Improving Prediction of Complications Post-Proton Therapy in Lung Cancer Using Large Language Models and Meta-Analysis.

PURPOSE: This study enhances the efficiency of predicting complications in lung cancer patients receiving proton therapy by utilizing large language models (LLMs) and meta-analytical techniques for literature quality assessment. MATERIALS AND METHODS: We integrated systematic reviews with LLM evaluations, sourcing studies from Web of Science, PubMed, and Scopus, managed via EndNote X20. Inclusion and exclusion criteria ensured literature relevance. Techniques included meta-analysis, heterogeneity assessment using Cochran's Q test and I2 statistics, and subgroup analyses for different complications. Quality and bias risk were assessed using the PROBAST tool and further analyzed with models such as ChatGPT-4, Llama2-13b, and Llama3-8b. Evaluation metrics included AUC, accuracy, precision, recall, F1 score, and time efficiency (WPM). RESULTS: The meta-analysis revealed an overall effect size of 0.78 for model predictions, with high heterogeneity observed (I2 = 72.88%, P < 0.001). Subgroup analysis for radiation-induced esophagitis and pneumonitis revealed predictive effect sizes of 0.79 and 0.77, respectively, with a heterogeneity index (I2) of 0%, indicating that there were no significant differences among the models in predicting these specific complications. A literature assessment using LLMs demonstrated that ChatGPT-4 achieved the highest accuracy at 90%, significantly outperforming the Llama3 and Llama2 models, which had accuracies ranging from 44% to 62%. Additionally, LLM evaluations were conducted 3229 times faster than manual assessments were, markedly enhancing both efficiency and accuracy. The risk assessment results identified nine studies as high risk, three as low risk, and one as unknown, confirming the robustness of the ChatGPT-4 across various evaluation metrics. CONCLUSION: This study demonstrated that the integration of large language models with meta-analysis techniques can significantly increase the efficiency of literature evaluations and reduce the time required for assessments, confirming that there are no significant differences among models in predicting post proton therapy complications in lung cancer patients.

Using Advanced AI to Improve Predictions of Treatment Side Effects in Lung Cancer: This research uses cutting-edge artificial intelligence (AI) techniques, including large language models like ChatGPT-4, to better predict potential side effects in lung cancer patients undergoing proton therapy. By analyzing extensive scientific literature quickly and accurately, this approach has proven to enhance the evaluation process, making it faster and more reliable in foreseeing complications from treatments.

Utilizing radiomics and dosiomics with AI for precision prediction of radiation dermatitis in breast cancer patients.

PURPOSE: This study explores integrating clinical features with radiomic and dosiomic characteristics into AI models to enhance the prediction accuracy of radiation dermatitis (RD) in breast cancer patients undergoing volumetric modulated arc therapy (VMAT). MATERIALS AND METHODS: This study involved a retrospective analysis of 120 breast cancer patients treated with VMAT at Kaohsiung Veterans General Hospital from 2018 to 2023. Patient data included CT images, radiation doses, Dose-Volume Histogram (DVH) data, and clinical information. Using a Treatment Planning System (TPS), we segmented CT images into Regions of Interest (ROIs) to extract radiomic and dosiomic features, focusing on intensity, shape, texture, and dose distribution characteristics. Features significantly associated with the development of RD were identified using ANOVA and LASSO regression (p-value < 0.05). These features were then employed to train and evaluate Logistic Regression (LR) and Random Forest (RF) models, using tenfold cross-validation to ensure robust assessment of model efficacy. RESULTS: In this study, 102 out of 120 VMAT-treated breast cancer patients were included in the detailed analysis. Thirty-two percent of these patients developed Grade 2+ RD. Age and BMI were identified as significant clinical predictors. Through feature selection, we narrowed down the vast pool of radiomic and dosiomic data to 689 features, distributed across 10 feature subsets for model construction. In the LR model, the J subset, comprising DVH, Radiomics, and Dosiomics features, demonstrated the highest predictive performance with an AUC of 0.82. The RF model showed that subset I, which includes clinical, radiomic, and dosiomic features, achieved the best predictive accuracy with an AUC of 0.83. These results emphasize that integrating radiomic and dosiomic features significantly enhances the prediction of Grade 2+ RD. CONCLUSION: Integrating clinical, radiomic, and dosiomic characteristics into AI models significantly improves the prediction of Grade 2+ RD risk in breast cancer patients post-VMAT. The RF model analysis demonstrates that a comprehensive feature set maximizes predictive efficacy, marking a promising step towards utilizing AI in radiation therapy risk assessment and enhancing patient care outcomes.

