Unbiased evaluation of predicted gamma passing rate by an event-mixing technique.

BACKGROUND: Predicting models of the gamma passing rate (GPR) have been studied to substitute the measurement-based gamma analysis. Since these studies used data from different radiotherapy systems comprising TPS, linear accelerator, and detector array, it has been difficult to compare the performances of the predicting models among institutions with different radiotherapy systems. PURPOSE: We aimed to develop unbiased scoring methods to evaluate the performance of the models predicting the GPR, by introducing both best and worst limits for the performance of the GPR prediction. METHODS: Two hundred head-and-neck VMAT plans were used to develop a framework. The GPRs were measured using the ArcCHECK device. The predicted GPR [p] was generated using a deep learning-based model [pDL ]. The predicting model was evaluated using four metrics: standard deviation (SD) [σ], Pearson's correlation coefficient (CC) [r], mean squared error (MSE) [s], and mean absolute error (MAE) [a]. The best limit [ σ m ${\sigma _m}$ , r m ${r_m}$ , s m ${s_m}$ , and a m ${a_m}$ ] was estimated by measuring the SD of measured GPR [m] by shifting the device along the longitudinal direction to measure different sampling points. Mimicked best and worst p's [pbest and pworst ] were generated from pDL . The worst limit was defined such that m and p have no correlation [CC ∼ 0]. The worst limit [σMix , rMix , sMix , and aMix ] was generated using the event-mixing (EM) technique originally introduced in high-energy physics experiments. The range of σ, r, s, and a was defined to be [ σ m , σ Mix ] $[ {{\sigma _m},{\sigma _{{\mathrm{Mix}}}}} ]$ , [ 0 , r m ] $[ {0,{r_m}} ]$ , [ s m , s Mix ] $[ {{s_m},{s_{{\mathrm{Mix}}}}} ]$ , and [ a m , a Mix ] $[ {{a_m},{a_{{\mathrm{Mix}}}}} ]$ . The achievement score (AS) independently based on σ, r, s, and a were calculated for pDL , pbest and pworst . The probability that p fails the gamma analysis (alert frequency; AF) was estimated as a function of σ d ${\sigma _d}$ values within the [ σ m ${\sigma _m}$ , σMix ] range for the 3%/2 mm data with a 95% criterion. RESULTS: SDs of the best limit were well reproduced by σ m = 0.531 100 - m ${\sigma _m} = \;0.531\sqrt {100 - m} $ . The EM technique successfully generated the ( m , p ) $( {m,p} )$ pairs with no correlation. The AS using four metrics showed good agreement. This agreement indicates successful definitions of both best and worst limits, consistent definitions of the AS, and successful generations of mixed events. The AF for the DL-based model with the 3%/2 mm tolerance was 31.5% and 63.0% with CL's 99% and 99.9%, respectively. CONCLUSION: We developed the AS to evaluate the predicting model of the GPR in an unbiased manner by excluding the effects of the precision of the radiotherapy system and the spreading of the GPR. The best and worst limits of the GPR prediction were successfully generated using the measured precision of the GPR and the EM technique, respectively. The AS and σ p ${\sigma _p}$ are expected to enable objective evaluation of the predicting model and setting exact achievement goal of precision for the predicted GPR.

A synthesized gamma distribution-based patient-specific VMAT QA using a generative adversarial network.

BACKGROUND: Artificial intelligence (AI)-based gamma passing rate (GPR) prediction has been proposed as a time-efficient virtual patient-specific QA method for the delivery of volumetric modulation arc therapy (VMAT). However, there is a limitation that the GPR value loses the locational information of dose accuracy. PURPOSE: The objective was to predict the failing points in the gamma distribution and the GPR using a synthesized gamma distribution of VMAT QA with a deep convolutional generative adversarial network (GAN). METHODS: The fluence maps of 270 VMAT beams for prostate cancer were measured using an electronic portal imaging device and analyzed using gamma evaluation with 3%/2-mm, 2%/1-mm, 1%/1-mm, and 1%/0.5-mm tolerances. The 270 gamma distributions were divided into two datasets: 240 training datasets for creating a model and 30 test datasets for evaluation. The image prediction network for the fluence maps calculated by the treatment planning system (TPS) to the gamma distributions was created using a GAN. The sensitivity, specificity, and accuracy of detecting failing points were evaluated using measured and synthesized gamma distributions. In addition, the difference between measured GPR (mGPR) and predicted GPR (pGPR) values calculated from the synthesized gamma distributions was evaluated. RESULTS: The root mean squared errors between mGPR and pGPR were 1.0%, 2.1%, 3.5%, and 3.6% for the 3%/2-mm, 2%/1-mm, 1%/1-mm, and 1%/0.5-mm tolerances, respectively. The accuracies for detecting failing points were 98.9%, 96.9%, 94.7%, and 93.7% for 3%/2-mm, 2%/1-mm, 1%/1-mm, and 1%/0.5-mm tolerances, respectively. The sensitivity and specificity were the highest for 1%/0.5-mm and 3%/2-mm tolerances, which were 82.7% and 99.6%, respectively. CONCLUSIONS: We developed a novel system using a GAN to generate a synthesized gamma distribution-based patient-specific VMAT QA. The system is promising from the point of view of quality assurance in radiotherapy because it shows high performance and can detect failing points.

