Background: Current multi-leaf collimator (MLC) quality assurance (QA) methods utilizing the picket fence (PF) test are susceptible to the influence of beam radiation scattering between strips, which could potentially lead to inaccurate analysis results. Purpose: This study intended to quantify the impact of stripe beam radiation scattering on algorithm parameters and partially removed it. Subsequently, MLC QA integration methods with high accuracy were proposed by incorporating log files. Methods: A series of electronic portal imaging devices (EPIDs) PF test templates were designed in this study to quantify the influence of beam radiation scattering between strips on three algorithmic parameters (full-width half-maximum (FWHM), peak height, and peak area) by varying the strip width (range: 7-13 mm, increment: 1 mm) and spacing (range: 10-20 mm, increment: 2 mm), and this effect was partially removed by creating a scattering library. Subsequently, three MLC QA algorithms (FWHM method, peak height method, and peak area method) were developed according to specific algorithm parameters by combining log files. To enhance the accuracy and robustness of algorithms, the voting integration method and fitting integration method were proposed by integrating three algorithms using voting and linear fitting, respectively. Additionally, this work also analyzed the impact of different algorithm data processing ways and strip spacing on position accuracy of the developed algorithms to seek the optimal algorithm development pattern. Results: An increase in both FWHM and peak area was observed for different-width stripes at all positions in the PF test images as the stripe spacing increased, while peak height exhibited the opposite trend. The FWHM and peak height gradually decreased from the central strip to the two side strips of the PF test images with a fixed strip spacing. Except for the stripes at both edges, the peak area of the others remained nearly unchanged. The highest algorithmic positional accuracy was achieved by performing independent algorithm development for the algorithm parameter for each opposite leaf in every strip. The overall absolute position error of the algorithms was relatively constant (0.155 f 0.168 mm) when the strip spacing was not less than 16 mm, and the absolute position errors of each algorithm was 0.294 f 0.213 mm (peak height method), 0.100 f 0.086 mm (peak area method), 0.071 f 0.054 mm (FWHM method), 0.064 f 0.066 mm (VIM), and 0.036 f 0.036 mm (FIM). Conclusions: The influence of beam radiation scattering between strips in PF test images on algorithm parameters cannot be ignored. The two MLC QA integration methods proposed in this study proved to be effective. The positional accuracy of the algorithms remained relatively stable when the strip spacing exceeded a specific threshold and was largely unaffected by variations in strip position or spacing.

BACKGROUND AND OBJECTIVES:Hematologic toxicity (HT) is a common and serious side effect for advanced cervical cancer patients undergoing chemoradiotherapy. Accurately predicting HT can significantly improve patient management and treatment outcomes. This study aims to develop and evaluate interpretable machine learning models that use radiomic and dosimetric features to predict HT in advanced cervical cancer patients. METHODS AND MATERIALS:Retrospectively collected general clinical data, planning CT images, and dose files from 205 patients with advanced cervical cancer who underwent chemoradiotherapy, and classified them according to the severity of HT. Radiomics and dosiomics features were extracted from the same region of interest, and feature selection was performed using a random forest algorithm. Radiomics models, dosiomics models, and hybrid models were then constructed based on extreme gradient boosting trees. Sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC) were calculated to evaluate the classification performance of the models. Finally, SHAP values were used to perform interpretability analysis on the best model to enhance the transparency and practicality of the model. RESULTS:The sensitivity, specificity, and AUC values for the radiomics model were 0.42, 0.86, and 0.78, respectively, while those for the dosiomics model were 0.50, 0.90, and 0.74. In contrast, the hybrid model exhibited superior classification performance with sensitivity, specificity, and AUC values of 0.50, 0.83, and 0.83, respectively. Compared to the standalone radiomics and dosiomics models, the hybrid model demonstrated enhanced classification capability. Interpretability analysis based on SHAP values not only provided a ranking of feature importance and the distribution of feature impacts on model outputs but also elucidated the specific decision-making processes influenced by these features and the interactions between them. This enables clinicians to gain a more intuitive understanding of the model's decisions. CONCLUSIONS:For patients with advanced cervical cancer undergoing chemoradiotherapy, the integration of radiomics and dosiomics features can significantly enhance the classification performance of predictive models, thereby holding considerable potential for refining patient treatment strategies. Interpretability analysis based on SHAP values can aid clinicians in more readily understanding the model's decisions, thus promoting the effective implementation of the model in clinical practice.

