Integrated radiomics, dose-volume histogram criteria and clinical features for early prediction of saliva amount reduction after radiotherapy in nasopharyngeal cancer patients

Abstract

Purpose Previously, the evaluation of xerostomia depended on subjective grading systems, rather than the accurate saliva amount reduction. Our aim was to quantify acute xerostomia with reduced saliva amount, and apply radiomics, dose-volume histogram (DVH) criteria and clinical features to predict saliva amount reduction by machine learning techniques. Material and methods Computed tomography (CT) of parotid glands, DVH, and clinical data of 52 patients were collected to extract radiomics, DVH criteria and clinical features, respectively. Firstly, radiomics, DVH criteria and clinical features were divided into 3 groups for feature selection, in order to alleviate the masking effect of the number of features in different groups. Secondly, the top features in the 3 groups composed integrated features, and features selection was performed again for integrated features. In this study, feature selection was used as a combination of eXtreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP) to alleviate multicollinearity. Finally, 6 machine learning techniques were used for predicting saliva amount reduction. Meanwhile, top radiomics features were modeled using the same machine learning techniques for comparison. Result 17 integrated features (10 radiomics, 4 clinical, 3 DVH criteria) were selected to predict saliva amount reduction, with a mean square error (MSE) of 0.6994 and a R2 score of 0.9815. Top 17 and 10 selected radiomics features predicted saliva amount reduction, with MSE of 0.7376, 0.7519, and R2 score of 0.9805, 0.9801, respectively. Conclusion With the same number of features, integrated features (radiomics + DVH criteria + clinical) performed better than radiomics features alone. The important DVH criteria and clinical features mainly included, white blood cells (WBC), parotid_glands_Dmax, Age, parotid_glands_V15, hemoglobin (Hb), BMI and parotid_glands_V45.

Predicting severe radiation-induced oral mucositis in head and neck cancer patients using integrated baseline CT radiomic, dosimetry, and clinical features: A machine learning approach

“…The augmentation of dosimetric and clinical information contributed to an improvement in AUC (91.7 %) and precision (100.0 %) values. Our findings align with previous studies [ 23 , 42 ], demonstrating that the incorporation of baseline imaging RFs with dose-volume and clinical data improves the accuracy of machine learning models in predicting radiation-induced xerostomia compared to clinical or dose-volume features alone. In contrast to the findings of Sheikh et al's study, our present study identified different top clinical features for mucositis prediction, as shown in Table 2 .…”

“…Many studies have indicated that radiomics can be a valuable tool to facilitate precision diagnosis, treatment planning, and predicting outcomes [ 22 ]. In recent years, it has been shown that integrating quantitative medical imaging biomarkers into clinical and dosimetric data has improved the prediction of radiation-induced toxicities in the treatment of various cancers [ 19 , [23] , [24] , [25] , [26] ]. Moreover, the advances in AI, principally machine learning models, have boosted the potential of the typically high-dimensional quantitative radiomics features (RFs) in predicting RT-induced toxicity [ [26] , [27] , [28] ].…”