What question did this study set out to answer?

The aim is to create a predictive model for radiation pneumonitis risk using dosiomics and radiomics features.

February 16, 2026Open Access

Improving the Prediction of Radiation Pneumonitis: Leveraging Radiomics and Dosiomics Within IDLSS Lung Subregions

Key Points

The aim is to create a predictive model for radiation pneumonitis risk using dosiomics and radiomics features.
Retrospective analysis of 136 lung cancer patients treated with VMAT
IDLSS method used to delineate seven lung subregions on CT images
Features extracted from the subregions and organized into nine feature sets
LASSO for feature selection, applied SMOTE to address class imbalance
Logistic regression, random forest, and neural networks used for modeling and evaluation
BMI and volume in specific lung regions were significant predictors of radiation pneumonitis
Dosiomics features outperformed traditional DVH features
Combined radiomics and dosiomics achieved highest accuracy with AUC of 0.91
SMOTE improved sensitivity without losing specificity
No additional performance gains were seen from incorporating all features together

Abstract

Purpose: This study develops a predictive model for radiation pneumonitis (RP) risk in lung cancer patients after volume-modulated arc therapy (VMAT) that leverages high-dimensional dosiomics and dose–volume histogram (DVH) features within IDLSS (incremental-dose interval-based lung subregion) lung subregions. Methods: We retrospectively analyzed data from 136 lung cancer patients treated with VMAT between 2015 and 2022, including 39 patients who developed RP greater than Grade 2. Using the IDLSS method, seven regions of interest (ROIs), including the Planning Target Volume (PTV), normal lung, and five subdivided lung areas, were delineated on pretreatment Computed Tomography (CT) images. DVH, radiomics, and dosiomics features were extracted from these ROIs and organized into nine distinct feature sets. A comprehensive pipeline was applied, integrating IDLSS-defined lung subregions, high-dimensional dosiomics features, LASSO-based feature selection, and SMOTE oversampling to address class imbalance in the training data. Logistic regression, random forest, and feedforward neural networks were constructed and optimized via tenfold cross-validation. Model performance across different feature sets was evaluated via the average AUC, F1 score, and other performance metrics. Results: LASSO regression revealed that BMI and volume within the 5–10 Gy and 10–20 Gy lung subregions were significant predictors of RP. The performance evaluation demonstrated that the dosiomics features consistently outperformed the DVH features across the models. Combining radiomics and dosiomics achieved the highest predictive accuracy (AUC = 0.91, ACC = 0.89, NPV = 0.95, PPV = 0.78, F1 score = 0.82, sensitivity = 0.88, specificity = 0.90). Applying SMOTE during training significantly improved sensitivity without compromising specificity, confirming the value of balancing strategies in enhancing model performance. Incorporating all the features together did not provide additional performance gains. Conclusions: Integrating radiomics and dosiomics features extracted from IDLSS-defined lung subregions significantly enhances the ability to predict RP after VMAT, surpassing traditional DVH metrics. The substantial contribution of dosiomics features highlights the importance of spatial dose heterogeneity in RP risk assessment.

AI에게 질문

Bookmark

View Full Paper