Clinical evaluation on automatic segmentation results of convolutional neural networks in rectal cancer radiotherapy.

Purpose: Image segmentation can be time-consuming and lacks consistency between different oncologists, which is essential in conformal radiotherapy techniques. We aimed to evaluate automatic delineation results generated by convolutional neural networks (CNNs) from geometry and dosimetry perspectives and explore the reliability of these segmentation tools in rectal cancer. Methods: Forty-seven rectal cancer cases treated from February 2018 to April 2019 were randomly collected retrospectively in our cancer center. The oncologists delineated regions of interest (ROIs) on planning CT images as the ground truth, including clinical target volume (CTV), bladder, small intestine, and femoral heads. The corresponding automatic segmentation results were generated by DeepLabv3+ and ResUNet, and we also used Atlas-Based Autosegmentation (ABAS) software for comparison. The geometry evaluation was carried out using the volumetric Dice similarity coefficient (DSC) and surface DSC, and critical dose parameters were assessed based on replanning optimized by clinically approved or automatically generated CTVs and organs at risk (OARs), i.e., the Planref and Plantest. Pearson test was used to explore the correlation between geometric metrics and dose parameters. Results: In geometric evaluation, DeepLabv3+ performed better in DCS metrics for the CTV (volumetric DSC, mean = 0.96, P< 0.01; surface DSC, mean = 0.78, P< 0.01) and small intestine (volumetric DSC, mean = 0.91, P< 0.01; surface DSC, mean = 0.62, P< 0.01), ResUNet had advantages in volumetric DSC of the bladder (mean = 0.97, P< 0.05). For critical dose parameters analysis between Planref and Plantest, there was a significant difference for target volumes (P< 0.01), and no significant difference was found for the ResUNet-generated small intestine (P > 0.05). For the correlation test, a negative correlation was found between DSC metrics (volumetric, surface DSC) and dosimetric parameters (δD95, δD95, HI, CI) for target volumes (P< 0.05), and no significant correlation was found for most tests of OARs (P > 0.05). Conclusions: CNNs show remarkable repeatability and time-saving in automatic segmentation, and their accuracy also has a certain potential in clinical practice. Meanwhile, clinical aspects, such as dose distribution, may need to be considered when comparing the performance of auto-segmentation methods.

Neural signals-based respiratory motion tracking: a proof-of-concept study.

Objective.Respiratory motion tracking techniques can provide optimal treatment accuracy for thoracoabdominal radiotherapy and robotic surgery. However, conventional imaging-based respiratory motion tracking techniques are time-lagged owing to the system latency of medical linear accelerators and surgical robots. This study aims to investigate the precursor time of respiratory-related neural signals and analyze the potential of neural signals-based respiratory motion tracking.Approach.The neural signals and respiratory motion from eighteen healthy volunteers were acquired simultaneously using a 256-channel scalp electroencephalography (EEG) system. The neural signals were preprocessed using the MNE python package to extract respiratory-related EEG neural signals. Cross-correlation analysis was performed to assess the precursor time and cross-correlation coefficient between respiratory-related EEG neural signals and respiratory motion.Main results.Respiratory-related neural signals that precede the emergence of respiratory motion are detectable via non-invasive EEG. On average, the precursor time of respiratory-related EEG neural signals was 0.68 s. The representative cross-correlation coefficients between EEG neural signals and respiratory motion of the eighteen healthy subjects varied from 0.22 to 0.87.Significance.Our findings suggest that neural signals have the potential to compensate for the system latency of medical linear accelerators and surgical robots. This indicates that neural signals-based respiratory motion tracking is a potential promising solution to respiratory motion and could be useful in thoracoabdominal radiotherapy and robotic surgery.

Effects of Rehabilitation Therapy at Different Intervention Times on Daily Living Activity and Motor Function in Patients with Traumatic Spinal Cord Injury.