A mini review of plan quality and secondary cancer risk in CyberKnife M6 radiosurgery for benign intracranial tumors.

With advancements in medical technology, stereotactic radiosurgery (SRS) has become an essential option for treating benign intracranial tumors. Due to its minimal side effects and high local control rate, SRS is widely applied. This paper evaluates the plan quality and secondary cancer risk (SCR) in patients with benign intracranial tumors treated with the CyberKnife M6 system. The CyberKnife M6 robotic radiosurgery system features both multileaf collimator (MLC) and IRIS variable aperture collimator systems, providing different treatment options. The study included 15 patients treated with the CyberKnife M6 system, examining the differences in plan quality and SCR between MLC and IRIS systems. Results showed that MLC and IRIS plans had equal PTV (planning target volume) coverage (98.57% vs. 98.75%). However, MLC plans demonstrated better dose falloff and conformity index (CI: 1.81 ± 0.26 vs. 1.92 ± 0.27, P = 0.025). SCR assessment indicated that MLC plans had lower cancer risk estimates, with IRIS plans having average LAR (lifetime attributable risk) and EAR (excess absolute risk) values approximately 25% higher for cancer induction and 15% higher for sarcoma induction compared to MLC plans. The study showed that increasing tumor volume increases SCR probability, but there was no significant difference between different plans in PTV and brainstem analyses.

Establishment and risk factor assessment of the abnormal body temperature probability prediction model (ABTP) for dairy cattle.

The study aims to develop an abnormal body temperature probability (ABTP) model for dairy cattle, utilizing environmental and physiological data. This model is designed to enhance the management of heat stress impacts, providing an early warning system for farm managers to improve dairy cattle welfare and farm productivity in response to climate change. The study employs the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm to analyze environmental and physiological data from 320 dairy cattle, identifying key factors influencing body temperature anomalies. This method supports the development of various models, including the Lyman Kutcher-Burman (LKB), Logistic, Schultheiss, and Poisson models, which are evaluated for their ability to predict abnormal body temperatures in dairy cattle effectively. The study successfully validated multiple models to predict abnormal body temperatures in dairy cattle, with a focus on the temperature-humidity index (THI) as a critical determinant. These models, including LKB, Logistic, Schultheiss, and Poisson, demonstrated high accuracy, as measured by the AUC and other performance metrics such as the Brier score and Hosmer-Lemeshow (HL) test. The results highlight the robustness of the models in capturing the nuances of heat stress impacts on dairy cattle. The research develops innovative models for managing heat stress in dairy cattle, effectively enhancing detection and intervention strategies. By integrating advanced technologies and novel predictive models, the study offers effective measures for early detection and management of abnormal body temperatures, improving cattle welfare and farm productivity in changing climatic conditions. This approach highlights the importance of using multiple models to accurately predict and address heat stress in livestock, making significant contributions to enhancing farm management practices.

Development of a risk prediction model for radiation dermatitis following proton radiotherapy in head and neck cancer using ensemble machine learning.

