Normal Tissue Radiomic Feature Kinetics in Oropharygeal Cancers Treated with Image-Guided Radiation Therapy: Assessment of Parotid Glands Textural Changes on Daily Non-contrast CT


Authors: Elhalawani, H., Mohamed, A., Volpe, V., Yang, P., Campbell, S., Granberry, R., Ger, R., Fave, X., Zhang, L., Marai, GE, Vock, DM, Canahuate, GM, Macking, D., Court, L., Gunn, GB, Rao, A., Fuller, CD

Publication: RSNA 2017, Scientific Reports

Parotid gland irradiation is a major risk factor for xerostomia in patients undergoing RT for head and neck cancers. We hypothesize that texture analysis allows for quantization of changes in parotid gland structure. 28 predominantly male patients diagnosed with locally advanced OPC who received concurrent chemoradiation constituted our cohort. The corresponding AUCs and CIs for predictive models suggest that the functional approach yields a superior ROC compared to using either the baseline radiomics feature or using the delta ratio between the mid and initial time points. Textural kinetic trajectories from consequential intra-treatment CT scans can predict for subsequent early and late radiation-induced toxicities.

Support:
National Institutes of Health:
NCI-R01-CA214825, “SMART-ACT: Spatial Methodologic Approaches for Risk Assessment and Therapeutic Adaptation in Cancer Treatment”
NCI-R01CA225190, “QuBBD: Precision E –Radiomics for Dynamic Big Head & Neck Cancer Data”

Date: November 26, 2017 - December 1, 2017

Document: View PDF
Actual Martingale residual by predicted value from random forest plot of time-to-local failure for the three sets based on the radiomic signature.

Related Entries

Directory:

Research:

Related Categories