Search

PURPOSE The purpose of this study is to evaluate the prediction and classification performances of the gamma passing rate (GPR) for different machine learning models and to select the best model for achieving machine learning-based patient-specific quality assurance (PSQA). METHODS The measurement verification of 356 head-and-neck volumetric modulated arc therapy plans was performed using a diode array phantom (Delta4 Phantom), and GPR values at 2%/2 mm with global normalization and 3%/2 mm with local normalization were calculated. Machine learning models, including ridge regression (RIDGE), random forest (RF), support vector regression (SVR), and stacked generalization (STACKING), were used to predict the GPR. Each machine learning model was trained using 260 plans, and the prediction accuracy was evaluated using the remaining 96 plans. The prediction error between the measured and predicted GPR was evaluated. For the classification evaluation, the lower control limit for the measured GPR and lower control limit for predicted GPR (LCLp ) was defined to identify whether the GPR values represent a "pass" or a "fail." LCLp values with 99% and 99.9% confidence levels were calculated as the upper prediction limits for the GPR estimated from the linear regression between the measured and predicted GPR. RESULTS There was an overestimation trend of the low measured GPR. The maximum prediction errors for RIDGE, RF, SVR, and STACKING were 3.2%, 2.9%, 2.3%, and 2.2% at global 2%/2 mm and 6.3%, 6.6%, 6.1%, and 5.5% at the local 3%/2 mm, respectively. In the global 2%/2 mm, the sensitivity was 100% for all the machine learning models except RIDGE when using 99% LCLp . The specificity was 76.1% for RIDGE, RF, and SVR and 66.3% for STACKING, however, the specificity decreased dramatically when 99.9% LCLp was used. In the local 3%/2 mm, however, only STACKING showed 100% sensitivity when using 99% LCLp . The decrease in the specificity using 99.9% LCLp was smaller than that in the global 2%/2mm, and the specificity for RIDGE, RF, SVR, and STACKING was 61.3%, 61.3%, 72.0%, and 66.8%, respectively. CONCLUSIONS STACKING had better prediction accuracy for low GPR values than other machine learning models. Applying LCLp to a regression model enabled the consistent evaluation of quantitative and qualitative GPR predictions. Adjusting the confidence level of the LCLp helped improve the balance between the sensitivity and specificity. We suggest that STACKING can assist the safe and efficient operation of PSQA. This article is protected by copyright. All rights reserved.

Purpose We analyzed interfractional robustness of scanning carbon ion radiotherapy (CIRT) for prostate cancer based on the dose distribution using daily in‐room computed tomography (CT) images. Materials and Methods We analyzed 11 consecutive patients treated with scanning CIRT for localized prostate cancer in our hospital between December 2015 and January 2016. In‐room CT images were taken under treatment conditions in every treatment session. The dose distribution on each in‐room CT image was recalculated, while retaining the pencil beam arrangement of the initial treatment plan. Then, the dose–volume histogram (DVH) parameters including the percentage of the clinical target volume (CTV) with 95% and 90% of the prescribed dose area (V95% of CTV, V90% of CTV) and V80% of rectum were calculated. The acceptance criteria for the CTV and rectum were set at V95% of CTV ≥95%, V90% of CTV ≥98%, and V80% of rectum < 10 ml. Results V95% of CTV, V90% of CTV, and V80% of rectum for the reproduced plans were 98.8 ± 3.49%, 99.5 ± 2.15%, and 4.39 ± 3.96 ml, respectively. Acceptance of V95% of CTV, V90% of CTV, and V80% of rectum was obtained in 123 (94%), 125 (95%) and 117 sessions (89%), respectively. Acceptance of the mean dose of V95% of CTV, V90% of CTV, and V80% of rectum for each patient was obtained in 10 (91%), 10 (91%), and 11 patients (100%), respectively. Conclusions We demonstrated acceptable interfractional robustness based on the dose distribution in scanning CIRT for prostate cancer.