PURPOSE: This study aims to develop an ensemble machine learning-based (EML-based) risk prediction model for radiation dermatitis (RD) in patients with head and neck cancer undergoing proton radiotherapy, with the goal of achieving superior predictive performance compared to traditional models. MATERIALS AND METHODS: Data from 57 head and neck cancer patients treated with intensity-modulated proton therapy at Kaohsiung Chang Gung Memorial Hospital were analyzed. The study incorporated 11 clinical and 9 dosimetric parameters. Pearson's correlation was used to eliminate highly correlated variables, followed by feature selection via LASSO to focus on potential RD predictors. Model training involved traditional logistic regression (LR) and advanced ensemble methods such as Random Forest and XGBoost, which were optimized through hyperparameter tuning. RESULTS: Feature selection identified six key predictors, including smoking history and specific dosimetric parameters. Ensemble machine learning models, particularly XGBoost, demonstrated superior performance, achieving the highest AUC of 0.890. Feature importance was assessed using SHAP (SHapley Additive exPlanations) values, which underscored the relevance of various clinical and dosimetric factors in predicting RD. CONCLUSION: The study confirms that EML methods, especially XGBoost with its boosting algorithm, provide superior predictive accuracy, enhanced feature selection, and improved data handling compared to traditional LR. While LR offers greater interpretability, the precision and broader applicability of EML make it more suitable for complex medical prediction tasks, such as predicting radiation dermatitis. Given these advantages, EML is highly recommended for further research and application in clinical settings.

Using meta-analysis and CNN-NLP to review and classify the medical literature for normal tissue complication probability in head and neck cancer.

PURPOSE: The study aims to enhance the efficiency and accuracy of literature reviews on normal tissue complication probability (NTCP) in head and neck cancer patients using radiation therapy. It employs meta-analysis (MA) and natural language processing (NLP). MATERIAL AND METHODS: The study consists of two parts. First, it employs MA to assess NTCP models for xerostomia, dysphagia, and mucositis after radiation therapy, using Python 3.10.5 for statistical analysis. Second, it integrates NLP with convolutional neural networks (CNN) to optimize literature search, reducing 3256 articles to 12. CNN settings include a batch size of 50, 50-200 epoch range and a 0.001 learning rate. RESULTS: The study's CNN-NLP model achieved a notable accuracy of 0.94 after 200 epochs with Adamax optimization. MA showed an AUC of 0.67 for early-effect xerostomia and 0.74 for late-effect, indicating moderate to high predictive accuracy but with high variability across studies. Initial CNN accuracy of 66.70% improved to 94.87% post-tuning by optimizer and hyperparameters. CONCLUSION: The study successfully merges MA and NLP, confirming high predictive accuracy for specific model-feature combinations. It introduces a time-based metric, words per minute (WPM), for efficiency and highlights the utility of MA and NLP in clinical research.

An investigation into the impact of volumetric rescanning and fractionation treatment on dose homogeneity in liver cancer proton therapy.

The Pencil Beam Scanning (PBS) technique in modern particle therapy offers a highly conformal dose distribution but poses challenges due to the interplay effect, an interaction between respiration-induced organ movement and PBS. This study evaluates the effectiveness of different volumetric rescanning strategies in mitigating this effect in liver cancer proton therapy. We used a Geant4-based Monte Carlo simulation toolkit, 'TOPAS,' and an image registration toolbox, 'Elastix,' to calculate 4D dose distributions from 5 patients' four-dimensional computed tomography (4DCT). We analyzed the homogeneity index (HI) value of the Clinical Tumor Volume (CTV) at different rescan numbers and treatment times. Our results indicate that dose homogeneity stabilizes at a low point after a week of treatment, implying that both rescanning and fractionation treatments help mitigate the interplay effect. Notably, an increase in the number of rescans doesn't significantly reduce the mean dose to normal tissue but effectively prevents high localized doses to tissue adjacent to the CTV. Rescanning techniques, based on statistical averaging, require no extra equipment or patient cooperation, making them widely accessible. However, the number of rescans, tumor location, diaphragm movement, and treatment fractionation significantly influence their effectiveness. Therefore, deciding the number of rescans should involve considering the number of beams, treatment fraction size, and total delivery time to avoid unnecessary treatment extension without significant clinical benefits. The results showed that 2-3 rescans are more clinically suitable for liver cancer patients undergoing proton therapy.

Using machine learning algorithm to analyse the hypothyroidism complications caused by radiotherapy in patients with head and neck cancer.

