Characterization of knowledge-based volumetric modulated arc therapy plans created by three different institutions' models for prostate cancer

A new predictive parameter for dose-volume metrics in intensity-modulated radiation therapy planning for prostate cancer: Initial phantom study

BACKGROUND

Organ-at-risk (OAR) sparing is often assessed using an overlap volume-based parameter, defined as the ratio of the volume of OAR that overlaps the planning target volume (PTV) to the whole OAR volume. However, this conventional overlap-based predictive parameter (COPP) does not consider the volume relationship between the PTV and OAR.

PURPOSE

We propose a new overlap-based predictive parameter that consider the PTV volume. The effectiveness of proposed overlap-based predictive parameter (POPP) is evaluated compared with COPP.

METHODS

We defined as POPP = (overlap volume between OAR and PTV/OAR volume) × (PTV volume/OAR volume). We generated intensity modulated radiation therapy (IMRT) based on step and shoot technique, and volumetric modulated arc therapy (VMAT) plans with the Auto-Planning module of Pinnacle3 treatment planning system (v14.0, Philips Medical Systems, Fitchburg, WI) using the American Association of Physicists in Medicine Task Group (TG119) prostate phantom. The relationship between the position and size of the prostate phantom was systematically modified to simulate various geometric arrangements. The correlation between overlap-based predictive parameters (COPP and POPP) and dose-volume metrics (mean dose, V70Gy, V60Gy, and V37.5 Gy for rectum and bladder) was investigated using linear regression analysis.

RESULTS

Our results indicated POPP was better than COPP in predicting intermediate-dose metrics. The bladder results showed a trend similar to that of the rectum. The correlation coefficient of POPP was significantly greater than that of COPP in < 62 Gy (82% of the prescribed dose) region for IMRT and in < 55 Gy (73% of the prescribed dose) region for VMAT regarding the rectum (p < 0.05).

CONCLUSIONS

POPP is superior to COPP for creating predictive models at an intermediate-dose level. Because rectal bleeding and bladder toxicity can be associated with intermediate-doses as well as high-doses, it is important to predict dose-volume metrics for various dose levels. POPP is a useful parameter for predicting dose-volume metrics and assisting the generation of treatment plans.

Patient-specific three-dimensional dose distribution prediction via deep learning for prostate cancer therapy: Improvement with the structure loss

PURPOSE

Deep learning (DL)-based dose distribution prediction can potentially reduce the cost of inverse planning process. We developed and introduced a structure-focused loss (L_struct) for 3D dose prediction to improve prediction accuracy. This study investigated the influence of L_struct on DL-based dose prediction for patients with prostate cancer. The proposed L_struct, which is similar in concept to dose-volume histogram (DVH)-based optimization in clinical practice, has the potential to provide more interpretable and accurate DL-based optimization.

METHODS

This study involved 104 patients who underwent prostate radiotherapy. We used 3D U-Net-based architecture to predict dose distributions from computed tomography and contours of the planning target volume and organs-at-risk. We trained two models using different loss functions: L2 loss and L_struct. Predicted doses were compared in terms of dose-volume parameters and the Dice similarity coefficient of isodose volume.

RESULTS

DVH analysis showed that the L_struct model had smaller errors from the ground truth than the L2 model. The L_struct model achieved more consistent dose distributions than the L2 model, with errors close to zero. The isodose Dice score of the L_struct model was greater than that of the L2 model by >20% of the prescribed dose.

CONCLUSIONS

We developed L_struct using labels of inputted contours for DL-based dose prediction for prostate radiotherapy. L_struct can be generalized to any DL architecture, thereby enhancing the dose prediction accuracy.

