Knowledge-based Planning Model Research Articles

Use of a constrained hierarchical optimization dataset enhances knowledge-based planning as a quality assurance tool for prostate bed irradiation.

To investigate whether building a knowledge-based planning (KBP) model with prostate bed plans constructed from constrained hierarchical optimization (CHO) would result in more efficient model construction with more consistent output than a model built using plans from a traditional, trial-and-error-based optimization (TEO) technique. Three KBP models were constructed from plans from subsets of 58 post-prostatectomy patients treated with intensity-modulated radiation therapy. TEO54 was built from 54 TEO plans, selected to represent typical clinical variations in target and organ-at-risk sizes and shapes. CHO30 and TEO30 were built from the same 30 patients populated with CHO and TEO plans, respectively. The three models were each applied to a new set of 18 patient scans and dose-volume histogram estimates (DVHEs) were generated for rectal and bladder walls and compared for each patient. CHO30 resulted in a significantly tighter range in DVHEs (P<0.01) for both the rectal and bladder walls compared with either of the TEO models, indicating less uncertainty in the dose estimation. Plans resulting from KBP optimization using each model were very similar. Populating a KBP model with CHO data resulted in a high quality model. Since CHO plans can be generated automatically offline in a process that necessitates little to no user interaction, a CHO-KBP model can quickly adapt to changes in plan evaluation criteria or planning techniques without the need to wait to accrue sufficient numbers of clinical TEO plans. This may facilitate the use of KBP approaches for initial or ongoing quality assurance procedures and plan quality audits.

OA035] Implementation of RapidPlan for head and neck cancer patients: The dosimetric advantages

Purpose To evaluate a RapidPlan (RP) knowledge-based planning model, generated for advanced head and neck cancer (HNC) patients. Methods Dosimetric and geometric data from 75 HNC patients were selected for model training. Volumetric modulated arc therapy using three arcs were used for all plans. Four different dose regimes, with either two or three dose levels, were combined in the model (60 Gy, 50 Gy in 30 fractions, 66 Gy, 60 Gy, 50 Gy in 34 fractions, 68 Gy, 60 Gy, 50 Gy in 33 fractions, and 76 Gy, 66 Gy, 56 Gy in 56 fractions). DVH estimates were generated for all organs at risk (OAR) and the order of their associated priorities followed national guidelines. The model was validated on 20 HNC patients, all with prescribed high dose levels of 66 Gy. For each patient a clinical and a RP plan were individually optimized based on either the clinical template or the RP DVH suggestions, respectively. The two plans were compared according to target dose coverage and mean doses to the brainstem, salivary glands, oral cavity, lips, thyroid, and swallowing structures. Results Target coverages were very similar for both planning strategies. For the planning target volumes receiving 95% of the prescribed doses, the average changes between the clinical plans and RP plans, were −0.07 ± 0.4%p, 0.11 ± 0.5%p, and −0.08 ± 0.4%p, respectively. Mean doses to all OARs were unchanged except for the thyroid, the pharyngeal constrictors and the glottis larynx, where a significant improvement was observed. The median mean doses were reduced by 0.5 Gy (p = 0.048), 1.0 Gy (p = 0.027), 3.8 Gy (p = 0.0001), 2.9 Gy (p = 0.0003) and 3.9 Gy (p = 0.0013), respectively. Furthermore for 25% of the patients the mean dose to the glottis larynx, the middle and the lower pharyngeal constrictor are lowered by at least 8.9 Gy, 6.3 Gy and 5.2 Gy, respectively. Conclusions Using RP for knowledge-based planning of HNC patients significantly improves the mean doses received by a number of OAR, without changing the mean doses received by the remaining OAR and without deteriorating the target coverage.

Creation of knowledge-based planning models intended for large scale distribution: Minimizing the effect of outlier plans.

