Applications of machine and deep learning to patient-specific IMRT/VMAT quality assurance

A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy

BACKGROUND AND PURPOSE

Artificial Intelligence (AI) models in radiation therapy are being developed with increasing pace. Despite this, the radiation therapy community has not widely adopted these models in clinical practice. A cohesive guideline on how to develop, report and clinically validate AI algorithms might help bridge this gap.

METHODS AND MATERIALS

A Delphi process with all co-authors was followed to determine which topics should be addressed in this comprehensive guideline. Separate sections of the guideline, including Statements, were written by subgroups of the authors and discussed with the whole group at several meetings. Statements were formulated and scored as highly recommended or recommended.

RESULTS

The following topics were found most relevant: Decision making, image analysis, volume segmentation, treatment planning, patient specific quality assurance of treatment delivery, adaptive treatment, outcome prediction, training, validation and testing of AI model parameters, model availability for others to verify, model quality assurance/updates and upgrades, ethics. Key references were given together with an outlook on current hurdles and possibilities to overcome these. 19 Statements were formulated.

CONCLUSION

A cohesive guideline has been written which addresses main topics regarding AI in radiation therapy. It will help to guide development, as well as transparent and consistent reporting and validation of new AI tools and facilitate adoption.

Generating 3D images of VMAT plans for predictive models and activation maps associated with plan deliverability

BACKGROUND

Intensity modulation with dynamic multi-leaf collimator (MLC) and monitor unit (MU) changes across control points (CPs) characterizes volumetric modulated arc therapy (VMAT). The increased uncertainty in plan deliverability required patient-specific quality assurance (PSQA), which remained inefficient upon Quality Assurance (QA) failure. To prevent waste before QA, plan complexity metrics (PCMs) and machine learning models with the metrics were generated, which were lack of providing CP-specific information upon QA failures.

PURPOSE

By generating 3D images from digital imaging and comminications in medicine in radiation therapy (DICOM RT) plan, we proposed a predictive model that can estimate the deliverability of VMAT plans and visualize CP-specific regions associated with plan deliverability.

METHODS

The patient cohort consisted of 259 and 190 cases for left- and right-breast VMAT treatments, which were split into 235 and 166 cases for training and 24 cases from each treatment for testing the networks. Three-channel 3D images generated from DICOM RT plans were fed into a DenseNet-based deep learning network. To reflect VMAT plan complexity as an image, the first two channels described MLC and MU variations between two consecutive CPs, while the last channel assigned the beam field size. The network output was defined as binary classified PSQA results, indicating deliverability. The predictive performance was assessed by accuracy, sensitivity, specificity, F1-score, and area under the curve (AUC). The gradient-weighted class activation map (Grad-CAM) highlighted the regions of CPs in VMAT plans associated with deliverability, compared against PCMs by Spearman correlation.

RESULTS

The DenseNet-based predictive model yielded AUCs of 92.2% and 93.8%, F1-scores of 97.0% and 93.8% and accuracies of 95.8% and 91.7% for the left- and right-breast VMAT cases. Additionally, the specificity of 87.5% for both cases indicated that the predictive model accurately detected QA failing cases. The activation maps significantly differentiated QA failing-labeled from passing-labeled classes for the non-deliverable cases. The PCM with the highest correlation to the Grad-CAM varied from patient cases, implying that plan deliverability would be considered patient-specific.

CONCLUSION

This work demonstrated that the deep learning-based network based on visualization of dynamic VMAT plan information successfully predicted plan deliverability, which also provided control-point specific planning parameter information associated with plan deliverability in a patient-specific manner.

Error detection for radiotherapy planning validation based on deep learning networks

BACKGROUND

Quality assurance (QA) of patient-specific treatment plans for intensity-modulated radiation therapy (IMRT) and volumetric modulated arc therapy (VMAT) necessitates prior validation. However, the standard methodology exhibits deficiencies and lacks sensitivity in the analysis of positional dose distribution data, leading to difficulties in accurately identifying reasons for plan verification failure. This issue complicates and impedes the efficiency of QA tasks.

