ABSTRACT
Objective:To establish a three-dimensional (3D) U-net-based deep learning model, and to predict the 3D dose distribution in CT-guided cervical cancer brachytherapy by using the established model.Methods:The brachytherapy plans of 114 cervical cancer cases with a prescription dose of 6 Gy for each case were studied. These cases were divided into training, validation, and testing groups, including 84, 11, and 19 patients, respectively. A total of 500 epochs of training were performed by using a 3D U-net model. Then, the dosimetric parameters of the testing groups were individually evaluated, including the mean dose deviation (MDD) and mean absolute dose deviation (MADD) at the voxel level, the Dice similarity coefficient (DSC) of the volumes enclosed by isodose surfaces, the conformal index (CI) of the prescription dose, the D90 and average dose Dmean delivered to high-risk clinical target volumes (HR-CTVs), and the D1 cm 3 and D2 cm 3 delivered to bladders, recta, intestines, and colons, respectively. Results:The overall MDD and MADD of the 3D dose matrix from 19 cases of the testing group were (-0.01 ± 0.03) and (0.04 ± 0.01) Gy, respectively. The CI of the prescription dose was 0.70 ± 0.04. The DSC of 50%-150% prescription dose was 0.89-0.94. The mean deviation of D90 and Dmean to HR-CTVs were 2.22% and -4.30%, respectively. The maximum deviations of the D1 cm 3 and D2 cm 3 to bladders, recta, intestines, and colons were 2.46% and 2.58%, respectively. The 3D U-net deep learning model took 2.5 s on average to predict a patient′s dose. Conclusions:In this study, a 3D U-net-based deep learning model for predicting 3D dose distribution in the treatment of cervical cancer was established, thus laying a foundation for the automatic design of cervical cancer brachytherapy.
ABSTRACT
Objective:To develop a dose prediction-based quantitative evaluation method of the quality of radiotherapy plans, and to verify the clinical feasibility and clinical value of the method .Methods:The 3D U-Netwas trained using the radiotherapy plans of 45 rectal cancer cases that were formulated by physicists with more than five years of radiotherapy experience. After obtaining 3D dose distribution using 3D U-Net prediction, this study established the plan quality metrics of intensity modulated radiotherapy(IMRT) rectal cancer radiotherapy plans using dose-volume histogram(DVH) indexes of dose prediction. Then, the initial scores of rectal cancer radiotherapy plans were determined.Taking the predicted dose as the optimization goal, the radiotherapy plans were optimized and scored again. The clinical significance of this scoring method was verified by comparing the scores and dosimetric parameters of the 15 rectal cancer cases before and after optimization.Results:The radiotherapy plans before and after optimization all met the clinical dose requirements. The total scores were(77.21±9.74) before optimization, and (88.78±4.92) after optimization. Therefore, the optimized radiotherapy planswon increased scores with a statistically significant difference( t=-4.105, P<0.05). Compared to the plans before optimization, the optimized plans show decreased Dmax of all organs at risk to different extents. Moreover, the Dmax, V107%, and HI of PTV and the Dmax of the bladder decreased in the optimized plans, with statistically significant differences ( t=2.346-5.771, P<0.05). There was no statistically significant difference in other indexes before and after optimization ( P>0.05).The quality of the optimized plans were improved to a certain extent. Conclusions:This study proposed a dose prediction-based quantitative evaluation method of the quality of radiotherapy plans. It can be used for the effective personalized elevation of the quality of radiotherapy plans, which is beneficial to effectively compare and review the quality of clinical plans determined by different physicists and provide personalized dose indicators. Moreover, it can provide great guidance for the formulation of clinical therapy plans.
ABSTRACT
Objective:To propose an automatic planning method of intensity-modulated radiotherapy (IMRT) for esophageal cancer based on dose volume histogram prediction and beam angle optimization in Raystation treatment planning system.Methods:50 IMRT plans of esophageal cancer were selected as the training set to establish a dose prediction model for organs at risk. Another 20 testing plans were optimized in Raystation using RuiPlan and manual method, and the beam angle optimization and dose volume histogram prediction functions of RuiPlan were used for automatic planning. Dosimetric differences and planning efficiency between two methods were statistically compared with paired t-test. Results:There were no significant dosimetric differences in the conformity index (CI), homogeneity index (HI) of PTV, V 5Gy of both lungs and D max of the spinal cord between automatic and manual plans (all P>0.05). Compared with those in the manual plans, the V 20Gy and D mean of the left and right lungs generated from automatic plans were reduced by 1.1%, 0.37 Gy and 1.2%, 0.38 Gy (all P<0.05), and the V 30Gy, V 40Gy and D mean of the heart in automatic plans were significantly decreased by 5.1%, 3.0% and 1.41 Gy, respectively (all P<0.05). The labor time, computer working time, and monitor unit (MU) number of automatic plans were significantly decreased by 65.8%, 14.1%, and 17.2%, respectively (all P<0.05). Conclusion:RuiPlan automatic planning scripts can improve the efficiency of esophageal cancer planning by dose prediction and beam angle optimization, providing an alternative for esophageal cancer radiotherapy planning.