MRI image synthesis for fluid-attenuated inversion recovery and diffusion-weighted images with deep learning.

This study aims to synthesize fluid-attenuated inversion recovery (FLAIR) and diffusion-weighted images (DWI) with a deep conditional adversarial network from T1- and T2-weighted magnetic resonance imaging (MRI) images. A total of 1980 images of 102 patients were split into two datasets: 1470 (68 patients) in a training set and 510 (34 patients) in a test set. The prediction framework was based on a convolutional neural network with a generator and discriminator. T1-weighted, T2-weighted, and composite images were used as inputs. The digital imaging and communications in medicine (DICOM) images were converted to 8-bit red-green-blue images. The red and blue channels of the composite images were assigned to 8-bit grayscale pixel values in T1-weighted images, and the green channel was assigned to those in T2-weighted images. The prediction FLAIR and DWI images were of the same objects as the inputs. For the results, the prediction model with composite MRI input images in the DWI image showed the smallest relative mean absolute error (rMAE) and largest mutual information (MI), and that in the FLAIR image showed the largest relative mean-square error (rMSE), relative root-mean-square error (rRMSE), and peak signal-to-noise ratio (PSNR). For the FLAIR image, the prediction model with the T2-weighted MRI input images generated more accurate synthesis results than that with the T1-weighted inputs. The proposed image synthesis framework can improve the versatility and quality of multi-contrast MRI without extra scans. The composite input MRI image contributes to synthesizing the multi-contrast MRI image efficiently.

Predictive gamma passing rate of 3D detector array-based volumetric modulated arc therapy quality assurance for prostate cancer via deep learning.

To predict the gamma passing rate (GPR) of the three-dimensional (3D) detector array-based volumetric modulated arc therapy (VMAT) quality assurance (QA) for prostate cancer using a convolutional neural network (CNN) with the 3D dose distribution. One hundred thirty-five VMAT plans for prostate cancer were selected: 110 plans were used for training and validation, and 25 plans were used for testing. Verification plans were measured using a helical 3D diode array (ArcCHECK). The dose distribution on the detector element plane of these verification plans was used as input data for the CNN model. The measured GPR (mGPR) values were used as the training data. The CNN model comprises eighteen layers and predicted GPR (pGPR) values. The mGPR and pGPR values were compared, and a cumulative frequency histogram of the prediction error was created to clarify the prediction error tendency. The correlation coefficients of pGPR and mGPR were 0.67, 0.69, 0.66, and 0.73 for 3%/3-mm, 3%/2-mm, 2%/3-mm, and 2%/2-mm gamma criteria, respectively. The respective mean±standard deviations of pGPR-mGPR were -0.87±2.18%, -0.65±2.93%, -0.44±2.53%, and -0.71±3.33%. The probabilities of false positive error cases (pGPR < mGPR) were 72%, 60%, 68%, and 56% for each gamma criterion. We developed a deep learning-based prediction model of the 3D detector array-based VMAT QA for prostate cancer, and evaluated the accuracy and tendency of prediction GPR. This model can provide a proactive estimation for the results of the patient-specific QA before the verification measurement.

[Improvement of Nonuniformity on Flatbed Scanner for Radiochromic Film Dosimetry Using Average Correction Factor with Multi-direction Scan Data].

In order to correct the lateral effect caused by the light source of the flatbed scanner in the Gafchromic film EBT3, the usefulness of the correction method using the average value of the correction coefficient considering the scan directions were evaluated. EBT3 was scanned from four directions to measure the optical density (OD) of the red, blue, and, red/blue components and the correction coefficient were calculated. For the correction coefficients, average values were calculated for the purpose of use, when the scan directions could not be aligned (average lateral effect correction). Correction accuracy was verified with the pass rate of gamma analysis (3 mm/3%, threshold 30%) of the dose distribution using the EBT3 film irradiated with the step pattern. OD of the red, blue, and, red/blue components in the scanning vertical direction tended to be higher in the center than in the peripheral portion. The pass rate of the step pattern was the red component's before correction, from 26.9 to 45.1% (before correction), from 84.1 to 96.7% (after correction), the red/blue component, from 37.6 to 48.4% (before correction) and from 84.4 to 96.7% (after correction). When using the correction coefficient using the average value, the pass rate was 89.8% for the red component and 94.7% for the red/blue component. The lateral effect correction improves the accuracy of the dose distribution verification, and the correction coefficient using the average value is useful when the scanning direction is different from that at the time of obtaining the dose concentration curve.