Backgroud and objectivesThe implementation of patient-specific quality assurance (PSQA) has become a crucial aspect of the radiation therapy process. Machine learning models have demonstrated their potential as virtual QA tools, accurately predicting the gamma passing rate (GPR) of volumetric modulated arc therapy (VMAT)plans, thereby ensuring safe and efficient treatment for patients. However, there is limited multi-center research dedicated to predicting the GPR. In this study, a dosiomics-based machine learning approach was employed to construct a prediction model for classifying GPR in multiple radiotherapy institutions. Additionally, the model’s performance was compared by evaluating the impact of two distinct feature selection methods.MethodsA retrospective data collection was conducted on 572 VMAT patients across three radiotherapy institutions. Utilizing a three-dimensional dose verification technique grounded in real-time measurements, γ analysis was conducted according to the criteria of 3%/2 mm and 2%/2 mm, employing a dose threshold of 10% along with absolute dose and global normalization mode. Dosiomics features were extracted from the dose files, and distinct subsets of features were selected as inputs for the model using the random forest (RF) and RF combined with SHapley Additive exPlanations (SHAP) methods. The data underwent training using the extreme gradient boosting (XGBoost) algorithm, and the model’s classification performance was assessed through F1-score and area under the curve (AUC) values.ResultsThe model exhibited optimal performance under the 3%/2 mm criteria, utilizing a subset of 20 features and attaining an AUC value of 0.88 and an F1-score of 0.89. Similarly, under the 2%/2 mm criteria, the model demonstrated superior performance with a subset of 10 features, resulting in an AUC value of 0.91 and an F1-score of 0.89. The feature selection methods of RF and RF + SHAP have achieved good model performance by selecting as few features as possible.ConclusionBased on the multi-center PSQA results, it is possible to utilize dosiomics features extracted from dose files to construct a machine learning predictive model. This model demonstrates excellent discriminative abilities, thus promoting the progress of gamma passing rate prognostic models in clinical application and implementation. Furthermore, it holds potential in providing patients with secure and efficient personalized QA management, while also reducing the workload of medical physicists.

Objective:To explore the feasibility of a classification prediction model for gamma pass rates (GPRs) under different intensity-modulated radiation therapy techniques for pelvic tumors using a radiomics-based machine learning approach, and compare the classification performance of four integrated tree models.Methods:With a retrospective collection of 409 plans using different IMRT techniques, the three-dimensional dose validation results were adopted based on modality measurements, with a GPR criterion of 3%/2 mm and 10% dose threshold. Then prediction were built models by extracting radiomics features based on dose documentation. Four machine learning algorithms were used, namely random forest (RF), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM). Their classification performance was evaluated by calculating sensitivity, specificity, F1 score, and AUC value. Results:The RF, AdaBoost, XGBoost, and LightGBM models had sensitivities of 0.96, 0.82, 0.93, and 0.89, specificities of 0.38, 0.54, 0.62, and 0.62, F1 scores of 0.86, 0.81, 0.88, and 0.86, and AUC values of 0.81, 0.77, 0.85, and 0.83, respectively. XGBoost model showed the highest sensitivity, specificity, F1 score, and AUC value, outperforming the other three models. Conclusions:To build a GPR classification prediction model using a radiomics-based machine learning approach is feasible for plans using different intensity-modulated radiotherapy techniques for pelvic tumors, providing a basis for future multi-institutional collaborative research on GPR prediction.

Objective:To explore the feasibility and validity of constructing an intensity-modulated radiotherapy gamma pass rate prediction model after combining the SHAP values with the extreme gradient boosting tree (XGBoost) algorithm feature selection technique, and to deliver corresponding model interpretation.Methods:The dose validation results of 196 patients with pelvic tumors receiving fixed-field intensity-modulated radiotherapy using modality-based measurements with a gamma pass rate criterion of 3%/2 mm and 10% dose threshold in Hunan Provincial Tumor Hospital from November 2020 to November 2021 were retrospectively analyzed. Prediction models were constructed by extracting radiomic features based on dose files and using SHAP values combined with the XGBoost algorithm for feature filtering. Four machine learning classification models were constructed when the number of features was 50, 80, 110 and 140, respectively. The area under the receiver operating characteristic curve (AUC), recall rate and F1 score were calculated to assess the classification performance of the prediction models.Results:The AUC of prediction model constructed with 110 features selected based on the SHAP-valued features was 0.81, the recall rate was 0.93 and the F1 score was 0.82, which were all better than the other 3 models.Conclusion:For intensity-modulated radiotherapy of pelvic tumor, SHAP values can be used in combination with the XGBoost algorithm to select the optimal subset of radiomic features to construct predictive models of gamma pass rates, and deliver an interpretation of the model output by SHAP values, which may provide value in understanding the prediction by machine learning-dependent models.