Knowledge‐based planning (KBP) can be used to estimate dose–volume histograms (DVHs) of organs at risk (OAR) using models. The task of model creation, however, can result in estimates with differing accuracy; particularly when outlier plans are not properly addressed. This work used RapidPlan™ to create models for the prostate and head and neck intended for large‐scale distribution. Potential outlier plans were identified by means of regression analysis scatter plots, Cook's distance, coefficient of determination, and the chi‐squared test. Outlier plans were identified as falling into three categories: geometric, dosimetric, and over‐fitting outliers. The models were validated by comparing DVHs estimated by the model with those from a separate and independent set of clinical plans. The estimated DVHs were also used as optimization objectives during inverse planning. The analysis tools lead us to identify as many as 7 geometric, 8 dosimetric, and 20 over‐fitting outliers in the raw models. Geometric and over‐fitting outliers were removed while the dosimetric outliers were replaced after re‐planning. Model validation was done by comparing the DVHs at 50%, 85%, and 99% of the maximum dose for each OAR (denoted as V50, V85, and V99) and agreed within −2% to 4% for the three metrics for the final prostate model. In terms of the head and neck model, the estimated DVHs agreed from −2.0% to 5.1% at V50, 0.1% to 7.1% at V85, and 0.1% to 7.6% at V99. The process used to create these models improved the accuracy for the pharyngeal constrictor DVH estimation where one plan was originally over‐estimated by more than twice. In conclusion, our results demonstrate that KBP models should be carefully created since their accuracy could be negatively affected by outlier plans. Outlier plans can be addressed by removing them from the model and re‐planning.

Functional-guided radiotherapy using knowledge-based planning

Background and purposeThere are two significant challenges when implementing functional-guided radiotherapy using 4DCT-ventilation imaging: (1) lack of knowledge of realistic patient specific dosimetric goals for functional lung and (2) ensuring consistent plan quality across multiple planners. Knowledge-based planning (KBP) is positioned to address both concerns. Material and methodsA KBP model was created from 30 previously planned functional-guided lung patients. Standard organs at risk (OAR) in lung radiotherapy and a ventilation contour delineating areas of high ventilation were included. Model validation compared dose-metrics to standard OARs and functional dose-metrics from 20 independent cases that were planned with and without KBP. ResultsA significant improvement was observed for KBP optimized plans in V20Gy and mean dose to functional lung (p = 0.005 and 0.001, respectively), V20Gy and mean dose to total lung minus GTV (p = 0.002 and 0.01, respectively), and mean doses to esophagus (p = 0.005). ConclusionThe current work developed a KBP model for functional-guided radiotherapy. Modest, but statistically significant, improvements were observed in functional lung and total lung doses.

An Ensemble Approach to Knowledge-Based Intensity-Modulated Radiation Therapy Planning.

Knowledge-based planning (KBP) utilizes experienced planners’ knowledge embedded in prior plans to estimate optimal achievable dose volume histogram (DVH) of new cases. In the regression-based KBP framework, previously planned patients’ anatomical features and DVHs are extracted, and prior knowledge is summarized as the regression coefficients that transform features to organ-at-risk DVH predictions. In our study, we find that in different settings, different regression methods work better. To improve the robustness of KBP models, we propose an ensemble method that combines the strengths of various linear regression models, including stepwise, lasso, elastic net, and ridge regression. In the ensemble approach, we first obtain individual model prediction metadata using in-training-set leave-one-out cross validation. A constrained optimization is subsequently performed to decide individual model weights. The metadata is also used to filter out impactful training set outliers. We evaluate our method on a fresh set of retrospectively retrieved anonymized prostate intensity-modulated radiation therapy (IMRT) cases and head and neck IMRT cases. The proposed approach is more robust against small training set size, wrongly labeled cases, and dosimetric inferior plans, compared with other individual models. In summary, we believe the improved robustness makes the proposed method more suitable for clinical settings than individual models.

Improving Quality and Consistency in NRG Oncology Radiation Therapy Oncology Group 0631 for Spine Radiosurgery via Knowledge-Based Planning