PURPOSE

The primary aim of this research is to utilize deep learning algorithms for the extraction of 3D dose distribution maps and the creation of a predictive model for error classification across multiple machine models, treatment methodologies, and tumor locations.

METHOD

We devised five categories of validation plans (normal, gantry error, collimator error, couch error, and dose error), conforming to tolerance limits of different accuracy levels and employing 3D dose distribution data from a sample of 94 tumor patients. A CNN model was then constructed to predict the diverse error types, with predictions compared against the gamma pass rate (GPR) standard employing distinct thresholds (3%, 3 mm; 3%, 2 mm; 2%, 2 mm) to evaluate the model's performance. Furthermore, we appraised the model's robustness by assessing its functionality across diverse accelerators.

RESULTS

The accuracy, precision, recall, and F1 scores of CNN model performance were 0.907, 0.925, 0.907, and 0.908, respectively. Meanwhile, the performance on another device is 0.900, 0.918, 0.900, and 0.898. In addition, compared to the GPR method, the CNN model achieved better results in predicting different types of errors.

CONCLUSION

When juxtaposed with the GPR methodology, the CNN model exhibits superior predictive capability for classification in the validation of the radiation therapy plan on different devices. By using this model, the plan validation failures can be detected more rapidly and efficiently, minimizing the time required for QA tasks and serving as a valuable adjunct to overcome the constraints of the GPR method.

A feasibility study to predict 3D dose delivery accuracy for IMRT using DenseNet with log files

OBJECTIVE

This study aims to explore the feasibility of DenseNet in the establishment of a three-dimensional (3D) gamma prediction model of IMRT based on the actual parameters recorded in the log files during delivery.

METHODS

A total of 55 IMRT plans (including 367 fields) were randomly selected. The gamma analysis was performed using gamma criteria of 3% /3 mm (Dose Difference/Distance to Agreement), 3% /2 mm, 2% /3 mm, and 2% /2 mm with a 10% dose threshold. In addition, the log files that recorded the gantry angle, monitor units (MU), multi-leaf collimator (MLC), and jaws position during delivery were collected. These log files were then converted to MU-weighted fluence maps as the input of DenseNet, gamma passing rates (GPRs) under four different gamma criteria as the output, and mean square errors (MSEs) as the loss function of this model.

RESULTS

Under different gamma criteria, the accuracy of a 3D GPR prediction model decreased with the implementation of stricter gamma criteria. In the test set, the mean absolute error (MAE) of the prediction model under the gamma criteria of 3% /3 mm, 2% /3 mm, 3% /2 mm, and 2% /2 mm was 1.41, 1.44, 3.29, and 3.54, respectively; the root mean square error (RMSE) was 1.91, 1.85, 4.27, and 4.40, respectively; the Sr was 0.487, 0.554, 0.573, and 0.506, respectively. There was a correlation between predicted and measured GPRs (P <  0.01). Additionally, there was no significant difference in the accuracy between the validation set and the test set. The accuracy in the high GPR group was high, and the MAE in the high GPR group was smaller than that in the low GPR group under four different gamma criteria.

CONCLUSIONS

In this study, a 3D GPR prediction model of patient-specific QA using DenseNet was established based on log files. As an auxiliary tool for 3D dose verification in IMRT, this model is expected to improve the accuracy and efficiency of dose validation.

Application of deep learning in radiation therapy for cancer

In recent years, with the development of artificial intelligence, deep learning has been gradually applied to clinical treatment and research. It has also found its way into the applications in radiotherapy, a crucial method for cancer treatment. This study summarizes the commonly used and latest deep learning algorithms (including transformer, and diffusion models), introduces the workflow of different radiotherapy, and illustrates the application of different algorithms in different radiotherapy modules, as well as the defects and challenges of deep learning in the field of radiotherapy, so as to provide some help for the development of automatic radiotherapy for cancer.