Background and objectives: Implementation of patient-specific quality assurance (PSQA) is a crucial aspect of precise radiotherapy. Various machine learning-based models have showed potential as virtual quality assurance tools, being capable of accurately predicting the dose verification results of fixed-beam intensity-modulated radiation therapy (IMRT) or volumetric modulated arc therapy (VMAT) plans, thereby ensuring safe and efficient treatment for patients. However, there has been no research yet that simultaneously integrates different IMRT techniques to predict the gamma pass rate (GPR) and explain the model.Methods: Retrospective analysis of the 3D dosimetric verification results based on measurements with gamma pass rate criteria of 3%/2 mm and 10% dose threshold of 409 pelvic IMRT and VMAT plans was carried out. Radiomics features were extracted from the dose files, from which the XGBoost algorithm based on SHapley Additive exPlanations (SHAP) values was used to select the optimal feature subset as the input for the prediction model. The study employed four different machine learning algorithms, namely, random forest (RF), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM), to construct predictive models. Sensitivity, specificity, F1 score, and AUC value were calculated to evaluate the classification performance of these models. The SHAP values were utilized to perform a related interpretive analysis on the best performing model.Results: The sensitivities and specificities of the RF, AdaBoost, XGBoost, and LightGBM models were 0.96, 0.82, 0.93, and 0.89, and 0.38, 0.54, 0.62, and 0.62, respectively. The F1 scores and area under the curve (AUC) values were 0.86, 0.81, 0.88, and 0.86, and 0.81, 0.77, 0.85, and 0.83, respectively. The explanation of the model output based on SHAP values can provide a reference basis for medical physicists when adjusting the plan, thereby improving the efficiency and quality of treatment plans.Conclusion: It is feasible to use a machine learning method based on radiomics to establish a gamma pass rate classification prediction model for IMRT and VMAT plans in the pelvis. The XGBoost model performs better in classification than the other three tree-based ensemble models, and global explanations and single-sample explanations of the model output through SHAP values may offer reference for medical physicists to provide high-quality plans, promoting the clinical application and implementation of GPR prediction models, and providing safe and efficient personalized QA management for patients.

目的 为肛管癌放疗患者提供一种3D打印个体化定制组织补偿物的方法,并进行剂量学和精度研究.方法 利用3D打印技术,打印出与患者皮肤贴合度好的组织补偿物,并设计多种放疗方案进行剂量学比较和验证,然后利用仿真人体模型进行胶片剂量验证,得出浅表肿瘤部位的剂量学准确性.结果 四组放疗方案的正常组织受量均能满足临床要求;靶区覆盖度D98分别为(64.8±1.6)、(64.5±1.67)、(64.6±1.3)、(64.7±1.4)Gy,靶区覆盖度均能满足临床要求且没有统计学差异;靶区最高剂量Dmax分别为(73.7±2.1)、(69.7±1.3)、(68.9±2.3)、(68.6±1.6)Gy,Plan A的靶区最高剂量最大,且有统计学差异.胶片剂量验证结果显示,没有加补偿物的放疗计划以及采用常规补偿物的放疗计划,肿瘤浅表部位的计划剂量与实际测量剂量平均偏差较大,分别为37.1％和12.6％,3D打印个体化补偿物的剂量平均偏差最小,为6.9％.结论 3D打印个体化组织补偿物满足肛管癌俯卧位放疗的要求,空气间隙小,与患者皮肤贴合度好,能真正提高肛管癌浅表肿瘤的组织受量.