Objectives: We investigated the impact of traumatic spinal cord injury (TSCI) on daily living activities and motor function of TSCI patients. Methods: A total of 88 TSCI patients were randomly divided into Group A (N=44) and Group B (N=44). Group A received rehabilitation treatment 7 days after the stabilization of vital signs, and Group B received rehabilitation treatment 30 days after hospitalization. Results: The compliance rate of Group A (93.18%) was higher than that of Group B (72.73%) (χ 2 =6.510, p<.05); The scores of American Spinal Injury Association (ASIA) and Activities of Daily Living (ADL) in Group A were higher than those in Group B. The self-rating score of anxiety and depression was lower than that of Group B (p<.05). Conclusion: For the rehabilitation treatment of TSCI patients, it is better to choose the intervention after the vital signs are stable to improve patients' ability for daily living activities and motor function.

Dihydro-Resveratrol Attenuates Oxidative Stress, Adipogenesis and Insulin Resistance in In Vitro Models and High-Fat Diet-Induced Mouse Model via AMPK Activation.

Management of obesity has become a prevalent strategy for preventing the diseases closely integrated with excess body weight such as diabetes over the last half century. Searching for therapeutic agents acting on oxidative stress, adipogenesis and insulin resistance is considered as an efficient approach to control obesity-related diseases. The present study was designed to examine the in vitro and in vivo effects of dihydro-resveratrol (DR2), a naturally occurring compound from Dendrobium medicinal plants, on oxidative stress aggravation, adipogenesis, lipogenesis and insulin sensitivity. We utilized an in vitro 3T3-L1 adipocyte differentiation model to show that DR2 could reduce pre-adipocyte maturation by activation of AMPK/SIRT1 signaling proteins to inhibit p38MAPK proteins. With the use of in vitro oxidative-stress-induced hepatocytes and myoblasts models, DR2 was also shown to be able to reduce oxidative stress aggravation through mediation of Nrf2-related antioxidative cascade, reduce intracellular lipid accumulation through phosphorylation of ACC protein, reduce lipid peroxidation in hepatocytes and promote insulin sensitivity via activation of AKT protein in the insulin-resistant HepG2 cells and C2C12 cells. The effects of DR2 on adipogenesis, lipid accumulation, insulin resistance and blood glucose clearance were further demonstrated in the high-fat diet-induced obesity mouse model. Our in vitro and in vivo studies determined that DR2 could contain therapeutic potential for the treatment of obesity and type 2 diabetes.

Young oncologists benefit more than experts from deep learning-based organs-at-risk contouring modeling in nasopharyngeal carcinoma radiotherapy: A multi-institution clinical study exploring working experience and institute group style factor.

Background: To comprehensively investigate the behaviors of oncologists with different working experiences and institute group styles in deep learning-based organs-at-risk (OAR) contouring. Methods: A deep learning-based contouring system (DLCS) was modeled from 188 CT datasets of patients with nasopharyngeal carcinoma (NPC) in institute A. Three institute oncology groups, A, B, and C, were included; each contained a beginner and an expert. For each of the 28 OARs, two trials were performed with manual contouring first and post-DLCS edition later, for ten test cases. Contouring performance and group consistency were quantified by volumetric and surface Dice coefficients. A volume-based and a surface-based oncologist satisfaction rate (VOSR and SOSR) were defined to evaluate the oncologists' acceptance of DLCS. Results: Based on DLCS, experience inconsistency was eliminated. Intra-institute consistency was eliminated for group C but still existed for group A and group B. Group C benefits most from DLCS with the highest number of improved OARs (8 for volumetric Dice and 10 for surface Dice), followed by group B. Beginners obtained more numbers of improved OARs than experts (7 v.s. 4 in volumetric Dice and 5 v.s. 4 in surface Dice). VOSR and SOSR varied for institute groups, but the rates of beginners were all significantly higher than those of experts for OARs with experience group significance. A remarkable positive linear relationship was found between VOSR and post-DLCS edition volumetric Dice with a coefficient of 0.78. Conclusions: The DLCS was effective for various institutes and the beginners benefited more than the experts.

Guaranteed performance of individual control chart used in gamma passing rate-based patient-specific quality assurance.

