Using prediction models to evaluate magnetic resonance image guided radiation therapy plans

M Allan Thomas; Joshua Olick-Gibson; Yabo Fu; Parag J Parikh; Olga Green; Deshan Yang

doi:10.1016/j.phro.2020.10.002

Using prediction models to evaluate magnetic resonance image guided radiation therapy plans

Phys Imaging Radiat Oncol. 2020 Oct 28:16:99-102. doi: 10.1016/j.phro.2020.10.002. eCollection 2020 Oct.

Authors

M Allan Thomas^{1

2}, Joshua Olick-Gibson¹, Yabo Fu^{1

3}, Parag J Parikh⁴, Olga Green¹, Deshan Yang¹

Affiliations

¹ Department of Radiation Oncology, Washington University in St. Louis, St. Louis, MO 63108, United States.
² Department of Imaging Physics, UT MD Anderson Cancer Center, Houston, TX 77030, United States.
³ Department of Radiation Oncology, Emory University, Atlanta, GA 30332, United States.
⁴ Department of Radiation Oncology, Henry Ford Cancer Institute, Detroit, MI 48202, United States.

Abstract

Comprehensive analysis of daily, online adaptive plan quality and safety in magnetic resonance imaging (MRI) guided radiation therapy is critical to its widespread use. Artificial neural network models developed with offline plans created after simulation were used to analyze and compare online plans that were adapted and reoptimized in real time prior to treatment. Roughly one third of ⁶⁰Co adapted plans were of inferior quality relative to fully optimized, offline plans, but MRI-linac adapted plans were essentially equivalent to offline plans. The models also enabled clear justification that MRI-linac plans are superior to ⁶⁰Co in an overwhelming majority of cases.

Keywords: Adaptive radiation therapy; Magnetic resonance image guidance; Neural network; Treatment plan quality.

Abstract

Grants and funding