Click here to


Are you sure ?

Yes, do it No, cancel

An Outcome-Based Treatment Planning Strategy to Improve Xerostomia Symptom in Head and Neck Cancer Patients

Y Guo*, P Lakshminarayanan , P Han , K Sheikh , Z Cheng , S Siddiqui , I Shpitser , R Taylor , H Quon , T McNutt , Johns Hopkins University, Severna Park, MD


(Thursday, 7/18/2019) 7:30 AM - 9:30 AM

Room: Stars at Night Ballroom 2-3

Purpose: To develop an outcome-based planning strategy for optimizing the spatial dose pattern in parotid glands (PGs), submandibular glands (SMGs), and oral cavity (OC) and improving the probability of xerostomia injury(grade≥2 within 3-months) and recovery(reduced to grade<2 by 18-months).

Methods: 198 dose features (D10-D90) of 9 sub-volumes (3 layers: superior, middle, and inferior; 3 portions in each layer: medial, anterior, and posterior) from PGs, and 3 sub-volumes (superior, middle, and inferior) from SMGs and OCs were extracted by a feature generation pipeline. The probability of xerostomia injury and recovery were computed from a previously developed ridge logistic regression model. Partial derivatives were calculated and sorted in descending order to compute the weights of the dose features. We optimized two types of treatment plans where one plan reduced risk of injury (injury-weighted) and the other maximized the chance of recovery (recovery-weighted). After adding objectives for the sub-volume dose features to existing physical dose-volume based objectives, IMRT optimization was applied in Pinnacle. Outcome-based plans were compared to the clinical plans for comparable target coverage and to ensure dose to the important region of interests met clinical constraints. For outcome-based plan evaluation, prediction of probability of injury and recovery after final optimization was compared to clinical plan. The outcome-based plan quality and the predicted clinical outcomes were reviewed by two independent clinicians.

Results: The predicted probability of injury and recovery for 4 cases were improved in both outcome-based plans. Both injury-weighted and recovery-weighted plans had reduced dose to low dose areas, injury-weighted were lower dose in the higher dose regions as well.

Conclusion: This work indicated the feasibility of outcome-based planning optimization algorithm for reducing risk of injury and improving chance of recovery from xerostomia. This was done by reducing dose to the salivary glands and oral cavity while maintaining target coverage.

Funding Support, Disclosures, and Conflict of Interest: This study is funded by ROI institute and Johns Hopkins Radiation Oncology Discovery Award.


Not Applicable / None Entered.


Not Applicable / None Entered.

Contact Email