Purpose: Despite being the standard metric in patient-specific quality assurance (QA) for intensitymodulated radiotherapy (IMRT), gamma analysis has two shortcomings: (a) it lacks sensitivity to small but clinically relevant errors (b) it does not provide efficient means to classify the error sources. The purpose of this work is to propose a dual neural network method to achieve simultaneous error detection and classification in patient-specific IMRT QA. Methods: For a pair of dose distributions, we extracted the dose difference histogram (DDH) for the low dose gradient region and two signed distance-to-agreement (sDTA) maps (one in x direction and one in y direction) for the high dose gradient region. An artificial neural network (ANN) and a convolutional neural network (CNN) were designed to analyze the DDH and the two sDTA maps, respectively. The ANN was trained to detect and classify six classes of dosimetric errors: incorrect multileaf collimator (MLC) transmission (AE1%) and four types of monitor unit (MU) scaling errors (AE1% and AE2%). The CNN was trained to detect and classify seven classes of spatial errors: incorrect effective source size, 1 mm MLC leaf bank overtravel or undertravel, 2 mm single MLC leaf overtravel or undertravel, and device misalignment errors (1 mm in x-or y direction). An in-house planar dose calculation software was used to simulate measurements with errors and noise introduced. Both networks were trained and validated with 13 IMRT plans (totaling 88 fields). A fivefold cross-validation technique was used to evaluate their accuracy. Results: Distinct features were found in the DDH and the sDTA maps. The ANN perfectly identified all four types of MU scaling errors and the specific accuracies for the classes of no error, MLC transmission increase, MLC transmission decrease were 98.9%, 96.6%, and 94.3%, respectively. For the CNN, the largest confusion occurred between the 1-mm-MLC bank overtravel class and the 1-mmdevice alignment error in x-direction class, which brought the specific accuracies down to 90.9% and 92.0%, respectively. The specific accuracy for the 2-mm-single MLC leaf undertravel class was 93.2% as it misclassified 5.7% of the class as being error free (false negative). Otherwise, the specific accuracy was above 95%. The overall accuracies across the fivefold were 98.3 AE 0.7% and 95.6% AE 1.5% for the ANN and the CNN, respectively. Conclusions: Both the DDH and the sDTA maps are suitable features for error classification in IMRT QA. The proposed dual neural network method achieved simultaneous error detection and classification with excellent accuracy. It could be used in complement with the gamma analysis to potentially shift the IMRT QA paradigm from passive pass/fail analysis to active error detection and root cause identification.

A sliding-window (SW) methodology for VMAT dose calculation was developed. For any two adjacent VMAT control points (CPs) n and n+1, the dose distribution was approximated by a 2-CP SW IMRT beam with the starting MLC positions at CP n and ending MLC positions at CP n+1, with the gantry angle fixed in the middle of the two VMAT CPs. Therefore, for any VMAT beam with N CPs, the dose is calculated with N-1 SW beams. VMAT plans were generated for ten patients in Pinnacle using 4° gantry spacing. For each patient, the VMAT plan was converted to a SW IMRT plan and dose was re-calculated. Another VMAT plan, with 1° gantry spacing, was created by interpolating the original VMAT beam. The original plans were delivered on an Elekta Versa HD and measured with Mapcheck2 using an in-house developed subarc method. For both the isodose distribution and DVH, there were significant differences between the original VMAT plan and either the SW or the interpolated plan. However, they were indistinguishable between the SW and interpolated plans. The average passing rate between the original VMAT plan and measurements was 84%. For both the interpolated and SW plans, the average passing rate was 96%. We conclude that the proposed SW approach improves VMAT dose calculation accuracy without increase in dose calculation time.

No abstract

No abstract