Error detection using a multi-channel hybrid network with a low-resolution detector in patient-specific quality assurance.

This study aimed to develop a hybrid multi-channel network to detect multileaf collimator (MLC) positional errors using dose difference (DD) maps and gamma maps generated from low-resolution detectors in patient-specific quality assurance (QA) for Intensity Modulated Radiation Therapy (IMRT). A total of 68 plans with 358 beams of IMRT were included in this study. The MLC leaf positions of all control points in the original IMRT plans were modified to simulate four types of errors: shift error, opening error, closing error, and random error. These modified plans were imported into the treatment planning system (TPS) to calculate the predicted dose, while the PTW seven29 phantom was utilized to obtain the measured dose distributions. Based on the measured and predicted dose, DD maps and gamma maps, both with and without errors, were generated, resulting in a dataset with 3222 samples. The network's performance was evaluated using various metrics, including accuracy, sensitivity, specificity, precision, F1-score, ROC curves, and normalized confusion matrix. Besides, other baseline methods, such as single-channel hybrid network, ResNet-18, and Swin-Transformer, were also evaluated as a comparison. The experimental results showed that the multi-channel hybrid network outperformed other methods, demonstrating higher average precision, accuracy, sensitivity, specificity, and F1-scores, with values of 0.87, 0.89, 0.85, 0.97, and 0.85, respectively. The multi-channel hybrid network also achieved higher AUC values in the random errors (0.964) and the error-free (0.946) categories. Although the average accuracy of the multi-channel hybrid network was only marginally better than that of ResNet-18 and Swin Transformer, it significantly outperformed them regarding precision in the error-free category. The proposed multi-channel hybrid network exhibits a high level of accuracy in identifying MLC errors using low-resolution detectors. The method offers an effective and reliable solution for promoting quality and safety of IMRT QA.

Yan B ，Shi J ，Xue X ，Peng H ，Wu A ，Wang X ，Ma C ... -  《Journal of Applied Clinical Medical Physics》

Error detection model developed using a multi-task convolutional neural network in patient-specific quality assurance for volumetric-modulated arc therapy.

In patient-specific quality assurance (QA) for static beam intensity-modulated radiation therapy (IMRT), machine-learning-based dose analysis methods have been developed to identify the cause of an error as an alternative to gamma analysis. Although these new methods have revealed that the cause of the error can be identified by analyzing the dose distribution obtained from the two-dimensional detector, they have not been extended to the analysis of volumetric-modulated arc therapy (VMAT) QA. In this study, we propose a deep learning approach to detect various types of errors in patient-specific VMAT QA. A total of 161 beams from 104 prostate VMAT plans were analyzed. All beams were measured using a cylindrical detector (Delta4; ScandiDos, Uppsala, Sweden), and predicted dose distributions in a cylindrical phantom were calculated using a treatment planning system (TPS). In addition to the error-free plan, we simulated 12 types of errors: two types of multileaf collimator positional errors (systematic or random leaf offset of 2 mm), two types of monitor unit (MU) scaling errors (±3%), two types of gantry rotation errors (±2° in clockwise and counterclockwise direction), and six types of phantom setup errors (±1 mm in lateral, longitudinal, and vertical directions). The error-introduced predicted dose distributions were created by editing the calculated dose distributions using a TPS with in-house software. Those 13 types of dose difference maps, consisting of an error-free map and 12 error maps, were created from the measured and predicted dose distributions and were used to train the convolutional neural network (CNN) model. Our model was a multi-task model that individually detected each of the 12 types of errors. Two datasets, Test sets 1 and 2, were prepared to evaluate the performance of the model. Test set 1 consisted of 13 types of dose maps used for training, whereas Test set 2 included the dose maps with 25 types of errors in addition to the error-free dose map. The dose map, which introduced 25 types of errors, was generated by combining two of the 12 types of simulated errors. For comparison with the performance of our model, gamma analysis was performed for Test sets 1 and 2 with the criteria set to 3%/2 mm and 2%/1 mm (dose difference/distance to agreement). For Test set 1, the overall accuracy of our CNN model, gamma analysis with the criteria set to 3%/2 mm, and gamma analysis with the criteria set to 2%/1 mm was 0.92, 0.19, and 0.81, respectively. Similarly, for Test set 2, the overall accuracy was 0.44, 0.42, and 0.95, respectively. Our model outperformed gamma analysis in the classification of dose maps containing a single type error, and the performance of our model was inferior in the classification of dose maps containing compound errors. A multi-task CNN model for detecting errors in patient-specific VMAT QA using a cylindrical measuring device was constructed, and its performance was evaluated. Our results demonstrate that our model was effective in identifying the error type in the dose map for VMAT QA.

Kimura Y ，Kadoya N ，Oku Y ，Kajikawa T ，Tomori S ，Jingu K ... -  《-》

Comparison of MLC error sensitivity of various commercial devices for VMAT pre-treatment quality assurance.