ABSTRACT
Objective:To develope an automatic volumetric modulated arc therapy (VMAT) planning for rectal cancer based on a dose-prediction model for organs at risk(OARs) and an iterative optimization algorithm for objective parameter optimization.Methods:Totally 165 VMAT plans of rectal cancer patients treated in Peking University Cancer Hospital & Institute from June 2018 to January 2021 were selected to establish automatic VMAT planning. Among them, 145 cases were used for training the deep-learning model and 20 for evaluating the feasibility of the model by comparing the automatic planning with manual plans. The deep learning model was used to predict the essential dose-volume histogram (DVH) index as initial objective parameters(IOPs) and the iterative optimization algorithm can automatically modify the objective parameters according to the result of protocol-based automatic iterative optimization(PBAIO). With the predicted IOPs, the automatic planning model based on the iterative optimization algorithm was achieved using a program mable interface.Results:The IOPs of OARs of 20 cases were effectively predicted using the deep learning model, with no significantly statistical difference in the conformity index(CI) for planning target volume(PTV)and planning gross tumor volume(PGTV)between automatic and manual plans( P>0.05). The homogeneity index (HI) of PGTV in automatic and manual plans was 0.06 and 0.05, respectively( t=-6.92, P< 0.05). Compared with manual plans, the automatic plans significantly decreased the V30 for urinary bladder by 2.7% and decreased the V20 for femoral head sand auxiliary structure(avoidance)by 8.37% and 15.95%, respectively ( t=5.65, 11.24, P< 0.05). Meanwhile, the average doses to bladder, femoral heads, and avoidance decreased by 1.91, 4.01, and 3.88 Gy, respectively( t=9.29, 2.80, 10.23, P< 0.05) using the automatic plans. The time of automatic VMAT planning was (71.49±25.48)min in 20 cases. Conclusions:The proposed automatic planning based on dose prediction and an iterative optimization algorithm is feasible and has great potential for sparing OARs and improving the utilization rate of clinical resources.
ABSTRACT
Objective To train individualized three-dimensional (3D) dose prediction models for radiotherapy planning,and use the models to establish a planning quality control method.Methods A total of 99 cases diagnosed as early nasopharyngeal carcinoma (NPC) were analyzed retrospectively,who received simultaneous integrated boost (SIB) with volumetric modulated arc therapy (VMAT).Seven geometric features were extracted,including the minimum distance features from each organs at risk (OARs) to planning target volume (PTV),boost targets and outline,as well as four coordinate position characteristics.89 cases were trained and 10 cases were tested based on 3D dose distribution prediction models using artificial neural network (ANN).A planning quality control method were established based on the prediction models.The dosimetric parameters including D2％,D25％,D50％,D75％ and mean dose (MD) of each OAR were used as quality control indicators,and the passing criteria was defined as that the dosimetric difference between manual planning and the predicted dose should be less than 10％.The quality control method was tested with 10 plans ()esigned by a junior physicist.Results There was no significant discrepancy between the model predicted dose and the result of expert plan in the main dosimetric indexes of 18 OARs.The dose differences of D2％,D25％,D50％,D75％ and MD were all controlled within 1.2 Gy.All the 10 plans designed by a junior physicist reached the general clinical dose requirements,while by using our proposes quality control method,one of these plans was observed not optimal enough and some dosimetric parameters of spinal cord,spinal cord PRV,brainstem and brainstem PRV could be improved.After re-optimizing this plan according to the predicted values of the model,the D2％ of spinal cord and brainstem decreased by 8.4 Gy and 5.8 Gy,respectively.Conclusions This study proposes a simple and convenient quality control method for radiotherapy planning.This method could overcome the disadvantage of unified dose constrains without considering patient-specific conditions,and improve the quality and stability of individualized radiotherapy planning.