Detecting outliers beyond tolerance limits derived from statistical process control in patient-specific quality assurance

BACKGROUND

Tolerance limit is defined on pre-treatment patient specific quality assurance results to identify "out of the norm" dose discrepancy in plan. An out-of-tolerance plan during measurement can often cause treatment delays especially if replanning is required. In this study, we aim to develop an outlier detection model to identify out-of-tolerance plan early during treatment planning phase to mitigate the above-mentioned risks.

METHODS

Patient-specific quality assurance results with portal dosimetry for stereotactic body radiotherapy measured between January 2020 and December 2021 were used in this study. Data were divided into thorax and pelvis sites and gamma passing rates were recorded using 2%/2 mm, 2%/1 mm, and 1%/1 mm gamma criteria. Statistical process control method was used to determine six different site and criterion-specific tolerance and action limits. Using only the inliers identified with our determined tolerance limits, we trained three different outlier detection models using the plan complexity metrics extracted from each treatment field-robust covariance, isolation forest, and one class support vector machine. The hyperparameters were optimized using the F1-score calculated from both the inliers and validation outliers' data.

RESULTS

308 pelvis and 200 thorax fields were used in this study. The tolerance (action) limits for 2%/2 mm, 2%/1 mm, and 1%/1 mm gamma criteria in the pelvis site are 99.1% (98.1%), 95.8% (91.1%), and 91.7% (86.1%), respectively. The tolerance (action) limits in the thorax site are 99.0% (98.7%), 97.0% (96.2%), and 91.5% (87.2%). One class support vector machine performs the best among all the algorithms. The best performing model in the thorax (pelvis) site achieves a precision of 0.56 (0.54), recall of 1.0 (1.0), and F1-score of 0.72 (0.70) when using the 2%/2 mm (2%/1 mm) criterion.

CONCLUSION

The model will help the planner to identify an out-of-tolerance plan early so that they can refine the plan further during the planning stage without risking late discovery during measurement.

A TPS integrated machine learning tool for predicting patient-specific quality assurance outcomes in volumetric-modulated arc therapy

PURPOSE

Machine learning (ML) models have been demonstrated to be beneficial for optimizing the workload of patient-specific quality assurance (PSQA). Implementing them in clinical routine frequently requires third-party applications beyond the treatment planning system (TPS), slowing down the workflow. To address this issue, a PSQA outcomes predictive model was carefully selected and validated before being fully integrated into the TPS.

MATERIALS AND METHODS

Nine ML algorithms were evaluated using cross-validation. The learning database was built by calculating complexity metrics (CM) and binarizing PSQA results into "pass"/"fail" classes for 1767 VMAT arcs. The predictive performance was evaluated using area under the ROC curve (AUROC), sensitivity, and specificity. The ML model was integrated into the TPS via a C# script. Script-guided reoptimization impact on PSQA and dosimetric results was evaluated on ten VMAT plans with "fail"-predicted arcs. Workload reduction potential was also assessed.

RESULTS

The selected model exhibited an AUROC of 0.88, with a sensitivity and specificity exceeding 50 % and 90 %, respectively. The script-guided reoptimization of the ten evaluated plans led to an average improvement of 1.4 ± 0.9 percentage points in PSQA results, while preserving the quality of the dose distribution. A yearly savings of about 140 h with the use of the script was estimated.

CONCLUSIONS

The proposed script is a valuable complementary tool for PSQA measurement. It was efficiently integrated into the clinical workflow to enhance PSQA outcomes and reduce PSQA workload by decreasing the risk of failing QA and thereby, the need for repeated replanning and measurements.

Machine learning-based ensemble prediction model for the gamma passing rate of VMAT-SBRT plan

PURPOSE

The purpose of this study was to accurately predict or classify the beam GPR with an ensemble model by using machine learning for SBRT(VMAT) plans.