目的 探究在辐照室穿墙布线并符合辐射防护三原则的方法.方法 选定一个后装治疗机及机房,辐照室与操作室之间的墙面预留一个直径为8.3 cm的布线孔洞,测量并比较辐射剂量仪位于操作室内孔洞旁不同位置和放射源位于辐照室内孔洞旁不同位置的最高辐射剂量率.结果 放射源距离孔洞延长线越远,辐射到室外的放射线越小;放射源固定时,在辐照室外距离孔洞延长线越远,受到的辐射越小,在孔洞延长线上受到的辐射远大于其他情况.结论 根据辐射防护的三原则,由测量结果可以得出,在辐照室内,放射源可能经过的位置不得位于孔洞延长线上,应尽量远离孔洞延长线;在操作室内,工作人员和公众居留因子高的位置应尽量远离孔洞延长线;孔洞面积应尽可能的小.

目的 比较动态多叶光栅(DMLC)调强放射治疗与分步照射(SS)调强放射治疗的剂量学差异,为DMLC调强放射治疗在宫颈癌放射治疗中临床应用提供依据.方法 选择20例经病理确诊的宫颈癌患者,年龄41～69岁,平均年龄53岁.分别使用DMLC调强技术和SS调强技术进行放射治疗计划设计,然后对两种放射治疗计划进行剂量学的对比,主要比较了剂量体积直方图、靶区剂量分布、危及器官受量、机器跳数和实际治疗时间.结果 DMLC调强放射治疗计划与SS调强放射治疗计划对靶区的覆盖程度是基本一致的,但最大剂量、均匀指数两者差异存在统计学意义(t=-11.686、-4.243,P<0.05),DMLC调强放射治疗计划的靶区剂量更均匀、最大剂量更低.对于危及器官的受量,膀胱、直肠4500 cGy剂量的受照体积,两者差异有统计学意义(t=-4.469、-5.029,P<0.05),DMLC调强放射治疗计划的受照体积更少.对于膀胱、直肠、小肠、股骨头和乙状结肠的平均剂量,小肠的3000 cGy、4000 cGy剂量的受照体积,以及股骨头的最大剂量,虽然差异无统计学意义,但DMLC调强放射治疗计划均低于(少于)SS调强放射治疗计划.DMLC调强放射治疗计划的单次机器跳数高于SS调强放射治疗计划,但DMLC调强放射治疗计划的单次治疗时间更少.结论 宫颈癌DMLC调强放射治疗计划和SS调强放射治疗计划都能满足临床要求,但DMLC调强放射治疗计划的靶区剂量均匀性更好,对危及器官的保护也更好,且大大缩短了单次治疗时间.

通过配置多个测量探头,改进现有的便携式辐射计量仪,使其能同时测量多个位置的辐射剂量,且测量探头可组成测量探头板,测量时通过计算可以推测出辐射源的大概位置.改进后的便携式辐射计量仪保证了多点测量条件的一致性,效率明显提升,且能用于快速定位放射源,使得工作人员在辐射区的驻留时间缩短,有利于工作人员的辐射防护.

BACKGROUND:Many studies have demonstrated that a higher radiotherapy dose is associated with improved outcomes in non-small-cell lung cancer (NSCLC). We performed a dosimetric planning study to assess the dosimetric feasibility of intensity-modulated radiation therapy (IMRT) with a simultaneous integrated boost (SIB) in locally advanced NSCLC.METHODS:We enrolled twenty patients. Five different dose plans were generated for each patient. All plans were prescribed a dose of 60 Gy to the planning tumor volume (PTV). In the three SIB groups, the prescribed dose was 69 Gy, 75 Gy, and 81 Gy in 30 fractions to the internal gross tumor volume (iGTV).RESULTS:The SIB-IMRT plans were associated with a significant increase in the iGTV dose (P < 0.05), without increased normal tissue exposure or prolonged overall treatment time. Significant differences were not observed in the dose to the normal lung in terms of the V5 and V20 among the four IMRT plans. The maximum dose (Dmax) in the esophagus moderately increased along with the prescribed dose (P < 0.05).CONCLUSIONS:Our results indicated that escalating the dose by SIB-IMRT is dosimetrically feasible; however, systematic evaluations via clinical trials are still warranted. We have designed a further clinical study (which is registered with ClinicalTrials.gov, number NCT02841228).