The purpose of this study was to compare the MLC error sensitivity of various measurement devices for VMAT pre-treatment quality assurance (QA). This study used four QA devices (Scandidos Delta4, PTW 2D-array, iRT systems IQM, and PTW Farmer chamber). Nine retrospective VMAT plans were used and nine MLC error plans were generated for all nine original VMAT plans. The IQM and Farmer chamber were evaluated using the cumulative signal difference between the baseline and error-induced measurements. In addition, to investigate the sensitivity of the Delta4 device and the 2D-array, global gamma analysis (1%/1, 2%/2, and 3%/3 mm), dose difference (1%, 2%, and 3%) were used between the baseline and error-induced measurements. Some deviations of the MLC error sensitivity for the evaluation metrics and MLC error ranges were observed. For the two ionization devices, the sensitivity of the IQM was significantly better than that of the Farmer chamber (P < 0.01) while both devices had good linearly correlation between the cumulative signal difference and the magnitude of MLC errors. The pass rates decreased as the magnitude of the MLC error increased for both Delta4 and 2D-array. However, the small MLC error for small aperture sizes, such as for lung SBRT, could not be detected using the loosest gamma criteria (3%/3 mm). Our results indicate that DD could be more useful than gamma analysis for daily MLC QA, and that a large-area ionization chamber has a greater advantage for detecting systematic MLC error because of the large sensitive volume, while the other devices could not detect this error for some cases with a small range of MLC error.

Saito M ，Sano N ，Shibata Y ，Kuriyama K ，Komiyama T ，Marino K ，Aoki S ，Ashizawa K ，Yoshizawa K ，Onishi H ... -  《Journal of Applied Clinical Medical Physics》

Error detection using a convolutional neural network with dose difference maps in patient-specific quality assurance for volumetric modulated arc therapy.

The aim of this study was to evaluate the use of dose difference maps with a convolutional neural network (CNN) to detect multi-leaf collimator (MLC) positional errors in patient-specific quality assurance for volumetric modulated radiation therapy (VMAT). A cylindrical three-dimensional detector (Delta4, ScandiDos, Uppsala, Sweden) was used to measure 161 beams from 104 clinical prostate VMAT plans. For the simulation used error-free plans plus plans with two types of MLC error were introduced: systematic error and random error. A total of 483 dose distributions in a virtual cylindrical phantom were calculated with a treatment planning system. Dose difference maps were created from two planar dose distributions from the measured and calculated dose distributions, and these were used as the input for the CNN, with 375 datasets assigned for training and 108 datasets assigned for testing. The CNN model had three convolution layers and was trained with five-fold cross-validation. The CNN model classified the error types of the plans as "error-free," "systematic error," or "random error," with an overall accuracy of 0.944. The sensitivity values for the "error-free," "systematic error," and "random error" classifications were 0.889, 1.000, and 0.944, respectively, and the specificity values were 0.986, 0.986, and 0.944, respectively. This approach was superior to those based on gamma analysis. Using dose difference maps with a CNN model may provide an effective solution for detecting MLC errors for patient-specific VMAT quality assurance.

Kimura Y ，Kadoya N ，Tomori S ，Oku Y ，Jingu K ... -  《-》

Deep learning for patient-specific quality assurance: Identifying errors in radiotherapy delivery by radiomic analysis of gamma images with convolutional neural networks.

Patient-specific quality assurance (QA) for intensity-modulated radiation therapy (IMRT) is a ubiquitous clinical procedure, but conventional methods have often been criticized as being insensitive to errors or less effective than other common physics checks. Recently, there has been interest in the application of radiomics, quantitative extraction of image features, to radiotherapy QA. In this work, we investigate a deep learning approach to classify the presence or absence of introduced radiotherapy treatment delivery errors from patient-specific QA. Planar dose maps from 186 IMRT beams from 23 IMRT plans were evaluated. Each plan was transferred to a cylindrical phantom CT geometry. Three sets of planar doses were exported from each plan corresponding to (a) the error-free case, (b) a random multileaf collimator (MLC) error case, and (c) a systematic MLC error case. Each plan was delivered to the electronic portal imaging device (EPID), and planned and measured doses were used to calculate gamma images in an EPID dosimetry software package (for a total of 558 gamma images). Two radiomic approaches were used. In the first, a convolutional neural network with triplet learning was used to extract image features from the gamma images. In the second, a handcrafted approach using texture features was used. The resulting metrics from both approaches were input into four machine learning classifiers (support vector machines, multilayer perceptrons, decision trees, and k-nearest-neighbors) in order to determine whether images contained the introduced errors. Two experiments were considered: the two-class experiment classified images as error-free or containing any MLC error, and the three-class experiment classified images as error-free, containing a random MLC error, or containing a systematic MLC error. Additionally, threshold-based passing criteria were calculated for comparison. In total, 303 gamma images were used for model training and 255 images were used for model testing. The highest classification accuracy was achieved with the deep learning approach, with a maximum accuracy of 77.3% in the two-class experiment and 64.3% in the three-class experiment. The performance of the handcrafted approach with texture features was lower, with a maximum accuracy of 66.3% in the two-class experiment and 53.7% in the three-class experiment. Variability between the results of the four machine learning classifiers was lower for the deep learning approach vs the texture feature approach. Both radiomic approaches were superior to threshold-based passing criteria. Deep learning with convolutional neural networks can be used to classify the presence or absence of introduced radiotherapy treatment delivery errors from patient-specific gamma images. The performance of the deep learning network was superior to a handcrafted approach with texture features, and both radiomic approaches were better than threshold-based passing criteria. The results suggest that radiomic QA is a promising direction for clinical radiotherapy.

Nyflot MJ ，Thammasorn P ，Wootton LS ，Ford EC ，Chaovalitwongse WA ... -  《-》