METHODS

A total of 128 SBRT VMAT plans with 330 arc beams were retrospectively selected, and 216 radiomics and 34 plan complexity features were calculated for each arc beam. Three models for GPR prediction and classification using support vector machine algorithm were as follows: (1) plan complexity feature-based model (plan model); (2) radiomics feature-based model (radiomics model); and (3) an ensemble model combining the two models (ensemble model). The prediction performance was evaluated by calculating the mean absolute error (MAE), root mean square error (RMSE), and Spearman's correlation coefficient (SC), and the classification performance was measured by calculating the area under the receiver operating characteristic curve (AUC), accuracy, specificity, and sensitivity.

RESULTS

The MAE, RMSE and SC at the 2 %/2 mm gamma criterion in the test dataset were 1.4 %, 2.57 %, and 0.563, respectively, for the plan model; 1.42 %, and 2.51 %, and 0.508, respectively, for the radiomics model; and 1.33 %, 2.49 %, and 0.611, respectively, for the ensemble model. The accuracy, specificity, sensitivity, and AUC at the 2 %/2 mm gamma criterion in the test dataset were 0.807, 0.824, 0.681, and 0.854, respectively, for the plan model; 0.860, 0.893, 0.624, and 0.877, respectively, for the radiomics model; and 0.852, 0.871, 0.710, and 0.896, respectively, for the ensemble model.

CONCLUSIONS

The ensemble model can improve the prediction and classification performance for the GPR of SBRT (VMAT).

Prediction of patient-specific quality assurance for volumetric modulated arc therapy using radiomics-based machine learning with dose distribution

PURPOSE

We sought to develop machine learning models to predict the results of patient-specific quality assurance (QA) for volumetric modulated arc therapy (VMAT), which were represented by several dose-evaluation metrics-including the gamma passing rates (GPRs)-and criteria based on the radiomic features of 3D dose distribution in a phantom.

METHODS

A total of 4,250 radiomic features of 3D dose distribution in a cylindrical dummy phantom for 140 arcs from 106 clinical VMAT plans were extracted. We obtained the following dose-evaluation metrics: GPRs with global and local normalization, the dose difference (DD) in 1% and 2% passing rates (DD1% and DD2%) for 10% and 50% dose threshold, and the distance-to-agreement in 1-mm and 2-mm passing rates (DTA1 mm and DTA2 mm) for 0.5%/mm and 1.0%.mm dose gradient threshold determined by measurement using a diode array in patient-specific QA. The machine learning regression models for predicting the values of the dose-evaluation metrics using the radiomic features were developed based on the elastic net (EN) and extra trees (ET) models. The feature selection and tuning of hyperparameters were performed with nested cross-validation in which four-fold cross-validation is used within the inner loop, and the performance of each model was evaluated in terms of the root mean square error (RMSE), the mean absolute error (MAE), and Spearman's rank correlation coefficient.

RESULTS

The RMSE and MAE for the developed machine learning models ranged from <1% to nearly <10% depending on the dose-evaluation metric, the criteria, and dose and dose gradient thresholds used for both machine learning models. It was advantageous to focus on high dose region for predicating global GPR, DDs, and DTAs. For certain metrics and criteria, it was possible to create models applicable for patients' heterogeneity by training only with dose distributions in phantom.

CONCLUSIONS

The developed machine learning models showed high performance for predicting dose-evaluation metrics especially for high dose region depending on the metric and criteria. Our results demonstrate that the radiomic features of dose distribution can be considered good indicators of the plan complexity and useful in predicting measured dose evaluation metrics.

Deep learning-based detection and classification of multi-leaf collimator modeling errors in volumetric modulated radiation therapy

PURPOSE

The purpose of this study was to create and evaluate deep learning-based models to detect and classify errors of multi-leaf collimator (MLC) modeling parameters in volumetric modulated radiation therapy (VMAT), namely the transmission factor (TF) and the dosimetric leaf gap (DLG).