Machine learning algorithms were used to analyze the odds and predictors of complications of thyroid damage after radiation therapy in patients with head and neck cancer. This study used decision tree (DT), random forest (RF), and support vector machine (SVM) algorithms to evaluate predictors for the data of 137 head and neck cancer patients. Candidate factors included gender, age, thyroid volume, minimum dose, average dose, maximum dose, number of treatments, and relative volume of the organ receiving X dose (X: 10, 20, 30, 40, 50, 60 Gy). The algorithm was optimized according to these factors and tenfold cross-validation to analyze the state of thyroid damage and select the predictors of thyroid dysfunction. The importance of the predictors identified by the three machine learning algorithms was ranked: the top five predictors were age, thyroid volume, average dose, V50 and V60. Of these, age and volume were negatively correlated with thyroid damage, indicating that the greater the age and thyroid volume, the lower the risk of thyroid damage; the average dose, V50 and V60 were positively correlated with thyroid damage, indicating that the larger the average dose, V50 and V60, the higher the risk of thyroid damage. The RF algorithm was most accurate in predicting the probability of thyroid damage among the three algorithms optimized using the above factors. The Area under the receiver operating characteristic curve (AUC) was 0.827 and the accuracy (ACC) was 0.824. This study found that five predictors (age, thyroid volume, mean dose, V50 and V60) are important factors affecting the chance that patients with head and neck cancer who received radiation therapy will develop hypothyroidism. Using these factors as the prediction basis of the algorithm and using RF to predict the occurrence of hypothyroidism had the highest ACC, which was 82.4%. This algorithm is quite helpful in predicting the probability of radiotherapy complications. It also provides references for assisting medical decision-making in the future.

Application of artificial intelligence in endoscopic image analysis for the diagnosis of a gastric cancer pathogen-Helicobacter pylori infection.

Helicobacter pylori (H. pylori) infection is the principal cause of chronic gastritis, gastric ulcers, duodenal ulcers, and gastric cancer. In clinical practice, diagnosis of H. pylori infection by a gastroenterologists' impression of endoscopic images is inaccurate and cannot be used for the management of gastrointestinal diseases. The aim of this study was to develop an artificial intelligence classification system for the diagnosis of H. pylori infection by pre-processing endoscopic images and machine learning methods. Endoscopic images of the gastric body and antrum from 302 patients receiving endoscopy with confirmation of H. pylori status by a rapid urease test at An Nan Hospital were obtained for the derivation and validation of an artificial intelligence classification system. The H. pylori status was interpreted as positive or negative by Convolutional Neural Network (CNN) and Concurrent Spatial and Channel Squeeze and Excitation (scSE) network, combined with different classification models for deep learning of gastric images. The comprehensive assessment for H. pylori status by scSE-CatBoost classification models for both body and antrum images from same patients achieved an accuracy of 0.90, sensitivity of 1.00, specificity of 0.81, positive predictive value of 0.82, negative predicted value of 1.00, and area under the curve of 0.88. The data suggest that an artificial intelligence classification model using scSE-CatBoost deep learning for gastric endoscopic images can distinguish H. pylori status with good performance and is useful for the survey or diagnosis of H. pylori infection in clinical practice.

Dosimetric Parameters Related to Acute Radiation Dermatitis of Patients with Nasopharyngeal Carcinoma Treated by Intensity-Modulated Proton Therapy.

Background: Growing patients with nasopharyngeal carcinoma (NPC) were treated with intensity-modulated proton therapy (IMPT). However, a high probability of severe acute radiation dermatitis (ARD) was observed. The objective of the study is to investigate the dosimetric parameters related to ARD for NPC patients treated with IMPT. Methods: Sixty-two patients with newly diagnosed NPC were analyzed. The ARD was recorded based on the criteria of Common Terminology Criteria for Adverse Events version 4.0. Logistic regression model was performed to identify the clinical and dosimetric parameters related to ARD. Receiver operating characteristic (ROC) curve analysis and the area under the curve (AUC) were used to evaluate the performance of the models. Results: The maximum ARD grade was 1, 2, and 3 in 27 (43.5%), 26 (42.0%), and 9 (14.5%) of the patients, respectively. Statistically significant differences (p < 0.01) in average volume to skin 5 mm with the respective doses were observed in the range 54−62 Cobalt Gray Equivalent (CGE) for grade 2 and 3 versus grade 1 ARD. Smoking habit and N2-N3 status were identified as significant predictors to develop grade 2 and 3 ARD in clinical model, and V58CGE to skin 5 mm as an independent predictor in dosimetric model. After adding the variable of V58CGE to the metric incorporating two parameters of smoking habit and N status, the AUC value of the metric increases from 0.78 (0.66−0.90) to 0.82 (0.72−0.93). The most appropriate cut-off value of V58CGE to skin 5 mm as determined by ROC curve was 5.0 cm3, with a predicted probability of 54% to develop grade 2 and 3 ARD. Conclusion: The dosimetric parameter of V58CGE to skin 5 mm < 5.0 cm3 could be used as a constraint in treatment planning for NPC patients treated by IMPT.

