ABSTRACT
Objective:To establish a metaheuristics-based automatic radiotherapy treatment planning method (ATP-STAR) and verify its effectiveness.Methods:The main process of the ATP-STAR method was as follows. First, the optimization parameters were vectorized for encoding and corrected using Gaussian convolution. Then, the candidate optimization parameter vector set was selected through simulated annealing. Finally, the optimal combination of optimization parameters was determined by combining the field fluence optimization to achieve automatic trial-and-error. Twenty cases with large individual differences in tumors were selected for testing. Clinical physicists with more than five years of experience were invited to perform manual planning. Both the manual and ATP-STAR plans were made utilizing the matRad open source software for radiation treatment planning, with the fields and prescribed doses consistent with those of the clinical treatment plans. The dosimetric differences of target volumes and organs at risk between the ATP-STAR and manual plans for different diseases were analyzed.Results:For the target volumes, the ATP-STAR plans showed superior homogeneity compared with the manual plans (brain tumors: z = 2.28, P = 0.022; lung cancers: z = 2.29, P = 0.022; liver cancers: z = 2.11, P = 0.035). The conformability of the ATP-STAR plans was comparable to that of the manual plans for brain tumors and liver cancer and was slightly lower than that of the manual plans for lung cancer ( z = 2.29, P = 0.022). The comparison result of doses to organs at risk (OARs) between the manual plans and STAR plans were as follows. For OARs of brain tumors, the ATP-STAR plans decreased the mean left lens Dmean from 2.19 Gy to 1.76 Gy ( z = 2.28, P = 0.022), decreased left optic nerve Dmean from 11.36 Gy to 10.22 Gy ( z = 2.28, P = 0.022), decreased right optic nerve Dmax from 32.92 Gy to 29.97 Gy ( z = 2.10, P = 0.036), and decreased pituitary Dmax from 39.53 Gy to 35.21 Gy ( z = 2.29, P = 0.022). For OARs of lung cancer, the ATP-STAR plans decreased the mean spinal cord Dmax from 38.00 Gy to 31.17 Gy ( z = 2.12, P = 0.034), decreased the bilateral lungs Dmean from 8.51 Gy to 8.07 Gy ( z = 2.29, P = 0.022), and decreased cardiac Dmean from 3.21 Gy to 2.69 Gy ( z =2.29, P = 0.022). For OARs of liver cancer, the ATP-STAR plans decreased spinal cord Dmax from 18.19 Gy to 14.76 Gy ( z = 2.11, P = 0.035), decreased liver Dmean from 15.61 Gy to 14.45 Gy ( z = 2.11, P = 0.035), and decreased kidneys Dmean from 4.76 Gy to 4.04 Gy ( z = 2.10, P = 0.036). Conclusions:The proposed ATP-STAR method relies little on the experience of manual planning and thus is easy to be widely applied. This method is expected to improve the quality and consistency of IMRT plans and save clinical labor and time costs.
ABSTRACT
Objective:Utilizing multi-criterion optimization (MCO) technology to improve plan design quality based on knowledge-based planning (KBP) model.Methods:Fifty-five patients with nasopharyngeal carcinoma (NPC) who had completed radiotherapy were selected, and fixed-field intensity-modulated radiotherapy (IMRT) technology was used in each case. Among them, 40 cases were randomly selected as training set 1. Then, IMRT plans in training set 1 were preprocessed by MCO technology to construct a new training set 2. With the initial training set 1 and the processed training set 2 as training samples, the traditional KBP model and the MCO-KBP model refined by MCO technology were trained, respectively. Among the remaining 15 cases, 5 cases were randomly selected as the validation set, and the remaining 10 cases were used as the test set. After verification, the test set was used to statistically analyze the plan quality of the initial manual plan and the automatic plan generated by the traditional KBP model and the MCO-KBP model.Results:The target dose (D 95%) of plans generated by the traditional KBP model and the MCO-KBP model met the clinical requirements. Conformity index (CI) and homogeneity index (HI) were almost the same ( P>0.05), and the doses of organ at risk (OAR) of the automatic plans generated by the MCO-KBP model were lower than those of the traditional KBP model. For example, compared with the traditional KBP model, the average D max of the brainstem in the automatic plans generated by the MCO-KBP model was lower by 2.13 Gy, the average D mean of the left parotid gland was lower by 1.39 Gy, the average D mean of the right parotid gland was lower by 1.59 Gy, and the average D max of the left optic nerve was lower by 1.42 Gy, the average D max of the right optic nerve was lower by 1.16 Gy, and the average D max of the pituitary gland was lower by 1.88 Gy. All of the above-mentioned dosimetry indexes were statistically significant. Conclusion:Compared with the traditional KBP model, the IMRT plans designed by the refined MCO-KBP model have obvious advantages in the protection of OAR, which proves the feasibility of utilizing MCO technology to improve the plan design quality of the KBP model.