METHODS

A total of 33 clinical VMAT plans for prostate and head-and-neck cancer were used, assuming a cylindrical and homogeneous phantom, and error plans were created by altering the original value of the TF and the DLG by ± 10, 20, and 30% in the treatment planning system (TPS). The Gaussian filters ofσ = 0.5 $\sigma = 0.5$ and 1.0 were applied to the planar dose maps of the error-free plan to mimic the measurement dose map, and thus dose difference maps between the error-free and error plans were obtained. We evaluated 3 deep learning-based models, created to perform the following detections/classifications: (1) error-free versus TF error, (2) error-free versus DLG error, and (3) TF versus DLG error. Models to classify the sign of the errors were also created and evaluated. A gamma analysis was performed for comparison.

RESULTS

The detection and classification of TF and DLG error were feasible forσ = 0.5 $\sigma = 0.5$ ; however, a considerable reduction of accuracy was observed forσ = 1.0 $\sigma = 1.0$ depending on the magnitude of error and treatment site. The sign of errors was detectable by the specifically trained models forσ = 0.5 $\sigma = 0.5$ and 1.0. The gamma analysis could not detect errors.

CONCLUSIONS

We demonstrated that the deep learning-based models could feasibly detect and classify TF and DLG errors in VMAT dose distributions, depending on the magnitude of the error, treatment site, and the degree of mimicked measurement doses.

Virtual pretreatment patient-specific quality assurance of volumetric modulated arc therapy using deep learning

BACKGROUND

Automatic patient-specific quality assurance (PSQA) is recently explored using artificial intelligence approaches, and several studies reported the development of machine learning models for predicting the gamma pass rate (GPR) index only.

PURPOSE

To develop a novel deep learning approach using a generative adversarial network (GAN) to predict the synthetic measured fluence.

METHODS AND MATERIALS

A novel training method called "dual training," which involves the training of the encoder and decoder separately, was proposed and evaluated for cycle GAN (cycle-GAN) and conditional GAN (c-GAN). A total of 164 VMAT treatment plans, including 344 arcs (training data: 262, validation data: 30, and testing data: 52) from various treatment sites, were selected for prediction model development. For each patient, portal-dose-image-prediction fluence from TPS was used as input, and measured fluence from EPID was used as output/response for model training. Predicted GPR was derived by comparing the TPS fluence with the synthetic measured fluence generated by the DL models using gamma evaluation of criteria 2%/2 mm. The performance of dual training was compared against the traditional single-training approach. In addition, we also developed a separate classification model specifically designed to detect automatically three types of errors (rotational, translational, and MU-scale) in the synthetic EPID-measured fluence.

RESULTS

Overall, the dual training improved the prediction accuracy of both cycle-GAN and c-GAN. Predicted GPR results of single training were within 3% for 71.2% and 78.8% of test cases for cycle-GAN and c-GAN, respectively. Moreover, similar results for dual training were 82.7% and 88.5% for cycle-GAN and c-GAN, respectively. The error detection model showed high classification accuracy (>98%) for detecting errors related to rotational and translational errors. However, it struggled to differentiate the fluences with "MU scale error" from "error-free" fluences.

CONCLUSION

We developed a method to automatically generate the synthetic measured fluence and identify errors within them. The proposed dual training improved the PSQA prediction accuracy of both the GAN models, with c-GAN demonstrating superior performance over the cycle-GAN. Our results indicate that the c-GAN with dual training approach combined with error detection model, can accurately generate the synthetic measured fluence for VMAT PSQA and identify the errors. This approach has the potential to pave the way for virtual patient-specific QA of VMAT treatments.

Prediction models as decision-support tools for virtual patient-specific quality assurance of helical tomotherapy plans

Background and purpose

Prediction models may be reliable decision-support tools to reduce the workload associated with the measurement-based patient-specific quality assurance (PSQA) of radiotherapy plans. This study compared the effectiveness of three different models based on delivery parameters, complexity metrics and sinogram radiomics features as tools for virtual-PSQA (vPSQA) of helical tomotherapy (HT) plans.