To estimate the physical dose at the center of spread-out Bragg peaks (SOBP) for various conditions of the irradiation system, a semiempirical approach was applied. The dose at the center of the SOBP depends on the field size because of large-angle scattering particles in the water phantom. For a small field of 5x5 cm{sup 2}, the dose was reduced to 99.2%, 97.5%, and 96.5% of the dose used for the open field in the case of 290, 350, and 400 MeV/n carbon beams, respectively. Based on the three-Gaussian form of the lateral dose distributions of the carbon pencil beam, which has previously been shown to be effective for describing scattered carbon beams, we reconstructed the dose distributions of the SOBP beam. The reconstructed lateral dose distribution reproduced the measured lateral dose distributions very well. The field-size dependencies calculated using the reconstructed lateral dose distribution of the therapeutic carbon beam agreed with the measured dose dependency very well. The reconstructed beam was also used for irregularly shaped fields. The resultant dose distribution agreed with the measured dose distribution. The reconstructed beams were found to be applicable to the treatment-planning system.

In carbon therapy, doses at center of spread-out Bragg peaks depend on field size. For a small field of 5 × 5 cm 2 , the central dose reduces to 96% of the central dose for the open field in case of 400 MeV ∕ n carbon beam. Assuming the broad beam injected to the water phantom is made up of many pencil beams, the transverse dose distribution can be reconstructed by summing the dose distribution of the pencil beams. We estimated dose profiles of this pencil beam through measurements of dose distributions of broad uniform beams blocked half of the irradiation fields. The dose at a distance of a few cm from the edge of the irradiation field reaches up to a few percent of the central dose. From radiation quality measurements of this penumbra, the large-angle scattered particles were found to be secondary fragments which have lower LET than primary carbon beams. Carbon ions break up in beam modifying devices or in water phantom through nuclear interaction with target nuclei. The angular distributions of these fragmented nuclei are much broader than those of primary carbon particles. The transverse dose distribution of the pencil beam can be approximated by a function of the three-Gaussian form. For a simplest case of mono-energetic beam, contributions of the Gaussian components which have large mean deviations become larger as the depth in the water phantom increases.

Purpose: The purpose of this study was to obtain a set of correction factors of the radiophotoluminescent glass dosimeter (RGD) output for field size changes and wedge insertions. Methods: Several linear accelerators were used for irradiation of the RGDs. The field sizes were changed from 5 × 5 cm to 25 × 25 cm for 4, 6, 10, and 15 MV x-ray beams. The wedge angles were 15°, 30°, 45°, and 60°. In addition to physical wedge irradiation, nonphysical (dynamic/virtual) wedge irradiations were performed. Results: The obtained data were fitted with a single line for each energy, and correction factors were determined. Compared with ionization chamber outputs, the RGD outputs gradually increased with increasing field size, because of the higher RGD response to scattered low-energy photons. The output increase was about 1% per 10 cm increase in field size, with a slight difference dependent on the beam energy. For both physical and nonphysical wedged beam irradiation, there were no systematic trends in the RGD outputs, such as monotonic increase or decrease depending on the wedge angle change if the authors consider the uncertainty, which is approximately 0.6% for each set of measured points. Therefore, no correction factor was needed for all inserted wedges. Based on this work, postal dose audits using RGDs for the nonreference condition were initiated in 2010. The postal dose audit results between 2010 and 2012 were analyzed. The mean difference between the measured and stated doses was within 0.5% for all fields with field sizes between 5 × 5 cm and 25 × 25 cm and with wedge angles from 15° to 60°. The standard deviations (SDs) of the difference distribution were within the estimated uncertainty (1SD) except for the 25 × 25 cm field size data, which were not reliable because of poor statistics (n = 16). Conclusions: A set of RGD output correction factors was determined for field size changes and wedge insertions. The results obtained from recent postal dose audits were analyzed, and the mean differences between the measured and stated doses were within 0.5% for every field size and wedge angle. The SDs of the distribution were within the estimated uncertainty, except for one condition that was not reliable because of poor statistics.