Development of Joint Activity Angle Measurement and Cloud Data Storage System.

In this study, we developed a range of motion sensing system (ROMSS) to simulate the function of the elbow joint, with errors less than 0.76 degrees and 0.87 degrees in static and dynamic verification by the swinging and angle recognition modules, respectively. In the simulation process, the É£ correlation coefficient of the Pearson difference between the ROMSS and the universal goniometer was 0.90, the standard deviations of the general goniometer measurements were between ±2 degrees and ±2.6 degrees, and the standard deviations between the ROMSS measurements were between ±0.5 degrees and ±1.6 degrees. With the ROMSS, a cloud database was also established; the data measured by the sensor could be uploaded to the cloud database in real-time to provide timely patient information for healthcare professionals. We also developed a mobile app for smartphones to enable patients and healthcare providers to easily trace the data in real-time. Historical data sets with joint activity angles could be retrieved to observe the progress or effectiveness of disease recovery so the quality of care could be properly assessed and maintained.

Using deep learning models to analyze the cerebral edema complication caused by radiotherapy in patients with intracranial tumor.

Using deep learning models to analyze patients with intracranial tumors, to study the image segmentation and standard results by clinical depiction complications of cerebral edema after receiving radiotherapy. In this study, patients with intracranial tumors receiving computer knife (CyberKnife M6) stereotactic radiosurgery were followed using the treatment planning system (MultiPlan 5.1.3) to obtain before-treatment and four-month follow-up images of patients. The TensorFlow platform was used as the core architecture for training neural networks. Supervised learning was used to build labels for the cerebral edema dataset by using Mask region-based convolutional neural networks (R-CNN), and region growing algorithms. The three evaluation coefficients DICE, Jaccard (intersection over union, IoU), and volumetric overlap error (VOE) were used to analyze and calculate the algorithms in the image collection for cerebral edema image segmentation and the standard as described by the oncologists. When DICE and IoU indices were 1, and the VOE index was 0, the results were identical to those described by the clinician.The study found using the Mask R-CNN model in the segmentation of cerebral edema, the DICE index was 0.88, the IoU index was 0.79, and the VOE index was 2.0. The DICE, IoU, and VOE indices using region growing were 0.77, 0.64, and 3.2, respectively. Using the evaluated index, the Mask R-CNN model had the best segmentation effect. This method can be implemented in the clinical workflow in the future to achieve good complication segmentation and provide clinical evaluation and guidance suggestions.

Quality of Life as a Mediator between Cancer Stage and Long-Term Mortality in Nasopharyngeal Cancer Patients Treated with Intensity-Modulated Radiotherapy.

