Personalized automation of treatment planning in head-neck cancer: A step forward for quality in radiation therapy?. (February 2021)

• Record Type: Journal Article
• Authors: Cilla, Savino; Deodato, Francesco; Romano, Carmela; Ianiro, Anna; Macchia, Gabriella; Re, Alessia; Buwenge, Milly; Boldrini, Luca; Indovina, Luca; Valentini, Vincenzo; Morganti, Alessio G.
• Is Part Of: Physica medica. Volume 82(2021)
• Page Start: 7
• Page End: 16
• Publication Date: 2021-02
• Subjects: Automation -- Artificial intelligence -- VMAT -- SIB -- Quality; Medical physics -- Periodicals; Biophysics -- Periodicals; Biophysics -- Periodicals; Imagerie médicale -- Périodiques; Radiothérapie -- Périodiques; Rayons X -- Sécurité -- Mesures -- Périodiques; Physique -- Périodiques; Médecine -- Périodiques; 610.153
• DOI: 10.1016/j.ejmp.2020.12.015
• Languages: English
• ISSNs: 1120-1797

Abstract

Highlights: Treatment planning for H&N tumors is challenging. Artificial intelligence has the potential to improve plan quality. Personalized Planning, a new automated optimization engine, is presented. Automated plans resulted in significant dosimetric sparing of OARs. Personalized Planning resulted in clinically favorable H&N cancer plans. Abstract: Purpose: To perform a comprehensive dosimetric and clinical evaluation of the new Pinnacle Personalized automated planning system for complex head-and-neck treatments. Methods: Fifteen consecutive head-neck patients were enrolled. Radiotherapy was prescribed using VMAT with simultaneous integrated boost strategy. Personalized planning integrates the Feasibility engine able to supply an "a priori" DVH prediction of the achievability of planning goals. Comparison between clinically accepted manually-generated (MP) and automated (AP) plans was performed using dose-volume histograms and a blinded clinical evaluation by two radiation oncologists. Planning time between MP and AP was compared. Dose accuracy was validated using the PTW Octavius-4D phantom together with the 1500 2D-array. Results: For similar targets coverage, AP plans reported less irradiation of healthy tissue, with significant dose reduction for spinal cord, brainstem and parotids. On average, the mean dose to parotids and maximal doses to spinal cord and brainstem were reduced by 13–15% (p < 0.001), 9% (p < 0.001) and 16% (p < 0.001), respectively. The integral dose was reduced by 16% (p < 0.001). The dose conformity for the three PTVs was significantly higher with AP plans (p < 0.001). The two oncologists chose AP plans in more than 80% of cases. Overall planning times were reduced to <30 min for automated optimization. All AP plans passed the 3%/2 mm γ-analysis by more than 95%. Conclusion: Complex head-neck plans created using Personalized automated engine provided an overall increase of plan quality, in terms of dose conformity and sparing of normal tissues. The Feasibility module allowed OARs dose sparing well beyond the clinical objectives.