PURPOSE: To assess the effect of sampling variability on the performance of individual charts (I-charts) for PSQA and provide a robust and reliable method for unknown PSQA processes. MATERIALS AND METHODS: A total of 1327 pretreatment PSQAs were analyzed. Different datasets with samples in the range of 20-1000 were used to estimate the lower control limit (LCL). Based on the iterative "Identify-Eliminate-Recalculate" and direct calculation without any outlier filtering procedures, five I-charts methods, namely the Shewhart, quantile, scaled weighted variance (SWV), weighted standard deviation (WSD), and skewness correction (SC) method, were used to compute the LCL. The average run length (ARL0) and false alarm rate (FAR0) were calculated to evaluate the performance of LCL. RESULTS: The ground truth of the values of LCL, FAR0, and ARL0 obtained via in-control PSQAs were 92.31%, 0.135%, and 740.7, respectively. Further, for in-control PSQAs, the width of the 95% confidence interval of LCL values for all methods tended to decrease with the increase in sample size. In all sample ranges of in-control PSQAs, only the median LCL and ARL0 values obtained via WSD and SWV methods were close to the ground truth. For the actual unknown PSQAs, based on the "Identify-Eliminate-Recalculate" procedure, only the median LCL values obtained by the WSD method were closest to the ground truth. CONCLUSIONS: Sampling variability seriously affected the I-chart performance in PSQA processes, particularly for small samples. For unknown PSQAs, the WSD method based on the implementation of the iterative "Identify-Eliminate-Recalculate" procedure exhibited sufficient robustness and reliability.

Machine learning for predicting accuracy of lung and liver tumor motion tracking using radiomic features.

Background: Internal tumor motion is commonly predicted using external respiratory signals. However, the internal/external correlation is complex and patient-specific. The purpose of this study was to develop various models based on the radiomic features of computed tomography (CT) images to predict the accuracy of tumor motion tracking using external surrogates and to find accurate and reliable tracking algorithms. Methods: Images obtained from a total of 108 and 71 patients pathologically diagnosed with lung and liver cancers, respectively, were examined. Real-time position monitoring motion was fitted to tumor motion, and samples with fitting errors greater than 2 mm were considered positive. Radiomic features were extracted from internal target volumes of average intensity projections, and cross-validation least absolute shrinkage and selection operator (LassoCV) was used to conduct feature selection. Based on the radiomic features, a total of 26 separate models (13 for the lung and 13 for the liver) were trained and tested. Area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were used to assess performance. Relative standard deviation was used to assess stability. Results: Thirty-three and 22 radiomic features were selected for the lung and liver, respectively. For the lung, the AUC varied from 0.848 (decision tree) to 0.941 [support vector classifier (SVC), logistic regression]; sensitivity varied from 0.723 (extreme gradient boosting) to 0.848 [linear support vector classifier (linearSVC)]; specificity varied from 0.834 (gaussian naive bayes) to 0.936 [multilayer perceptron (MLP), wide and deep (W&D)]; and MLP and W&D had better performance and stability than the median. For the liver, the AUC varied from 0.677 [light gradient boosting machine (Light)] to 0.892 (logistic regression); sensitivity varied from 0.717 (W&D) to 0.862 (MLP); specificity varied from 0.566 (Light) to 0.829 (linearSVC); and logistic regression, MLP, and SVC had better performance and stability than the median. Conclusions: Respiratory-sensitive radiomic features extracted from CT images of lung and liver tumors were proved to contain sufficient information to establish an external/internal motion relationship. We developed a rapid and accurate method based on radiomics to classify the accuracy of monitoring a patient's external surface for lung and liver tumor tracking. Several machine learning algorithms-in particular, MLP-demonstrated excellent classification performance and stability.

Predictive value of magnetic resonance imaging radiomics-based machine learning for disease progression in patients with high-grade glioma.