Multi-institution model (big model) versus single-institution model of knowledge-based volumetric modulated arc therapy (VMAT) planning for prostate cancer

We established a multi-institution model (big model) of knowledge-based treatment planning with over 500 treatment plans from five institutions in volumetric modulated arc therapy (VMAT) for prostate cancer. This study aimed to clarify the efficacy of using a large number of registered treatment plans for sharing the big model. The big model was created with 561 clinically approved VMAT plans for prostate cancer from five institutions (A: 150, B: 153, C: 49, D: 60, and E: 149) with different planning strategies. The dosimetric parameters of planning target volume (PTV), rectum, and bladder for two validation VMAT plans generated with the big model were compared with those from each institutional model (single-institution model). The goodness-of-fit of regression lines (R2 and χ2 values) and ratios of the outliers of Cook’s distance (CD) > 4.0, modified Z-score (mZ) > 3.5, studentized residual (SR) > 3.0, and areal difference of estimate (dA) > 3.0 for regression scatter plots in the big model and single-institution model were also evaluated. The mean ± standard deviation (SD) of dosimetric parameters were as follows (big model vs. single-institution model): 79.0 ± 1.6 vs. 78.7 ± 0.5 (D50) and 0.13 ± 0.06 vs. 0.13 ± 0.07 (Homogeneity Index) for the PTV; 6.6 ± 4.0 vs. 8.4 ± 3.6 (V90) and 32.4 ± 3.8 vs. 46.6 ± 15.4 (V50) for the rectum; and 13.8 ± 1.8 vs. 13.3 ± 4.3 (V90) and 39.9 ± 2.0 vs. 38.4 ± 5.2 (V50) for the bladder. The R2 values in the big model were 0.251 and 0.755 for rectum and bladder, respectively, which were comparable to those from each institution model. The respective χ2 values in the big model were 1.009 and 1.002, which were closer to 1.0 than those from each institution model. The ratios of the outliers in the big model were also comparable to those from each institution model. The big model could generate a comparable VMAT plan quality compared with each single-institution model and therefore could possibly be shared with other institutions.

An updating approach for knowledge-based planning models to improve plan quality and variability in volumetric-modulated arc therapy for prostate cancer

PURPOSE

The purpose of this study was to compare the dose-volume parameters and regression scatter plots of the iteratively improved RapidPlan (RP) models, specific knowledge-based planning (KBP) models, in volumetric-modulated arc therapy (VMAT) for prostate cancer over three periods.

METHODS

A RP1 model was created from 47 clinical intensity-modulated radiation therapy (IMRT)/VMAT plans. A RP2 model was created to exceed dosimetric goals which set as the mean values +1SD of the dose-volume parameters of RP1 (50 consecutive new clinical VMAT plans). A RP3 model was created with more strict dose constraints for organs at risks (OARs) than RP1 and RP2 models (50 consecutive anew clinical VMAT plans). Each RP model was validated against 30 validation plans (RP1, RP2, and RP3) that were not used for model configuration, and the dose-volume parameters were compared. The Cook's distances of regression scatterplots of each model were also evaluated.

RESULTS

Significant differences (p < 0.05) between RP1 and RP2 were found in D_mean (101.5% vs. 101.9%), homogeneity index (3.90 vs. 4.44), 95% isodose conformity index (1.22 vs. 1.20) for the target, V_40Gy (47.3% vs. 45.7%), V_60Gy (27.9% vs. 27.1%), V_70Gy (16.4% vs. 15.2%), and V_78Gy (0.4% vs. 0.2%) for the rectal wall, and V_40Gy (43.8% vs. 41.8%) and V_70Gy (21.3% vs. 20.5%) for the bladder wall, whereas only V_70Gy (15.2% vs. 15.8%) of the rectal wall differed significantly between RP2 and RP3. The proportions of cases with a Cook's distance of <1.0 (RP1, RP2, and RP3 models) were 55%, 78%, and 84% for the rectal wall, and 77%, 68%, and 76% for the bladder wall, respectively.

CONCLUSIONS

The iteratively improved RP models, reflecting the clear dosimetric goals based on the RP feedback (dose-volume parameters) and more strict dose constraints for the OARs, generated superior dose-volume parameters and the regression scatterplots in the model converged. This approach could be used to standardize the inverse planning strategies.

Dosimetric Evaluation of Simplified Knowledge-Based Plan with an Extensive Stepping Validation Approach in Volumetric-Modulated Arc Therapy-Stereotactic Body Radiotherapy for Lung Cancer

Purpose:

We investigated the performance of the simplified knowledge-based plans (KBPs) in stereotactic body radiotherapy (SBRT) with volumetric-modulated arc therapy (VMAT) for lung cancer.

