Virtual patient‐specific QA with DVH‐based metrics

Abstract

We demonstrate a virtual pretreatment patient‐specific QA (PSQA) procedure that is capable of quantifying dosimetric effect on patient anatomy for both intensity modulated radiotherapy (IMRT) and volumetric modulated arc therapy (VMAT). A machine learning prediction model was developed to use linear accelerator parameters derived from the DICOM‐RT plan to predict delivery discrepancies at treatment delivery (defined as the difference between trajectory log file and DICOM‐RT) and was coupled with an independent Monte Carlo dose calculation algorithm for dosimetric analysis. Machine learning models for IMRT and VMAT were trained and validated using 120 IMRT and 206 VMAT fields of prior patients, with 80% assigned for iterative training and testing, and 20% for post‐training validation. Various prediction models were trained and validated, with the final models selected for clinical implementation being a boosted tree and bagged tree for IMRT and VMAT, respectively. After validation, these models were then applied clinically to predict the machine parameters at treatment delivery for 7 IMRT plans from various sites (61 fields) and 10 VMAT multi‐target intracranial radiosurgery plans (35 arcs) and compared to the dosimetric effect calculated directly from trajectory log files. Dose indices tracked for targets and organs at risk included dose received by 99%, 95%, and 1% of the volume, mean dose, percent of volume receiving 25%–100% of the prescription dose. The average coefficient of determination (r2) when comparing intra‐field predicted and actual delivery error was 0.987 ± 0.012 for IMRT and 0.895 ± 0.095 for VMAT, whereas r2 when comparing inter‐field predicted versus actual delivery error was 0.982 for IMRT and 0.989 for VMAT. Regarding dosimetric analysis, r2 when comparing predicted versus actual dosimetric changes for all dose indices was 0.966 for IMRT and 0.907 for VMAT. Prediction models can be used to anticipate the dosimetric effect calculated from trajectory files and have potential as a “delivery‐free” pretreatment analysis to enhance PSQA.

A hybrid method to improve efficiency of patient specific SRS and SBRT QA using 3D secondary dose verification

“…Lay et al developed a ML model to predict the trajectory log errors of a plan delivery, from which a DICOM RT plan of the predicted delivery would be generated and used by a monte carlo dose algorithm to calculate the dose and compute DVH agreement. 49 Wall et al presented a virtual QA technique that combines independent secondary dose calculation by Mobius3D (Varian) and a ML model to predict the agreement of a point dose ionization chamber measurement,where a 1% tolerance in the predicted agreement was used to determine if a measurement should be performed. 50 Their use of a computational method to determine whether a measurement should be acquired is similar to the hybrid technique presented in the current study.…”

“…Lay et al. developed a ML model to predict the trajectory log errors of a plan delivery, from which a DICOM RT plan of the predicted delivery would be generated and used by a monte carlo dose algorithm to calculate the dose and compute DVH agreement 49 . Wall et al.…”

Clinical Validation of the COMPASS System for Two Matched Elekta Versa HD Linear Accelerators in Neuroblastoma

“…COMPASS is 3D dosimetry QA system (8)(9)(10)(11)(12), which consists of 3D anatomy-based dose verification software. It works in conjunction with MatriXX Evolution (serial number 25731) (IBA Dosimetry, Schwarzenbruck, Germany) and with gantry angle sensor.…”

“…That's why patient specific QA measurements are recommended by both American Association of Physicists in Medicine (AAPM) Task Group (TG) 119 and TG 218 to make sure that the treatments are provided as planned [4,5] . Both VMAT and IMRT are frequent treatment modalities with highly conformal dose distributions [6][7][8] .…”

A structured FMEA approach to optimizing combinations of plan‐specific quality assurance techniques for IMRT and VMAT QA

“…7 Furthermore, the standard of care PSQA process was developed without accounting for important new developments which include: disruptions to the PSQA process required to accommodate emerging online adaptive planning techniques, 11 daily machine performance checks provided by linear accelerator vendors, 12 development of automated plan checks to enhance PSQA (such as ClearCheck by Radformation, New York, NY), and development of artificial intelligence prediction models for PSQA. 13,14 With these innovations, the ability to fully re-assess the role of each of the various checks in the PSQA process is warranted.…”