Background: Accurately predicting the prognosis of patients with high-grade glioma (HGG) is potentially important for treatment. However, the predictive value of images of various magnetic resonance imaging (MRI) sequences for prognosis at different time points is unknown. We established predictive machine learning models of HGG disease progression and recurrence using MRI radiomics and explored the factors influencing prediction accuracy. Methods: Radiomics features were extracted from T1-weighted (T1WI), contrast-enhanced T1-weighted (CE-T1WI), T2-weighted (T2WI), and fluid-attenuated inversion recovery (FLAIR) images (postoperative radiotherapy planning MRI images) obtained from 162 patients with HGG. The Mann-Whitney U test and least absolute shrinkage and selection operator (LASSO) algorithm were used for feature selection. Machine learning models were used to build prediction models to estimate disease progression or recurrence. The influence of different MRI sequences, regions of interest (ROIs), and prediction time points was also explored. The receiver operating characteristic (ROC) curve was used to evaluate the discriminative performance of each model, and the DeLong test was employed to compare the ROC curves. Results: Radiomics features from T2WI and FLAIR demonstrated greater predictive value for disease progression compared with T1WI or CE-TIWI. The best predictive models, with areas under the ROC curves (AUCs) of 0.70, 0.68, 0.78, 0.78, and 0.78 for predicting disease progression at the 6th, 9th, 12th, 15th, and 18th month after radiotherapy, respectively, were obtained by combining clinical features with gross tumor volume (GTV) and clinical target volume (CTV) features extracted from T2WI and FLAIR. Conclusions: Structural MRI obtained before radiotherapy can be used to predict the disease progression or posttreatment recurrence of HGG. When using MRI radiomics to predict long-term outcomes as opposed to short-term outcomes, better predictive results may be obtained.

A Script-Based Automatic Intensity Modulated Radiation Therapy Planning Method With Robust Optimization for Craniospinal Irradiation.

This report describes a script-based automatic planning method with robust optimization for craniospinal irradiation (CSI) to reduce sensitivity to field matching errors and increase planning efficiency. The data of 10 CSI patients with planning target volume (PTV) lengths between 49.8 and 85.0 cm were retrospectively studied. Robust intensity modulated radiation therapy plans with ±5-mm longitudinal position uncertainty were generated by the automatic planning script. A simple dose prediction model and a self-adjusting method were implied in the automatic plans. The plans' robustness against setup errors was evaluated by deliberately shifting the middle beamset ±5 mm in the superior-inferior direction. Manual and nonrobust plans were also created to evaluate the automatic robust plans' quality, efficiency, and robustness. There were no significant differences between the manual and automatic plans in terms of homogeneity index; conformity index; D1%, D2%, and D98% of PTV; and average doses of organs at risk. However, the D99% of the PTV in the automatic plans was slightly inferior to that in the manual plans. Compared with the manual plans, the automatic plans greatly increased efficiency, with a reduction in planning time of approximately 48%. When ±5-mm superior-inferior errors were introduced, the average deviations of the maximum dose D1% and minimum dose D99% to the spinal cord were 4.9% (±1.1%) and -3.4% (±1.3%), respectively. However, the corresponding values of the nonrobust plans were 20.0% (±5.4%) and -21.2 (±6.3%), respectively. The script-based automatic CSI planning method, combining robust optimization and a dose prediction model, efficiently created a good-quality plan that was robust to setup errors.

Machine Learning Radiomics Model for External and Internal Respiratory Motion Correlation Prediction in Lung Tumor.