Materials and methods

A dataset including 881 RT plans created with two different treatment planning systems (TPSs) was collected. Sixty-five indicators including 12 delivery parameters (DP) and 53 complexity metrics (CM) were extracted using a dedicated software library. Additionally, 174 radiomics features (RF) were extracted from the plans' sinograms. Three groups of variables were formed: A (DP), B (DP + CM) and C (DP + CM + RF). Regression models were trained to predict the gamma index passing rate P R γ (3%G, 2mm) and the impact of each group of variables was investigated. ROC-AUC analysis measured the ability of the models to accurately discriminate between 'deliverable' and 'non-deliverable' plans.

Results

The best performance was achieved by model C which allowed detecting around 16% and 63% of the 'deliverable' plans with 100% sensitivity for the two TPSs, respectively. In a real clinical scenario, this would have decreased the whole PSQA workload by approximately 35%.

Conclusions

The combination of delivery parameters, complexity metrics and sinogram radiomics features allows for robust and reliable PSQA gamma passing rate predictions and high-sensitivity detection of a fraction of deliverable plans for one of the two TPSs. Promising yet improvable results were obtained for the other one. The results foster a future adoption of vPSQA programs for HT.

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.

Machine Learning Based Prediction of Gamma Passing Rate for VMAT Radiotherapy Plans

The use of machine learning algorithms (ML) in radiotherapy is becoming increasingly popular. More and more groups are trying to apply ML in predicting the so-called gamma passing rate (GPR). Our team has developed a customized approach of using ML algorithms to predict global GPR for electronic portal imaging device (EPID) verification for dose different 2% and distance to agreement 2 mm criteria for VMAT dynamic plans. Plans will pass if the GPR is greater than 98%. The algorithm was learned and tested on anonymized clinical data from 13 months which resulted in more than 3000 treatment plans. The obtained results of GPR prediction are very interesting. Average specificity of the algorithm based on an ensemble of 50 decision tree regressors is 91.6% for our criteria. As a result, we can reduce the verification process by 50%. The novel approach described by our team can offer a new insight into the application of ML and neural networks in GPR prediction and dosimetry.

Machine learning-based predictions of gamma passing rates for virtual specific-plan verification based on modulation maps, monitor unit profiles, and composite dose images

Machine learning (ML) methods have been implemented in radiotherapy to aid virtual specific-plan verification protocols, predicting gamma passing rates (GPR) based on calculated modulation complexity metrics because of their direct relation to dose deliverability. Nevertheless, these metrics might not comprehensively represent the modulation complexity, and automatically extracted features from alternative predictors associated with modulation complexity are needed. For this reason, three convolutional neural networks (CNN) based models were trained to predict GPR values (regression and classification), using respectively three predictors: (1) the modulation maps (MM) from the multi-leaf collimator, (2) the relative monitor units per control point profile (MUcp), and (3) the composite dose image (CDI) used for portal dosimetry, from 1024 anonymized prostate plans. The models' performance was assessed for classification and regression by the area under the receiver operator characteristic curve (AUC_ROC) and Spearman's correlation coefficient (r). Finally, four hybrid models were designed using all possible combinations of the three predictors. The prediction performance for the CNN-models using single predictors (MM, MUcp, and CDI) were AUC_ROC = 0.84 ± 0.03, 0.77 ± 0.07, 0.75 ± 0.04, andr= 0.6, 0.5, 0.7. Contrastingly, the hybrid models (MM + MUcp, MM + CDI, MUcp+CDI, MM + MUcp+CDI) performance were AUC_ROC = 0.94 ± 0.03, 0.85 ± 0.06, 0.89 ± 0.06, 0.91 ± 0.03, andr= 0.7, 0.5, 0.6, 0.7. The MP, MUcp, and CDI are suitable predictors for dose deliverability models implementing ML methods. Additionally, hybrid models are susceptible to improving their prediction performance, including two or more input predictors.