ABSTRACT
Objective:To propose an automatic planning approach for Eclipse15.6 planning system based on Eclipse scripting application programming interface (ESAPI) and evaluate its clinical application.Methods:20 patients with nasopharyngeal carcinoma and 20 cases of rectal cancer were selected in the clinical planning. The developed automatic planning script SmartPlan and RapidPlan were used for automatic planning and dosimetric parameters were compared with manual planning. The differences were compared between two groups by using Wilcoxon signed rank test. Results:The dosimetric results of automatic and manual plans could meet clinical requirements. There was no significant difference in target coverage in nasopharyngeal carcinoma planning between two groups ( P>0.05), and automatic plans were superior to manual plans in organs at risk sparing ( P<0.05). Except for the homogeneity index of PTV and the maximum dose of bowel in rectal cancer plans, the other dosimetric parameters of the automatic plans were better than those of the manual plans (all P<0.05). Conclusions:Compared with the manual plans, the automatic plans have the same or similar target coverage, similar or better protection of organs at risk, and more convenient implementation. The developed SmartPlan based on ESAPI has clinical feasibility and effectiveness.
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 establish an automatic planning method using volumetric-modulated arc therapy (VMAT) for primary liver cancer (PLC) radiotherapy based on predicting the feasibility dose-volume histogram (DVH) and evaluate its performance.Methods:Ten patients with PLC were randomly chosen in this retrospective study. Pinnacle Auto-Planning was used to design the VMAT automatic plan, and the feasibility DVH curve was obtained through the PlanIQ dose prediction, and the initial optimization objectives of the automatic plan were set according to the displayed feasible objectives interval. The plans were accessed according to dosimetric parameters of the planning target volume and organs at risk as well as the monitor units. All patients′ automatic plans were compared with clinically accepted manual plans by using the paired t-test. Results:There was no significant difference of the planning target volume D 2%, D 98%, D mean or homogeneity index between the automatic and manual plans ((58.55±2.81) Gy vs.(57.98±4.17) Gy, (47.15±1.58) Gy vs.(47.82±1.38) Gy, (53.14±0.95) Gy vs.(53.44±1.67) Gy and 1.15±0.05 vs. 1.14±0.07, all P>0.05). The planning target volume conformity index of the manual plan was slightly higher than that of the automatic plan (0.77±0.08 vs. 0.69±0.06, P<0.05). The mean doses of normal liver, V 30Gy, V 20Gy, V 10Gy, V 5Gy and V< 5Gy of the automatic plan were significantly better than those of the manual plan ((26.68±11.13)% vs.(28.00±10.95)%, (29.96±11.50)% vs.(31.89±11.51)%, (34.88±11.51)% vs.(38.66±11.67)%, (45.38±12.40)% vs.(50.74±13.56)%, and (628.52±191.80) cm 3vs.(563.15±188.39) cm 3, all P<0.05). The mean doses of the small intestine, the duodenum, and the heart, as well as lung V 10 of the automatic plan were significantly less than those of the manual plan ((1.83±2.17) Gy vs.(2.37±2.81) Gy, (9.15±9.36) Gy vs.(11.18±10.49) Gy, and (5.44±3.10) Gy vs.(6.25±3.26) Gy, as well as (12.70±7.08)% vs.(14.47±8.11)%, all P<0.05). Monitor units did not significantly differ between two plans ((710.67±163.72) MU vs.(707.53±155.89) MU, P>0.05). Conclusions:The automatic planning method using VMAT for PLC radiotherapy based on predicting the feasibility DVH enhances the quality for PLC plans, especially in terms of normal liver sparing. Besides, it also has advantages for the protection of the intestine, whole lung and heart.