Objectives: The complexity and specificity of lung tumor motion render it necessary to determine the external and internal correlation individually before applying indirect tumor tracking. However, the correlation cannot be determined from patient respiratory and tumor clinical characteristics before treatment. The purpose of this study is to present a machine learning model for an external/internal correlation prediction that is based on computed tomography (CT) radiomic features. Methods: 4-dimensional computed tomography (4DCT) images of 67 patients were collected retrospectively, and the external/internal correlation of lung tumor was calculated based on Spearman's rank correlation coefficient. Radiomic features were extracted from average intensity projection and the light gradient boosting machine (LightGBM)-based cross-validation (the recursive elimination method) was used for feature selection. The LightGBM framework forecasting models with classification thresholds 0.7, 0.8, and 0.9 are established using stratified 5-fold cross-validation. Model performance was assessed using receiver operating characteristics, sensitivity, and specificity. Results: There were 16, 18, and 13 features selected for models 0.7, 0.8, and 0.9, respectively. Texture features are of great importance in external/internal correlation prediction compared to other features in all models. The sensitivities of the predictions in models 0.7, 0.8, and 0.9 were 0.800 ± 0.126, 0.829 ± 0.140, and 0.864 ± 0.086, respectively. The specificities were 0.771 ± 0.114, 0.936 ± 0.0581, and 0.839 ± 0.101, whereas the area under the curve (AUC) was 0.837, 0.946, and 0.877, respectively. Conclusions: Our findings indicate that radiomics is an effective tool for respiratory motion correlation prediction, which can extract tumor motion characteristics. We proposed a machine learning framework for correlation prediction in the motion management strategy for lung tumor patients.

Correlation of Optical Surface Respiratory Motion Signal and Internal Lung and Liver Tumor Motion: A Retrospective Single-Center Observational Study.

Purpose: Surface-guided radiation therapy (SGRT) application has limitations. This study aimed to explore the relationship between patient characteristics and their external/internal correlation to qualitatively assess the external/internal correlation in a particular patient. Methods: Liver and lung cancer patients treated with radiotherapy in our institution were retrospectively analyzed. The external/internal correlation were calculated with Spearman correlation coefficient (SCC) and SCC after support vector regression (SVR) fitting (SCCsvr). The relationship between the external/internal correlation and magnitudes of motion of the tumor and external marker (Ai, Ae), tumor volume Vt, patient age, gender, and tumor location were explored. Results: The external/internal motions of liver and lung cancer patients were strongly correlated in the S-I direction, with mean SCCsvr values of 0.913 and 0.813. The correlation coefficients between the external/internal correlations and the patients' characteristics (Ai, Ae, Vt, and age) were all smaller than 0.5; Ai, Ae and liver tumor volumes were positively correlated with the strength of the external/internal correlation, while lung tumor volumes and patient age were negative. The external/internal correlations in males and females were roughly equal, and the external/internal correlations in patients with peripheral lung cancers were stronger than those in patients with central lung cancers. Conclusion: The external/internal correlation shows great individual differences. The effects of Ai, Ae, Vt, and age are weakly to moderately correlated. Our results suggest the necessity of individualized assessment of patient's external/internal motion correlation prior to the application of SGRT technique for breath motion monitoring.

CDC6 is a prognostic biomarker and correlated with immune infiltrates in glioma.

BACKGROUND: Cell division cycle 6 (CDC6) has been proven to be associated with the initiation and progression of human multiple tumors. However, it's role in glioma, which is ranked as one of the common primary malignant tumor in the central nervous system and is associated with high morbidity and mortality, is unclear. METHODS: In this study, we explored CDC6 gene expression level in pan-cancer. Furthermore, we focused on the relationships between CDC6 expression, its prognostic value, potential biological functions, and immune infiltrates in glioma patients. We also performed vitro experiments to assess the effect of CDC6 expression on proliferative, apoptotic, migrant and invasive abilities of glioma cells. RESULTS: As a result, CDC6 expression was upregulated in multiple types of cancer, including glioma. Moreover, high expression of CDC6 was significantly associated with age, IDH status, 1p/19q codeletion status, WHO grade and histological type in glioma (all p < 0.05). Meanwhile, high CDC6 expression was associated with poor overall survival (OS) in glioma patients, especially in different clinical subgroups. Furthermore, a univariate Cox analysis showed that high CDC6 expression was correlated with poor OS in glioma patients. Functional enrichment analysis indicated that CDC6 was mainly involved in pathways related to DNA transcription and cytokine activity, and Gene Set Enrichment Analysis (GSEA) revealed that MAPK pathway, P53 pathway and NF-κB pathway in cancer were differentially enriched in glioma patients with high CDC6 expression. Single-sample gene set enrichment analysis (ssGSEA) showed CDC6 expression in glioma was positively correlated with Th2 cells, Macrophages and Eosinophils, and negative correlations with plasmacytoid dendritic cells, CD8 T cells and NK CD56bright cells, suggesting its role in regulating tumor immunity. Finally, CCK8 assay, flow cytometry and transwell assays showed that silencing CDC6 could significantly inhibit proliferation, migration, invasion, and promoted apoptosis of U87 cells and U251 cells (p < 0.05). CONCLUSION: In conclusion, high CDC6 expression may serve as a promising biomarker for prognosis and correlated with immune infiltrates, presenting to be a potential immune therapy target in glioma.