Efficient dose-volume histogram-based pretreatment patient-specific quality assurance methodology with combined deep learning and machine learning models for volumetric modulated arc radiotherapy

BACKGROUND

Weak correlation between gamma passing rates and dose differences in target volumes and organs at risk (OARs) has been reported in several studies. Evaluation on the differences between planned dose-volume histogram (DVH) and reconstructed DVH from measurement was adopted and incorporated into patient-specific quality assurance (PSQA). However, it is difficult to develop a methodology allowing the evaluation of errors on DVHs accurately and quickly.

PURPOSE

To develop a DVH-based pretreatment PSQA for volumetric modulated arc therapy (VMAT) with combined deep learning (DL) and machine learning models to overcome the limitation of conventional gamma index (GI) and improve the efficiency of DVH-based PSQA.

METHODS

A DL model with a three-dimensional squeeze-and-excitation residual blocks incorporated into a modified U-net was developed to predict the measured PSQA DVHs of 208 head-and-neck (H&N) cancer patients underwent VMAT between 2018 and 2021 from two hospitals, in which 162 cases was randomly selected for training, 18 for validation, and 28 for testing. After evaluating the differences between treatment planning system (TPS) and PSQA DVHs predicted by DL model with multiple metrics, a pass or fail (PoF) classification model was developed using XGBoost algorithm. Evaluation of domain experts on dose errors between TPS and reconstructed PSQA DVHs was taken as ground truth for PoF classification model training.

RESULTS

The prediction model was able to achieve a good agreement between predicted, measured, and TPS doses. Quantitative evaluation demonstrated no significant difference between predicted PSQA dose and measured dose for target and OARs, except for D_mean of PTV6900 (p = 0.001), D₅₀ of PTV6000 (p = 0.014), D₂ of PTV5400 (p = 0.009), D₅₀ of left parotid (p = 0.015), and D_max of left inner ear (p = 0.007). The XGBoost model achieved an area under curves, accuracy, sensitivity, and specificity of 0.89 versus 0.88, 0.89 versus 0.86, 0. 71 versus 0.71, and 0.95 versus 0.91 with measured and predicted PSQA doses, respectively. The agreement between domain experts and the classification model was 86% for 28 test cases.

CONCLUSIONS

The successful prediction of PSQA doses and classification of PoF for H&N VMAT PSQA indicating that this DVH-based PSQA method is promising to overcome the limitations of GI and to improve the efficiency and accuracy of VMAT delivery.

Prediction of VMAT delivery accuracy using plan modulation complexity score and log-files analysis

The purpose of this study was to develop a predictive model based on plan complexity metrics and linac log-files analysis to classify the dosimetric accuracy of VMAT plans. A total of 612 VMAT plans, corresponding to 1224 arcs, were analyzed. All VMAT arcs underwent pre-treatment verification that was performed by means of the dynamic log-files generated by the linac. The comparison of predicted (by TPS) and measured (by log-files) integral fluences was performed using γ-analysis in terms of the percentage of points with γ-value smaller than one (γ%) and using a stringent 2%(local)/2mm criteria. This γ-analysis was performed by a commercial software LinacWatch. The action limits (AL) were derived from the mean values, standard deviations and the confidence limit (CL) of the γ% distribution. A plan complexity metric, the modulation complexity score (MCS), based on the aperture beam area variability and leaf sequence variability was used as input variable of the model. A binary logistic regression (LR) model was developed to classify QA results as "pass" (γ%≥AL) or "fail" (γ%<AL). Receiver operator characteristics (ROC) curves were used to determine the optimal MCS threshold to flag "failed" plans that need to be re-optimized. The model reliability was evaluated stratifying the plans in training, validation and testing groups. The confidence and action limits for γ% were found 20.1% and 79.9%, respectively. The accuracy of the model for the training and testing dataset was 97.4% and 98.0%, respectively. The optimal MCS threshold value for the identification of failed plans was 0.142, providing a true positive rate able to flag the plans failing QA of 91%. In clinical routine, the use of this MCS threshold may allow the prompt identification of overly modulated plans, then reducing the number of QA failures and improving the quality of VMAT plans used for treatment.