BACKGROUND: Quality of life (QoL) attained before, during, or after treatments is recognized as a vital factor associated with therapeutic benefits in cancer patients. This nasopharyngeal cancer (NPC) patient longitudinal study assessed the relationship among QoL, cancer stage, and long-term mortality in patients with nasopharyngeal carcinoma (NPC) treated with intensity-modulated radiotherapy (IMRT). PATIENTS AND METHODS: The European Organization for Research and Treatment of Cancer (EORTC) core QoL questionnaire (QLQ-C30) and the head and neck cancer-specific QoL questionnaire module (QLQ-HN35) were employed to evaluate four-dimensional QoL outcomes at five time points: pre- (n = 682), during (around 40 Gy) (n = 675), 3 months (n = 640), 1 year (n = 578) and 2 years post-IMRT (n = 505), respectively, for 682 newly diagnosed NPC patients treated between 2003 and 2017 at a single institute. The median followed-up time was 7.5 years, ranging from 0.3 to 16.1 years. Generalized estimating equations, multivariable proportional hazards models, and Baron and Kenny's method were used to assess the investigated effects. RESULTS: Advanced AJCC stage (III-IV) patients revealed a 2.26-fold (95% CI-1.56 to 3.27) higher covariate-adjusted mortality risk than early-stage (I-II) patients. Compared with during IMRT, advanced-stage patients had a significantly low global health QoL and a significantly high QoL-HN35 symptom by a large magnitude at pre-, 3 months, and 2 years post-IMRT. QoL scales at pre-IMRT, 1 year, and 2 years post-IMRT were significantly associated with mortality. The effect changes of mortality risk explained by global health QoL, QoL-C30, and QoL-HN35 symptom were 5.8-9.8% at pre-IMRT but at 2 years post-IMRT were 39.4-49.4% by global health QoL and QoL-HN35 symptoms. CONCLUSIONS: We concluded advanced cancer stage correlates with a long-term high mortality in NPC patients treated with IMRT and the association is partially intermediated by QoL at pre-IMRT and 2 years post-IMRT. Therefore, QoL-HN35 symptom and global health QoL-dependent medical support and care should be focused and tailored at 2 years post-IMRT.

Pre-screening for osteoporosis with calcaneus quantitative ultrasound and dual-energy X-ray absorptiometry bone density.

Calcaneal quantitative ultrasonography (QUS) is a useful prescreening tool for osteoporosis, while the dual-energy X-ray absorptiometry (DXA) is the mainstream in clinical practice. We evaluated the correlation between QUS and DXA in a Taiwanese population. A total of 772 patients were enrolled and demographic data were recorded with the QUS and DXA T-score over the hip and spine. The correlation coefficient of QUS with the DXA-hip was 0.171. For DXA-spine, it was 0.135 overall, 0.237 in females, and 0.255 in males. The logistic regression model using DXA-spine as a dependent variable was established, and the classification table showed 66.2% accuracy. A receiver operating characteristic (ROC) analyses with Youden's Index revealed the optimal cut-off point of QUS for predicting osteoporosis to be 2.72. This study showed a meaningful correlation between QUS and DXA in a Taiwanese population. Thus, it is important to pre-screen for osteoporosis with calcaneus QUS.

Outcomes of patients with nasopharyngeal carcinoma treated with intensity-modulated radiotherapy.

Nasopharyngeal cancer shows a good response to intensity-modulated radiotherapy. However, there is no clear evidence for the benefits of routine use of image-guided radiotherapy. The purpose of this study was to perform a retrospective investigation of the treatment outcomes, treatment-related complications and prognostic factors for nasopharyngeal cancer treated with intensity-modulated radiotherapy and image-guided radiotherapy techniques. Retrospective analysis was performed on 326 consecutive nasopharyngeal cancer patients treated between 2004 and 2015. Potentially significant patient-related and treatment-related variables were analyzed. Radiation-related complications were recorded. The 5-year overall survival and disease-free survival rates of these patients were 77.9% and 70.5%, respectively. Age, AJCC (American Joint Committee on Cancer) stage, retropharyngeal lymphadenopathy, treatment interruption and body mass index were independent prognostic factors for overall survival. Age, AJCC stage, retropharyngeal lymphadenopathy, image-guided radiotherapy and body mass index were independent prognostic factors for disease-free survival. In conclusion, intensity-modulated radiotherapy significantly improves the treatment outcomes of nasopharyngeal cancer. With the aid of image-guided radiotherapy, the advantage of intensity-modulated radiotherapy might be further amplified.

Calibration of the EBT3 Gafchromic Film Using HNN Deep Learning.