Automated Segmentation of the Clinical Target Volume in the Planning CT for Breast Cancer Using Deep Neural Networks.

3-D radiotherapy is an effective treatment modality for breast cancer. In 3-D radiotherapy, delineation of the clinical target volume (CTV) is an essential step in the establishment of treatment plans. However, manual delineation is subjective and time consuming. In this study, we propose an automated segmentation model based on deep neural networks for the breast cancer CTV in planning computed tomography (CT). Our model is composed of three stages that work in a cascade manner, making it applicable to real-world scenarios. The first stage determines which slices contain CTVs, as not all CT slices include breast lesions. The second stage detects the region of the human body in an entire CT slice, eliminating boundary areas, which may have side effects for the segmentation of the CTV. The third stage delineates the CTV. To permit the network to focus on the breast mass in the slice, a novel dynamically strided convolution operation, which shows better performance than standard convolution, is proposed. To train and evaluate the model, a large dataset containing 455 cases and 50 425 CT slices is constructed. The proposed model achieves an average dice similarity coefficient (DSC) of 0.802 and 0.801 for right-0 and left-sided breast, respectively. Our method shows superior performance to that of previous state-of-the-art approaches.

[Automatic Delineation of Clinical Target Volume and Organ at Risk by Deep Learning for Prostate Cancer Adaptive Radiotherapy].

Adaptive radiotherapy can modify the treatment plan online based on the clinical target volume (CTV) and organ at risk (OAR) contours on the cone-beam CT (CBCT) before treatment, improving the accuracy of radiotherapy. However, manual delineation of CTV and OAR on CBCT is time-consuming. In this study, a deep neural network-based method based on U-Net was purposed. CBCT images and corresponding mask were used for model training and validation, showing superior performance in terms of the segmentation accuracy. The proposed method could be used in the clinic to support rapid CTV and OAR contouring for prostate adaptive radiotherapy.

A robust approach to establish tolerance limits for the gamma passing rate-based patient-specific quality assurance using the heuristic control charts.