ABSTRACT
Objective@#To train individualized three-dimensional (3D) dose prediction models for radiotherapy planning, and use the models to establish a planning quality control method .@*Methods@#A total of 99 cases diagnosed as early nasopharyngeal carcinoma (NPC) were analyzed retrospectively, who received simultaneous integrated boost (SIB) with volumetric modulated arc therapy (VMAT). Seven geometric features were extracted, including the minimum distance features from each organs at risk (OARs) to planning target volume (PTV), boost targets and outline, as well as four coordinate position characteristics.89 cases were trained and 10 cases were tested based on 3D dose distribution prediction models using artificial neural network (ANN). A planning quality control method were established based on the prediction models. The dosimetric parameters including D2%, D25%, D50%, D75% and mean dose (MD) of each OAR were used as quality control indicators, and the passing criteria was defined as that the dosimetric difference between manual planning and the predicted dose should be less than 10%. The quality control method was tested with 10 plans designed by a junior physicist.@*Results@#There was no significant discrepancy between the model predicted dose and the result of expert plan in the main dosimetric indexes of 18 OARs. The dose differences of D2%, D25%, D50%, D75% and MD were all controlled within 1.2 Gy.All the 10 plans designed by a junior physicist reached the general clinical dose requirements, while by using our proposes quality control method, one of these plans was observed not optimal enough and some dosimetric parameters of spinal cord, spinal cord PRV, brainstem and brainstem PRV could be improved. After re-optimizing this plan according to the predicted values of the model, the D2% of spinal cord and brainstem decreased by 8.4 Gy and 5.8 Gy, respectively.@*Conclusions@#This study proposes a simple and convenient quality control method for radiotherapy planning. This method could overcome the disadvantage of unified dose constrains without considering patient-specific conditions, and improve the quality and stability of individualized radiotherapy planning.
ABSTRACT
@#Objective To evaluate the quality of warfarin anticoagulant therapy in patients with stable stage after mechanical valve replacement surgery, to observe the effect of compound salvia miltiorrhiza tablet on the anticoagulant effect of warfarin in patients after mechanical valve replacement, and to understand the impact of genetic polymorphisms of VKORC1, CYP2C9 and CYP4F2 on warfarin resistance in patients with mechanical valve replacement in the stable period. Methods From July 2011 to February 2014, 1 831 patients who had ≥ 6 months after mechanical valve replacement surgery were enrolled at the outpatient follow-up. The basic clinical data were recorded. Anticoagulant therapy uses a target international normalized ratio（INR, 1.60–2.20) and a weekly warfarin dose adjustment strategy. Forty-six patients who needed compound salvia miltiorrhiza tablet were screened and the INR values. Before and after taking tablets were recorded and compared. The patients were divided into three groups according to the percentile of warfarin dosage including a warfarin sensitive patients group, a control patients group, and a warfarin resistance patients group. And 101 of them were selected. TIANGEN blood DNA Kit blood genomic DNA extraction kit was used to extract samples and polymerase chain restriction fragment length polymorphism (PCR-RELP) was used to determine the genotypes of patients. The detected gene loci included CYP4F2: rs2108622C>T locus; VKORC1:1639G>A locus; VKORC1:1173C>T locus; CYP2C9*2: rs1799853C>T locus; CYP2C9*3:1061A>C locus. Results The time in therapeutic range (TTR) and fraction of time in therapeutic range (FTTR) in the target INR range of the patients included in the study period was 27.2% and 49.4%, respectively, and the TTR and FTTR in the acceptable INR range was 34.25% and 63.36%, respectively. Before and after the addition of compound salvia miltiorrhiza tablets, the INR value was 1.55±0.03 and 1.69±0.30, respectively, and the difference was statistically different (P<0.05). A total of 101 patients with genetic testing, in which the C/T composition of the VKORC1: 1173C>T locus increased in the warfarin sensitivity, contrast and warfarin resistance patients, while the ratio of allelic loci of C/T in CYP2C9*3: 1061A>C loci decreased in turn. There was no difference in the CYP4F2 gene, VKORC1639 gene, and CYP2C9*2 locus. The IWPC model predicts that warfarin dose is only consistent with the actual warfarin dose in warfarin sensitive patients. Conclusion Relatively low TTR and FTTR are acceptable in patients with stable stage after mechanical valve replacement. It is beneficial to the patients with compound salvia miltiorrhiza tablets in terms of some appropriate patients. VKORC1: 1173C>T site and CYP2C9*3: 1061A>C site mutation is the main pharmacological gene factor of warfarin dose sensitivity and warfarin resistance in stable period after mechanical valve replacement. The IWPC dose prediction model is only consistent with the actual dose of warfarin sensitive patients.