Objective: To explore a dosimetric analysis about the effect of simultaneous integrated boost - intensity-modulated radiation therapy (SIB-IMRT) under different dose for normal tissue of patients with locally advanced non-small cell lung cancer (NSCLC). Methods: 20 patients with NSCLC who couldn't receive operation were divided in IIIA group (10cases) and IIIB group (10cases) according to the classification method of Union for International Cancer Control (2009, 7th edition). Every patient received 4 radiotherapy plans included one routine IMRT and three SIB-IMRT plans, and then the dosimetric characteristic of different SIB-IMRT plan was evaluated. In all of these plans, the dose of planning target volume (PTV) was 60Gy/30f, and the planning gross tumor volume (PGTV) of three SIB-IMRT groups (SIB-IMRT-1 group, SIB-IMRT-2 group and SIB-IMRT-3 group) received, respectively, different dose (69Gy/30f, 75Gy/30f and 81Gy/30f), and the single divided doses of the three groups were 2.3Gy, 2.5Gy and 2.7Gy, respectively. The distributed dose of the four groups and received dose of normal group were evaluated and compared. Results: The PGTV doses of three SIB-IMRT groups were significantly increased, and all of dose of four groups were , respectively, 62.1Gy (IMRT group), 68.5Gy (SIB-IMRT-1 group), 74.2Gy(SIB-IMRT-2 group) and 79.6Gy (SIB-IMRT-3 group) (P<0.05). The differences of V20 in normal tissue among four groups were no significant (F=5.511, P>0.05). The mean lung dose (MLD) of SIB-IMRT-3 group was significantly higher than other groups (F=9.441, P<0.05), while it still was within the scope of limited requirement. Besides, the Dmax of esophagus was gradually increased with increasing of prescriptive dose, and the received doses of heart among various groups were no significant (F=1.204, P>0.05). Conclusion: On dosiology, it is feasible that PGTV dose is selectively increased when SIB-IMRT is used in the locally advanced NSCLC. This method don't increase total curative time and risk of toxic reaction of heart and lung. While the maximum dose of esophagus should be limited and this method still need more verification for its effectiveness and safety in clinical experiment.

[目的]比较Monaco治疗计划系统中两种不同算法在非小细胞肺癌静态调强放疗中的剂量学差异.[方法]选取12例经临床及病理确诊为非小细胞肺癌的患者,采用Monaco计划系统分别为每例患者设计XVMC算法和PB算法两组静态调强放疗计划,优化条件相同,分析比较两组计划的靶区均匀性指数(HI)和适形度指数(CI)以及正常组织的剂量分布.[结果]无论是靶区还是危及器官各项指标,XVMC算法结果均高于PB算法.其中,XVMC算法和PB算法的靶区HI和CI差异分别为1.11％和1.08％,且差异具有统计学意义(P＜0.05);脊髓的最大量以及心脏的各项指标(V10、V20、V30、Va0、Dmean)差异均小于2％,差异无统计学意义(P＞0.05);但双肺的各项指标(V5、V10、V20、V30、Dmean)以及食管的V30 V50、Dean差值均大于2％,且差异具有统计学意义(P＜0.05).XVMC组MU较低,优于PB组(P＜0.05).[结论]分析XVMC算法和PB算法的差异原因在于相比于XVMC算法,PB算法未考虑次级电子的输运和能量沉积以及侧向电子失衡,导致计算不精确.因此,在实际的临床计划设计时,对于组织结构密度差异较大、且低密度组织范围较大的部位,建议使用XVMC算法进行剂量计算.

Objective:To analyze the differences region of interest volume between Monaco and Pinnacle planning system, and provide reference for clinical application.Methods:Delineate 1,5 and 10 slices triangles, hexagonal and circular contours in Pinnacle treatment planning system.Meanwhile select 10 cases with head neck tumor,10 cases with chest tumor and 10 cases with abdomen tumors.Transfer image and ROI to Monaco treatment plan system by DICOM protocol.Compare ROI volume between two kinds of TPS.Results:There are significant differences in the volume of ROI between the two kinds of TPS, especially for small volume ROI. Conclusions:When the transmission ROI between two kinds of planning systems, especially the small volume ROI, should pay attention to the difference of ROI volume calculation.

目的:研究不同品牌、不同批次的有机玻璃托架板对托架因子的影响.方法:在Varian 600C/D加速器上测量不同品牌、不同批次的有机玻璃托架板的托架因子并进行比对.结果:不同品牌、不同批次的有机玻璃托架板的托架因子不相同.结论:在使用适形挡铅技术放疗中,应考虑不同品牌、不同批次的有机玻璃托架板的托架因子对治疗的影响.