PURPOSE: Establishing the tolerance limits of patient-specific quality assurance (PSQA) processes based on the gamma passing rate (GPR) by using normal statistical process control (SPC) methods involves certain problems. The aim of this study was threefold: (a) to show that the heuristic SPC method can replace the quantile method for establishing tolerance limits in PSQA processes and is more robust, (b) to introduce an iterative procedure of "Identify-Eliminate-Recalculate" for establishing the tolerance limits in PSQA processes with unknown states based on retrospective GPRs, and (c) to recommend a workflow to define tolerance limits based on actual clinical retrospective GPRs. MATERIALS AND METHODS: A total of 1671 volumetric-modulated arc therapy (VMAT) pretreatment plans were measured on four linear accelerators (linacs) and analyzed by treatment sites using the GPRs under the 2%/2 mm, 3%/2 mm, and 3%/3 mm criteria. Normality testing was performed using the Anderson-Darling (AD) statistic and the optimal distributions of GPRs were determined using the Fitter Python package. The iterative "Identify-Eliminate-Recalculate" procedure was used to identify the PSQA outliers. The tolerance limits of the initial PSQAs, remaining PSQAs after elimination, and in-control PSQAs after correction were calculated using the conventional Shewhart method, two transformation methods, three heuristic methods, and two quantile methods. The tolerance limits of PSQA processes with different states for the respective methods, linacs, and treatment sites were comprehensively compared and analyzed. RESULTS: It was found that 75% of the initial PSQA processes and 63% of the in-control processes were non-normal (AD test, p < 0.05). The optimal distributions of GPRs for the initial and in-control PSQAs varied with different linacs and treatment sites. In the implementation of the "Identify-Eliminate-Recalculate" procedure, the quantile methods could not identify the out-of-control PSQAs effectively due to the influence of outliers. The tolerance limits of the in-control PSQAs, calculated using the quantile of optimal fitting distributions, represented the ground truth. The tolerance limits of the in-control PSQAs and remaining PSQAs after elimination calculated using the heuristic methods were considerably close to the ground truth (the maximum average absolute deviations were 0.50 and 1.03%, respectively). Some transformation failures occurred under both transformation methods. For the in-control PSQAs at 3%/2 mm gamma criteria, the maximum differences in the tolerance limits for four linacs and different treatment sites were 3.10 and 5.02%, respectively. CONCLUSIONS: The GPR distributions of PSQA processes vary with different linacs and treatment sites but most are skewed. In applying SPC methodologies to PSQA processes, heuristic methods are robust. For in-control PSQA processes, the tolerance limits calculated by heuristic methods are in good agreement with the ground truth. For unknown PSQA processes, the tolerance limits calculated by the heuristic methods after the iterative "Identify-Eliminate-Recalculate" procedure are closest to the ground truth. Setting linac- and treatment site-specific tolerance limits for PSQA processes is necessary for clinical applications.

Analysis of EPID Transmission Fluence Maps Using Machine Learning Models and CNN for Identifying Position Errors in the Treatment of GO Patients.

PURPOSE: To find a suitable method for analyzing electronic portal imaging device (EPID) transmission fluence maps for the identification of position errors in the in vivo dose monitoring of patients with Graves' ophthalmopathy (GO). METHODS: Position errors combining 0-, 2-, and 4-mm errors in the left-right (LR), anterior-posterior (AP), and superior-inferior (SI) directions in the delivery of 40 GO patient radiotherapy plans to a human head phantom were simulated and EPID transmission fluence maps were acquired. Dose difference (DD) and structural similarity (SSIM) maps were calculated to quantify changes in the fluence maps. Three types of machine learning (ML) models that utilize radiomics features of the DD maps (ML 1 models), features of the SSIM maps (ML 2 models), and features of both DD and SSIM maps (ML 3 models) as inputs were used to perform three types of position error classification, namely a binary classification of the isocenter error (type 1), three binary classifications of LR, SI, and AP direction errors (type 2), and an eight-element classification of the combined LR, SI, and AP direction errors (type 3). Convolutional neural network (CNN) was also used to classify position errors using the DD and SSIM maps as input. RESULTS: The best-performing ML 1 model was XGBoost, which achieved accuracies of 0.889, 0.755, 0.778, 0.833, and 0.532 in the type 1, type 2-LR, type 2-AP, type 2-SI, and type 3 classification, respectively. The best ML 2 model was XGBoost, which achieved accuracies of 0.856, 0.731, 0.736, 0.949, and 0.491, respectively. The best ML 3 model was linear discriminant classifier (LDC), which achieved accuracies of 0.903, 0.792, 0.870, 0.931, and 0.671, respectively. The CNN achieved classification accuracies of 0.925, 0.833, 0.875, 0.949, and 0.689, respectively. CONCLUSION: ML models and CNN using combined DD and SSIM maps can analyze EPID transmission fluence maps to identify position errors in the treatment of GO patients. Further studies with large sample sizes are needed to improve the accuracy of CNN.

[Application of Virtual Monochromatic Images Reconstructed by Dual-energy Computed Tomography in Radiotherapy Treatment Planning System].