To achieve a dose distribution conformal to the target volume while sparing normal tissues, intensity modulation with steep dose gradient is used for treatment planning. To successfully deliver such treatment, high spatial and dosimetric accuracy are crucial and need to be verified. With high 2D dosimetry resolution and a self-development property, the Ashland Inc. product EBT3 Gafchromic film is a widely used quality assurance tool designed especially for this. However, the film should be recalibrated each quarter due to the "aging effect," and calibration uncertainties always exist between individual films even in the same lot. Recently, artificial neural networks (ANN) are applied to many fields. If a physicist can collect the calibration data, it could be accumulated to be a substantial ANN data input used for film calibration. We therefore use the Keras functional Application Program Interface to build a hierarchical neural network (HNN), with the inputs of net optical densities, pixel values, and inverse transmittances to reveal the delivered dose and train the neural network with deep learning. For comparison, the film dose calculated using red-channel net optical density with power function fitting was performed and taken as a conventional method. The results show that the percentage error of the film dose using the HNN method is less than 4% for the aging effect verification test and less than 4.5% for the intralot variation test; in contrast, the conventional method could yield errors higher than 10% and 7%, respectively. This HNN method to calibrate the EBT film could be further improved by adding training data or adjusting the HNN structure. The model could help physicists spend less calibration time and reduce film usage.

Radiation-Induced Secondary Cancer Risk Assessment in Patients With Lung Cancer After Stereotactic Body Radiotherapy Using the CyberKnife M6 System With Lung-Optimized Treatment.

BACKGROUND: To evaluate the lifetime secondary cancer risk (SCR) of stereotactic body radiotherapy (SBRT) using the CyberKnife (CK) M6 system with a lung-optimized treatment (LOT) module for lung cancer patients. METHODS: We retrospectively enrolled 11 lung cancer patients curatively treated with SBRT using the CK M6 robotic radiosurgery system. The planning treatment volume (PTV) and common organs at risk (OARs) for SCR analysis included the spinal cord, total lung, and healthy normal lung tissue (total lung volume - PTV). Schneider's full model was used to calculate SCR according to the concept of organ equivalent dose (OED). RESULTS: CK-LOT-SBRT delivers precisely targeted radiation doses to lung cancers and achieves good PTV coverage and conformal dose distribution, thus posing limited SCR to surrounding tissues. The three OARs had similar risk equivalent dose (RED) values among four different models. However, for the PTV, differences in RED values were observed among the models. The cumulative excess absolute risk (EAR) value for the normal lung, spinal cord, and PTV was 70.47 (per 10,000 person-years). Schneider's Lnt model seemed to overestimate the EAR/lifetime attributable risk (LAR). CONCLUSION: For lung cancer patients treated with CK-LOT optimized with the Monte Carlo algorithm, the SCR might be lower. Younger patients had a greater SCR, although the dose-response relationship seemed be non-linear for the investigated organs, especially with respect to the PTV. Despite the etiological association, the SCR after CK-LOT-SBRT for carcinoma and sarcoma, is low, but not equal to zero. Further research is required to understand and to show the lung SBRT SCR comparisons and differences across different modalities with motion management strategies.

Comparison of Intrafractional Motion in Head and Neck Cancer Between Two Immobilization Methods During Stereotactic Ablative Radiation Therapy by CyberKnife.

PURPOSE: Maintaining immobilization to minimize spine motion is very important during salvage stereotactic ablative radiation therapy (SABR) for recurrent head and neck cancer. This study aimed to compare the intrafractional motion between two immobilization methods. PATIENTS AND METHODS: With a spine tracking system for image guiding, 9094 records from 41 patients receiving SABR by CyberKnife were obtained for retrospective comparison. Twenty-one patients were immobilized with a thermoplastic mask and headrest (Group A), and another 20 patients used a thermoplastic mask and headrest together with a vacuum bag to support the head and neck area (Group B). The intrafractional motion in the X (superior-inferior), Y (right-left), Z (anterior-posterior) axes, 3D (three-dimensional) vector, Roll, Pitch and Yaw in the two groups was compared. The margins of the planning target volume (PTV) to cover 95% intrafractional motion were evaluated. RESULTS: The translational movements in the X-axis, Y-axis, and 3D vector in Group A were significantly smaller than in Group B. The rotational errors in the Roll and Yaw in Group A were also significantly smaller than those in Group B; conversely, those in the Pitch in Group A were larger. To cover 95% intrafractional motion, margins of 0.96, 1.55, and 1.51 mm in the X, Y and Z axes, respectively were needed in Group A, and 1.06, 2.86, and 1.34 mm, respectively were required in Group B. CONCLUSION: The immobilization method of thermoplastic mask and head rest with vacuum bag did not provide better immobilization than that without vacuum bag in most axes. The clinical use of 2 mm as a margin of PTV to cover 95% intrafractional motion was adequate in Group A but not in Group B.

