Predicting acute radiation induced xerostomia in head and neck Cancer using MR and CT Radiomics of parotid and submandibular glands

Abstract

Purpose To analyze baseline CT/MR-based image features of salivary glands to predict radiation-induced xerostomia 3-months after head-and-neck cancer (HNC) radiotherapy. Methods A retrospective analysis was performed on 266 HNC patients who were treated using radiotherapy at our institution between 2009 and 2018. CT and T1 post-contrast MR images along with NCI-CTCAE xerostomia grade (3-month follow-up) were prospectively collected at our institution. CT and MR images were registered on which parotid/submandibular glands were contoured. Image features were extracted for ipsilateral/contralateral parotid and submandibular glands relative to the location of the primary tumor. Dose-volume-histogram (DVH) parameters were also acquired. Features were pre-selected based on Spearman correlation before modelling by examining the correlation with xerostomia ( p < 0.05). A shrinkage regression analysis of the pre-selected features was performed using LASSO. The internal validity of the variable selection was estimated by repeating the entire variable selection procedure using a leave-one-out-cross-validation. The most frequently selected variables were considered in the final model. A generalized linear regression with repeated ten-fold cross-validation was developed to predict radiation-induced xerostomia at 3-months after radiotherapy. This model was tested in an independent dataset ( n = 50) of patients who were treated at the same institution in 2017–2018. We compared the prediction performances under eight conditions (DVH-only, CT-only, MR-only, CT + MR, DVH + CT, DVH + CT + MR, Clinical+CT + MR, and Clinical+DVH + CT + MR) using the area under the receiver operating characteristic curve (ROC-AUC). Results Among extracted features, 7 CT, 5 MR, and 2 DVH features were selected. The internal cohort ( n = 216) ROC-AUC values for DVH, CT, MR, and Clinical+DVH + CT + MR features were 0.73 ± 0.01, 0.69 ± 0.01, 0.70 ± 0.01, and 0.79 ± 0.01, respectively. The validation cohort ( n = 50) ROC-AUC values for DVH, CT, MR, and Clinical+DVH + CT + MR features were 0.63, 0.57, 0.66, and 0.68, respectively. The DVH-ROC was not significantly different than the CT-ROC ( p = 0.8) or MR-ROC ( p = 0.4). However, the CT + MR-ROC was significantly different than the CT-ROC ( p = 0.03), but not the Clinical+DVH + CT + MR model ( p = 0.5). Conclusion Our results suggest that baseline CT and MR image features may reflect baseline salivary gland function and potential risk for radiation injury. The integration of baseline image features into prediction models has the potential to improve xerostomia risk stratification with the ultimate goal of truly personalized HNC radiotherapy. Electronic supplementary material ...

Application of Radiomics for the Prediction of Radiation-Induced Toxicity in the IMRT Era: Current State-of-the-Art

“…The authors concluded that the rate of CBCT-measured parotid gland image feature changes improved NTCP modeling over dose alone for late xerostomia prediction (AUC 0.77). In the context of late xerostomia prediction, baseline evaluation of changes in magnetic resonance (MR) and 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET-CT)-based parotid gland features was also shown to be a promising field of application (39)(40)(41)(42)(43). In particular, parotid glands with low metabolic activity and a low fat-to-functional parenchymal ratio were matched by more heterogeneous intensity and texture imaging features: overall, these hypothesisgenerating studies showed that pre-treatment radiomics-based prediction outperformed conventional NTCP models.…”

Radiomics Nomogram for Prediction of Peritoneal Metastasis in Patients With Gastric Cancer

“…In order to predict the PM status of patients with GC, we used the least absolute shrinkage and selection operator (LASSO) logistic regression model to select the optimal radiomics features from the primary texture features, and then, the development of the radiomics score (Rad-score) was constructed in the training cohort (21). For further detecting and addressing the collinearity among features, scatterplot correlation matrix with Person correlation coefficient was applied to investigate the interrelationship among the primary selected features and PM status, and if features had a correlation coefficient that was higher than 0.80 between each other, then the one with the highest collinearity was excluded from the analysis (22)(23)(24). In this study, we used the R software (version 3.5.3) with the "glmnet" package to perform the LASSO regression (25,26).…”

A longitudinal study on parotid and submandibular gland changes assessed by magnetic resonance imaging and ultrasonography in post-radiotherapy nasopharyngeal cancer patients

“…Examples of these include parotid gland fat-related MRI biomarkers, 38 dosiomic and demographic features, 39 F-FDG positron emission tomography image biomarkers 40 and CTand MR radiomics. 41 Such technology will also facilitate the prompt management of xerostomia in patients after radiotherapy.…”