Virtual monochromatic images (VMI) that reconstructed on dual-energy computed tomography (DECT) have further application prospects in radiotherapy, and there is still a lack of clinical dose verification. In this study, GE Revolution CT scanner was used to perform conventional imaging and gemstone spectral imaging on the simulated head and body phantom. The CT images were imported to radiotherapy treatment planning system (TPS), and the same treatment plans were transplanted to compare the CT value and the dose distribution. The results show that the VMI can be imported into TPS for CT value-relative electron density conversion and dose calculation. Compared to conventional images, the VMI varies from 70 to 140 keV, has little difference in dose distribution of 6 MV photon treatment plan.

Clinically Oriented Target Contour Evaluation Using Geometric and Dosimetric Indices Based on Simple Geometric Transformations.

PURPOSE: In radiotherapy, geometric indices are often used to evaluate the accuracy of contouring. However, the ability of geometric indices to identify the error of contouring results is limited primarily because they do not consider the clinical background. The purpose of this study is to investigate the relationship between geometric and clinical dosimetric indices. METHODS: Four different types of targets were selected (C-shaped target, oropharyngeal cancer, metastatic spine cancer, and prostate cancer), and the translation, scaling, rotation, and sine function transformation were performed with the software Python to introduce systematic and random errors. The transformed contours were regarded as reference contours. Dosimetric indices were obtained from the original dose distribution of the radiotherapy plan. The correlations between geometric and dosimetric indices were quantified by linear regression. RESULTS: The correlations between the geometric and dosimetric indices were inconsistent. For systematic errors, and with the exception of the sine function transformation (R2: 0.023-0.04, P > 0.05), the geometric transformations of the C-shaped target were correlated with the D98% and Dmean (R2: 0.689-0.988), 80% of which were P < 0.001. For the random errors, the correlations obtained by the all targets were R2 > 0.384, P < 0.05. The Wilcoxon signed-rank test was used to compare the spatial direction resolution capability of geometric indices in different directions of the C-shaped target (with systematic errors), and the results showed only the volumetric geometric indices with P < 0.05. CONCLUSIONS: Clinically, an assessment of the contour accuracy of the region-of-interest is not feasible based on geometric indices alone. Dosimetric indices should be added to the evaluations of the accuracy of the delineation results, which can be helpful for explaining the clinical dose response relationship of delineation more comprehensively and accurately.

Radiomics analysis of EPID measurements for patient positioning error detection in thyroid associated ophthalmopathy radiotherapy.

PURPOSE: Electronic portal imaging detector (EPID)-based patient positioning verification is an important component of safe radiotherapy treatment delivery. In computer simulation studies, learning-based approaches have proven to be superior to conventional gamma analysis in the detection of positioning errors. To approximate a clinical scenario, the detectability of positioning errors via EPID measurements was assessed using radiomics analysis for patients with thyroid-associated ophthalmopathy. METHODS: Treatment plans of 40 patients with thyroid-associated ophthalmopathy were delivered to a solid anthropomorphic head phantom. To simulate positioning errors, combinations of 0-, 2-, and 4-mm translation errors in the left-right (LR), superior-inferior (SI), and anterior-posterior (AP) directions were introduced to the phantom. The positioning errors-induced dose differences between measured portal dose images were used to predict the magnitude and direction of positioning errors. The detectability of positioning errors was assessed via radiomics analysis of the dose differences. Three classification models-support vector machine (SVM), k-nearest neighbors (KNN), and XGBoost-were used for the detection of positioning errors (positioning errors larger or smaller than 3 mm in an arbitrary direction) and direction classification (positioning errors larger or smaller than 3 mm in a specific direction). The receiver operating characteristic curve and the area under the ROC curve (AUC) were used to evaluate the performance of classification models. RESULTS: For the detection of positioning errors, the AUC values of SVM, KNN, and XGBoost models were all above 0.90. For LR, SI, and AP direction classification, the highest AUC values were 0.76, 0.91, and 0.80, respectively. CONCLUSIONS: Combined radiomics and machine learning approaches are capable of detecting the magnitude and direction of positioning errors from EPID measurements. This study is a further step toward machine learning-based positioning error detection during treatment delivery with EPID measurements.