Materials and Methods:

For 50 cases who underwent SBRT, only three structures were registered into knowledge-based model: total lung, spinal cord, and planning target volume. We performed single auto-optimization on VMAT plans in two steps: 19 cases used for the model training (closed-loop validation) and 16 new cases outside of training set (open-loop validation) for TrueBeam (TB) and Halcyon (Hal) linacs. The dosimetric parameters were compared between clinical plans (CLPs) and KBPs: CLP_closed, KBP_closed-TB and KBP_closed-Hal in closed-loop validation, CLP_open, KBP_open-TB and KBP_open-Hal in open-loop validation.

Results:

All organs at risk were comparable between CLPs and KBPs except for contralateral lung: V₅ of KBPs was approximately 3%–7% higher than that of CLPs. V₂₀ of total lung for KBPs showed comparable to CLPs; CLP_closed vs. KBP_closed-TB and CLP_closed vs. KBP_closed-Hal: 4.36% ± 2.87% vs. 3.54% ± 1.95% and 4.36 ± 2.87% vs. 3.54% ± 1.94% (P = 0.54 and 0.54); CLP_open vs. KBP_open-TB and CLP_open vs. KBP_open-Hal: 4.18% ± 1.57% vs. 3.55% ± 1.27% and 4.18% ± 1.57% vs. 3.67% ± 1.26% (P = 0.19 and 0.27). CI₉₅ of KBPs with both linacs was superior to that of the CLP in closed-loop validation: CLP_closed vs. KBP_closed-TB vs. KBP_closed-Hal: 1.32% ± 0.12% vs. 1.18% ± 0.09% vs. 1.17% ± 0.06% (P < 0.01); and open-loop validation: CLP_open vs. KBP_open-TB vs. KBP_open-Hal: 1.22% ± 0.09% vs. 1.14% ± 0.04% vs. 1.16% ± 0.05% (P ≤ 0.01).

Conclusions:

The simplified KBPs with limited number of structures and without planner intervention were clinically acceptable in the dosimetric parameters for lung VMAT-SBRT planning.

[Impact of Aperture Shape Controller on Knowledge-based VMAT Planning of Prostate Cancer]

PURPOSE

Knowledge-based planning (KBP) has disadvantages of high monitor unit (MU) and complex multi-leaf collimator (MLC) motion. We investigated the optimal aperture shape controller (ASC) level for the KBP to reduce these factors in volumetric modulated arc therapy (VMAT) for prostate cancer.

METHODS

The KBP model was created based on 51 clinical plans (CPs) of patients who underwent the VMAT for prostate cancer. Another 10 CPs were selected randomly, and the KBPs with/without ASC, changed stepwise from very low (KBP-VL) to very high (KBP-VH), were performed with a single auto-optimization. The parameters of dose-volume histograms (DVHs) and MLC performance metrics were evaluated. We obtained the modulation complexity score for VMAT (MCSv), closed leaf score (CLS), small aperture score (SAS), leaf travel (LT), and total MU.

RESULTS

The ASC did not affect the DVH parameters negatively. The following comparisons of MLC performance were obtained (KBP vs. KBP-VL vs. KBP-VH, respectively): 0.25 vs. 0.27 vs. 0.30 (MCSv), 0.19 vs. 0.18 vs. 0.16 (CLS), 0.50 vs. 0.45 vs. 0.40 (SAS_{10 mm}), 0.73 vs. 0.68 vs. 0.63 (SAS_{20 mm}), 768.35 mm vs. 671.50 mm vs. 551.32 mm (LT), and 672.87 vs. 642.36 vs. 607.59 (MU). There were significant differences between KBP and KBP-VH for MCSv and LT (p<0.05).

CONCLUSIONS

The KBP using an ASC set to the very high level could reduce the complexity of MLC motion significantly more without deterioration of the DVH parameters compared with the KBP in VMAT for prostate cancer.