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 design a knowledge-based cervical cancer planning model and apply it to cases of endometrial cancer and rectal cancer in order to explore the generalization of the model.Methods:A total of 179 cases of pelvic regions with different prescribed doses of dual-arc volumetric modulated arc therapy clinical plans were collected, of which 99 cases of cervical cancer clinical plans with a prescribed dose of 50.4 Gy were used as the training set to establish the RapidPlan model, and the remaining clinical plans were divided into 4 validation groups with 20 cases in each group. The clinical plans for cervical cancer and endometrial cancer with a prescription dose of 50.4 Gy were named groups A and B, while the clinical plan for endometrial cancer and rectal cancer with a prescription dose of 45 Gy were named groups C and D. The model was used to redesign the clinical plans in the 4 groups and the automatic plans were obtained. The planning target volume (PTV) and organ at risk (OAR) dosimetry parameters were compared between automatic plans and clinical plans.Results:The conformity index (CI) of the automatic plans in the A, B, C, and D groups were equivalent to that of the clinical plans ( P>0.05). The homogeneity index (HI) and D2% of the automatic plans in groups A, B, and C were all lower than those in clinical plans(HI, Z=-3.248, -3.360, -2.329, P<0.05; D2%, Z=-2.987, -3.397, -2.442, P<0.05). The HI and D2% of the automatic plans in group D were similar those in the clinical plans ( P>0.05). While ensuring the PTV coverage, the average value of OAR dosimetry parameters in all automatic plans groups were lower than that of the clinical plans. Conclusions:The RapidPlan model established by the cervical cancer clinical plans can complete the automatic plan design for endometrial cancer and rectal cancer under different prescription doses, which preliminarily proves the possibility of the generalization of the RapidPlan model.
ABSTRACT
Objective To evaluate the feasibility of an in-room automated volumetric arc therapy (VMAT) planning engine based on dose volume histogram (DVH) prediction model in RayStation treatment planning system.Methods A total of 4,0 VMAT plans of cervix cancer,planned by experts,were chosen to build DVH estimation model by principal component regression analytic method.An in-room automated VMAT planning program based on IroPython scripting language combined with DVH prediction model was performed in RayStation treatment planning system.The DVH estimation model was applied to Another 10 testing cases of cervical cancer and the feasibility was evaluated by comparing the automatic plans with manual plans.Results The predicted DVH of organs at risk showed a good fit with real DVH in the ten testing cases.There were no statistically significant differences between manual and automatic plans in PTV conformal index (CI) and homogeneity index (HI) (P ＞ O.05).V40 and V50 of bladder were significantly decreased by 4.3％ and 1.6％ in automatic plans (t =2.75,5.26,P ＜ 0.05).V30,V40 and Vs0 of rectum were also decreased by 6.8％,5.8 ％ and 2.1％ (t =2.26,3.55,5.19,P ＜ 0.05).Both left and right femoral heads were better spared in automatic plans with average doses decreased by 380 and 322 cGy(t =5.55,7.25,P ＜ 0.05).The time of creating a treatment plan was 36 min for automatic plan and 53 min for manual plan.Conclusions The fully automated VMAT treatment plan program can create a VMAT plan of cervix cancer with high efficiency and good quality.