4D modeling in a gimbaled linear accelerator by using gold anchor markers.

PURPOSE: The purpose of this study was to verify whether the dynamic tumor tracking (DTT) feature of a Vero4DRT system performs with 10-mm-long and 0.28 mm diameter gold anchor markers. METHODS: Gold anchor markers with a length of 10 mm and a diameter of 0.28 mm were used. Gold anchor markers were injected with short and long types into bolus material. These markers were sandwiched by a Tough Water (TW) phantom in the bolus material. For the investigation of 4-dimensional (4D) modeling feasibility under various phantom thicknesses, the TW phantom was added at 2 cm intervals (in upper and lower each by 1 cm). A programmable respiratory motion table was used to simulate breathing-induced organ motion, with an amplitude of 30 mm and a breathing cycle of 3 s. X-ray imaging parameters of 80 kV and 125 kV (320 mA and 5 ms) were used. The least detection error of the fiducial marker was defined as the 4D-modeling limitation. RESULTS: The 4D modeling process was attempted using short and long marker types and its limitation with the short and long types was with phantom thicknesses of 6 and 10 cm at 80 kV and 125 kV, respectively. However, the loss in detectability of the gold anchor because of 4D-modeling errors was found to be approximately 6% (2/31) with a phantom thickness of 2 cm under 125 kV. 4D-modeling could be performed except under the described conditions. CONCLUSIONS: This work showed that a 10-mm-long gold anchor marker in short and long types can be used with DTT for short water equivalent path length site, such as lung cancer patients, in the Vero4DRT system.

Proposed patient motion monitoring system using feature point tracking with a web camera.

Patient motion monitoring systems play an important role in providing accurate treatment dose delivery. We propose a system that utilizes a web camera (frame rate up to 30 fps, maximum resolution of 640 × 480 pixels) and an in-house image processing software (developed using Microsoft Visual C++ and OpenCV). This system is simple to use and convenient to set up. The pyramidal Lucas-Kanade method was applied to calculate motions for each feature point by analysing two consecutive frames. The image processing software employs a color scheme where the defined feature points are blue under stable (no movement) conditions and turn red along with a warning message and an audio signal (beeping alarm) for large patient movements. The initial position of the marker was used by the program to determine the marker positions in all the frames. The software generates a text file that contains the calculated motion for each frame and saves it as a compressed audio video interleave (AVI) file. We proposed a patient motion monitoring system using a web camera, which is simple and convenient to set up, to increase the safety of treatment delivery.

[Investigation of the columnar carbon-scatterer length for X-ray spectral measurement on 320-slice computed tomography].

A short length scatterer is adopted to measure the X-ray spectrum of computed tomography (CT) equipment with a wide irradiation field in the body axis direction. The purpose of this study is to compare X-ray spectra measured using different length scatterers and determine the most appropriate length for the scatterer. 320-slice CT equipment (Aquilion ONE) was used in this study. Circular carbonrods (3 cm diameter) with five different lengths (1-16 cm) were used as scatterers. The effect of the beam hardening phenomenon from different length carbon rods was evaluated according to the effective energy. The measurement accuracy for photon information was also evaluated based on the photon count corresponding to the characteristic X-ray. As a result, the beam hardening effect was scarcely observed when the 1 cm long scatterer was used, and the number of the photons measured for the characteristic X-ray was the most. Therefore, it was concluded that the 1 cm long circular carbon rod scatterer was the most suitable.

[Production of a leaf electroscope having separators and proposal of an experiment using the diagnostic X-ray equipment].

In order to use the practical training for beginners by means of a diagnostic X-ray, a leaf electroscope (which has a function to explain the ionization) was newly produced. The X-ray was introduced to the air in the electroscope having the electric charged leaf (the leaf was open at this time). The air irradiated by the X-ray was ionized, and then the produced ions or electrons were combined with charges on the leaf. As a result, the leaf was closed. In this way, experimenters can know the production and/or movement of charges by observing the conditions of the leaf. For the developed leaf electroscope, we added separators to divide the inner space into two regions; one is the irradiation area and the other is the space including the leaf. The separators have through-holes and/or a metallic mesh in order to create various conditions. In this paper, we described that different experimental results based on uses of the different separators were reflected in the ionization of the irradiated air and in the interaction of the charged particles. We summarized that the practical training by means of the developed leaf electroscope was valuable to educate beginners.