Developing a multivariable normal tissue complication probability model to predict late rectal bleeding following intensity-modulated radiation therapy.

Purpose: To develop a multivariable normal tissue complication probability (NTCP) model to predict moderate to severe late rectal bleeding following intensity-modulated radiation therapy (IMRT). Methods and materials: Sixty-eight patients with localized prostate cancer treated by IMRT from 2008 to 2011 were enrolled. The median follow-up time was 56 months. According to the criteria of D'Amico risk classifications, there were 9, 20 and 39 patients in low, intermediate and high-risk groups, respectively. Forty-two patients were combined with androgen deprivation therapy. Fifteen patients had suffered from grade 2 or more (grade 2+) late rectal bleeding. The numbers of predictors for a multivariable logistic regression NTCP model were determined by the least absolute shrinkage and selection operator (LASSO). Results: The most important predictors for late rectal bleeding ranked by LASSO were platelet count, risk group and the relative volume of rectum receiving at least 65 Gy (V65). The NTCP model of grade 2+ rectal bleeding was as follows: S = -17.49 + Platelets (1000/µL) * (-0.025) + Risk group * Corresponding coefficient (low-risk group = 0; intermediate-risk group = 19.07; high-risk group = 20.41) + V65 * 0.045. Conclusions: A LASSO-based multivariable NTCP model comprising three important predictors (platelet count, risk group and V65) was established to predict the incidence of grade 2+ late rectal bleeding after IMRT.

Plan Quality and Secondary Cancer Risk Assessment in Patients with Benign Intracranial Lesions after Radiosurgery using the CyberKnife M6 Robotic Radiosurgery System.

This study was performed to examine the quality of planning and treatment modality using a CyberKnife (CK) robotic radiosurgery system with multileaf collimator (MLC)-based plans and IRIS (variable aperture collimator system)-based plans in relation to the dose-response of secondary cancer risk (SCR) in patients with benign intracranial tumors. The study population consisted of 15 patients with benign intracranial lesions after curative treatment using a CyberKnife M6 robotic radiosurgery system. Each patient had a single tumor with a median volume of 6.43 cm3 (range, 0.33-29.72 cm3). The IRIS-based plan quality and MLC-based plan quality were evaluated by comparing the dosimetric indices, taking into account the planning target volume (PTV) coverage, the conformity index (CI), and the dose gradient (R10% and R50%). The dose-response SCR with sarcoma/carcinoma induction was calculated using the concept of the organ equivalent dose (OED). Analyses of sarcoma/carcinoma induction were performed using excess absolute risk (EAR) and various OED models of dose-response type/lifetime attributable risk (LAR). Moreover, analyses were performed using the BEIR VII model. PTV coverage using both IRIS-based plans and MLC-based plans was identical, although the CI values obtained using the MLC-based plans showed greater statistical significance. In comparison with the IRIS-based plans, the MLC-based plans showed better dose falloff for R10% and R50% evaluation. The estimated difference between Schneider's model and BEIR VII in linear-no-threshold (Lnt) cumulative EAR was about twofold. The average values of LAR/EAR for carcinoma, for the IRIS-based plans, were 25% higher than those for the MLC-based plans using four SCR models; for sarcoma, they were 15% better in Schneider's SCR models. MLC-based plans showed slightly better conformity, dose gradients, and SCR reduction. There was a slight increase in SCR with IRIS-based plans in comparison with MLC-based plans. EAR analyses did not show any significant difference between PTV and brainstem analyses, regardless of the tumor volume. Nevertheless, an increase in target volume led to an increase in the probability of SCR. EAR showed statistically significant differences in the soft tissue according to tumor volume (1-10 cc and ≥10 cc).