Differentiation of Benign From Malignant Parotid Gland Tumors Using Conventional MRI Based on Radiomics Nomogram

Objectives

We aimed to develop and validate radiomic nomograms to allow preoperative differentiation between benign- and malignant parotid gland tumors (BPGT and MPGT, respectively), as well as between pleomorphic adenomas (PAs) and Warthin tumors (WTs).

Materials and Methods

This retrospective study enrolled 183 parotid gland tumors (68 PAs, 62 WTs, and 53 MPGTs) and divided them into training (n = 128) and testing (n = 55) cohorts. In total, 2553 radiomics features were extracted from fat-saturated T2-weighted images, apparent diffusion coefficient maps, and contrast-enhanced T1-weighted images to construct single-, double-, and multi-sequence combined radiomics models, respectively. The radiomics score (Rad-score) was calculated using the best radiomics model and clinical features to develop the radiomics nomogram. The receiver operating characteristic curve and area under the curve (AUC) were used to assess these models, and their performances were compared using DeLong’s test. Calibration curves and decision curve analysis were used to assess the clinical usefulness of these models.

Results

The multi-sequence combined radiomics model exhibited better differentiation performance (BPGT vs. MPGT, AUC=0.863; PA vs. MPGT, AUC=0.929; WT vs. MPGT, AUC=0.825; PA vs. WT, AUC=0.927) than the single- and double sequence radiomics models. The nomogram based on the multi-sequence combined radiomics model and clinical features attained an improved classification performance (BPGT vs. MPGT, AUC=0.907; PA vs. MPGT, AUC=0.961; WT vs. MPGT, AUC=0.879; PA vs. WT, AUC=0.967).

Conclusions

Radiomics nomogram yielded excellent diagnostic performance in differentiating BPGT from MPGT, PA from MPGT, and PA from WT.

Recent Applications of Artificial Intelligence in Radiotherapy: Where We Are and Beyond

In recent decades, artificial intelligence (AI) tools have been applied in many medical fields, opening the possibility of finding novel solutions for managing very complex and multifactorial problems, such as those commonly encountered in radiotherapy (RT). We conducted a PubMed and Scopus search to identify the AI application field in RT limited to the last four years. In total, 1824 original papers were identified, and 921 were analyzed by considering the phase of the RT workflow according to the applied AI approaches. AI permits the processing of large quantities of information, data, and images stored in RT oncology information systems, a process that is not manageable for individuals or groups. AI allows the iterative application of complex tasks in large datasets (e.g., delineating normal tissues or finding optimal planning solutions) and might support the entire community working in the various sectors of RT, as summarized in this overview. AI-based tools are now on the roadmap for RT and have been applied to the entire workflow, mainly for segmentation, the generation of synthetic images, and outcome prediction. Several concerns were raised, including the need for harmonization while overcoming ethical, legal, and skill barriers.

Clinical Application of Early Warning Scoring Based on BiLSTM-Attention in Emergency Obstetric Preexamination and Triage

Maternity is a special category of population and the criteria for emergency prescreening cannot be directly applied to adults. Therefore, a set of criteria for grading maternal conditions should be established. In this paper, we have combined the semantic analysis technique of BiLSTM-Attention neural network and fuzzy defect risk assessment method, to develop a hybrid approach, to preprocess the text of emergency obstetric prescreening information. Furthermore, we have used word2vec to characterize the word embedding vector and highlight the features related to the degree of defects of emergency obstetric prescreening information through the attention mechanism and obtain the semantic feature vector of the warning information. BiLSTM-Attention neural network has the dual advantages of extracting bidirectional semantic information and giving weight to important judgment information which has effectively improved the semantic understanding accuracy. Experimental tests and application analysis show that the judgment model which is based on proposed method has accurately classified and graded the defects of emergency obstetric prescreening alerts. Additionally, the accuracy and microaverage value are used as evaluation indexes.