomics.

Fig. 1

Analysis Workflow. The workflow consists of the following steps: Feature Extraction: Radiomic and dosimetric features are extracted from lung tissue regions. Feature Selection and Modeling: Features are extracted and selected from intra-tumoral, 3 mm peritumoral, and fused intra-peritumoral regions using correlation analysis, Least Absolute Shrinkage and Selection Operator (LASSO) regression, and embedded logistic regression with three machine learning classification algorithms. Model Evaluation: Model performance is assessed through discrimination and calibration metrics. Clinical Application Assessment: The clinical applicability is evaluated using a nomogram and decision curve analysis

Fig. 2

Flowchart of patient enrollment, eligibility, and exclusion criteria

Fig. 3

Coefficients for feature selection in fused intra-peritumoral, intra-tumoral, and peritumoral regions

Fig. 4

Nomogram of the comprehensive predictive model combining the 3 mm peritumoral-fused intra-peritumoral feature model with clinical predictive factors

Fig. 5

Predictive performance of the final model’s radiomic features, clinical parameters, and comprehensive nomogram in the training cohort. decision curve analysis and calibration curves

Fig. 6

Predictive performance of radiomic features, clinical parameters, and the comprehensive nomogram in the external validation cohort. Includes decision curve analysis and calibration curves