Radiomics and dosiomics-based prediction of radiotherapy-induced xerostomia in head and neck cancer patients

Dose-response modeling for radiotherapy-induced xerostomia in head and neck cancer (HN) patients is a promising frontier for personalized therapy. Feature extraction from diagnostic and therapeutic images (radiomics and dosiomics features) can be used for data-driven response modeling. The aim of this study is to develop xerostomia predictive models based on radiomics-dosiomics features. Data from the cancer imaging archive (TCIA) for 31 HN cancer patients were employed. For all patients, parotid CT radiomics features were extracted, utilizing Lasso regression for feature selection and multivariate modeling. The models were developed by selected features from pretreatment (CT₁), mid-treatment (CT₂), post-treatment (CT₃), and delta features (ΔCT_2-1, ΔCT_3-1, ΔCT_3-2). We also considered dosiomics features extracted from the parotid dose distribution images (Dose model). Thus, combination models of radio-dosiomics (CT + dose & ΔCT + dose) were developed. Moreover, clinical, and dose-volume histogram (DVH) models were built. Nested 10-fold cross-validation was used to assess the predictive classification of patients into those with and without xerostomia, and the area under the receiver operative characteristic curve (AUC) was used to compare the predictive power of the models. The sensitivity and accuracy of models also were obtained. In total, 59 parotids were assessed, and 13 models were developed. Our results showed three models with AUC of 0.89 as most predictive, namely ΔCT_2-1 + Dose (Sensitivity 0.99, Accuracy 0.94 & Specificity 0.86), CT₃ model (Sensitivity 0.96, Accuracy 0.94 & Specificity 0.86) and DVH (Sensitivity 0.93, Accuracy 0.89 & Specificity 0.84). These models were followed by Clinical (AUC 0.89, Sensitivity 0.81, Accuracy 0.97 & Specificity 0.89) and CT₂ & Dose (AUC 0.86, Sensitivity 0.97, Accuracy 0.87 & Specificity 0.82). The Dose model (developed by dosiomics features only) had AUC, Sensitivity, Specificity, and Accuracy of 0.72, 0.98, 0.33, and 0.79 respectively. Quantitative features extracted from diagnostic imaging during and after radiotherapy alone or in combination with dosiomics markers obtained from dose distribution images can be used for radiotherapy response modeling, opening up prospects for personalization of therapies toward improved therapeutic outcomes.

头颈癌（head and neck cancer, HN）患者放疗诱导口干症的剂量-效应建模是实现个性化治疗的极具前景的前沿方向。从诊断与治疗影像中提取特征（放射组学（radiomics）与剂量组学（dosiomics）特征）可用于数据驱动的效应建模。本研究旨在基于放射-剂量组学特征构建口干症预测模型。本研究使用了癌症影像档案（The Cancer Imaging Archive, TCIA）中31例头颈癌患者的临床数据。对所有患者，我们提取了腮腺CT放射组学特征，并采用套索回归（Lasso regression）进行特征选择与多变量建模。模型基于治疗前（CT₁）、治疗中（CT₂）、治疗后（CT₃）的特征以及差值特征（ΔCT₂₋₁、ΔCT₃₋₁、ΔCT₃₋₂）构建。我们还考虑了从腮腺剂量分布影像中提取的剂量组学特征（剂量模型），由此构建了放射-剂量组学联合模型（CT+剂量及ΔCT+剂量）。此外，本研究还构建了临床模型与剂量体积直方图（dose-volume histogram, DVH）模型。采用嵌套10折交叉验证评估患者是否发生口干症的预测分类性能，并以受试者工作特征曲线下面积（area under the receiver operating characteristic curve, AUC）比较各模型的预测能力，同时计算模型的灵敏度与准确率。本研究共评估了59个腮腺样本，构建了13个模型。结果显示，3个模型的AUC达到0.89，为最优预测模型，分别为ΔCT₂₋₁+剂量模型（灵敏度0.99，准确率0.94，特异度0.86）、CT₃模型（灵敏度0.96，准确率0.94，特异度0.86）以及DVH模型（灵敏度0.93，准确率0.89，特异度0.84）。紧随其后的为临床模型（AUC 0.89，灵敏度0.81，准确率0.97，特异度0.89）与CT₂+剂量模型（AUC 0.86，灵敏度0.97，准确率0.87，特异度0.82）。仅基于剂量组学特征构建的剂量模型的AUC、灵敏度、特异度与准确率分别为0.72、0.98、0.33与0.79。单独从放疗期间及放疗后诊断影像中提取的量化特征，或联合从剂量分布影像中获取的剂量组学标志物，可用于放疗效应建模，为实现个性化治疗以改善治疗结局开辟了新的前景。