Touse knowledge-based planning (KBP) as a method of producing high-quality, consistent, protocol-compliant treatment plans in a complex setting of spine stereotactic body radiation therapy on NRG Oncology Radiation Therapy Oncology Group (RTOG)0631. An internally developed KBP model was applied to an external validation cohort of 22 anonymized cases submitted under NRG Oncology RTOG 0631. The original and KBP plans were compared via their protocol compliance, target conformity and gradient index, dose to critical structures, and dose to surrounding normal tissues. The KBP model generated plans meeting all protocol objectives in a single optimization when tested on both internal and protocol-submitted NRG Oncology RTOG 0631 cases. Two submitted plans that were considered to have a protocol-unacceptable deviation were made protocol compliant through the use of the model. There were no statistically significant differences in protocol spinal cord metrics (D10% and D0.03cc) between the manually optimized plans and the KBP plans. The volume of planning target volume receiving prescription dose increased from 93.3%±3.2% to 98.3%±1.4% (P=.01) when using KBP. High-dose spillage to surrounding normal tissues (V105%) showed no significant differences (2.1±7.3cm3 for manual plans to 1.8±0.6cm3 with KBP), and dosimetric outliers with large amounts of spillage were eliminated through the use of KBP. Knowledge-based planning plans were also found to be significantly more consistent in several metrics, including target coverage and high dose outside of the target. Incorporation of KBP models into the clinical trial setting may have a profound impact on the quality of trial results, owing to the increase in consistency and standardization of planning, especially for treatment sites or techniques that are nonstandard.

Knowledge-based treatment planning and its potential role in the transition between treatment planning systems

Commissioning a new treatment planning system (TPS) involves many time-consuming tasks. We investigated the role that knowledge-based planning (KBP) can play in aiding a clinic's transition to a new TPS. Sixty clinically treated prostate/prostate bed intensity-modulated radiation therapy (IMRT) plans were exported from an in-house TPS and were used to create a KBP model in a newly implemented commercial application. To determine the benefit that KBP may have in a TPS transition, the model was tested on 2 groups of patients. Group 1 consisted of the first 10 prostate/prostate bed patients treated in the commercial TPS after the transition from the in-house TPS. Group 2 consisted of 10 patients planned in the commercial TPS after 8 months of clinical use. The KBP-generated plan was compared with the clinically used plan in terms of plan quality (ability to meet planning objectives and overall dose metrics) and planning efficiency (time required to generate clinically acceptable plans). The KBP-generated plans provided a significantly improved target coverage (p = 0.01) compared with the clinically used plans for Group 1, but yielded plans of comparable target coverage to the clinically used plans for Group 2. For the organs at risk, the KBP-generated plans produced lower doses, on average, for every normal-tissue objective except for the maximum dose to 0.1 cc of rectum. The time needed for the KBP-generated plans ranged from 6 to 15 minutes compared to 30 to 150 and 15 to 60 minutes for manual planning in Groups 1 and 2, respectively. KBP is a promising tool to aid in the transition to a new TPS. Our study indicates that high-quality treatment plans could have been generated in the newly implemented TPS more efficiently compared with not using KBP. Even after 8 months of the clinical use, KBP still showed an increase in plan quality and planning efficiency compared with manual planning.

Improving Quality and Consistency in Clinical Trials via Knowledge-Based Planning, NRG Oncology RTOG 0631

Consistency and standardization of radiotherapy planning quality for conducting a multi-institutional clinical trial are always challenging, and non-protocol compliant radiotherapy plans have been shown to impact patient outcomes. This study was aimed to utilize knowledge-based planning (KBP) as a method of producing high quality, consistent, protocol compliant treatment plans, in a complex setting of spine SBRT on RTOG 0631. An internally developed KBP model was applied to an external validation cohort of 22 anonymized cases submitted to NRG for RTOG 0631. The original and KBP plans were compared via their protocol scores, target conformity and gradient index, dose to critical structures, and dose to surrounding normal tissues. The KBP model generated plans meeting all protocol objectives in a single optimization when tested on both internal and external RTOG 0631 cases. Two external plans that were considered to have a protocol-unacceptable deviation were made protocol compliant through the use of the model. There were no statistically significant differences in conformity or gradient indices between the manually optimized plans and the KBP plans. The volume of PTV receiving prescription dose increased from 93.3 ± 3.2% to 99.5 ± 0.7% (P<0.001) when using KBP. High-dose spillage to surrounding normal tissues (V105%) showed no significant differences (2.1 ± 7.3 cc for manual plans to 1.2 ± 0.4 cc with KBP), and dosimetric outliers with large amounts of spillage were eliminated through the use of KBP. Incorporation of KBP models into the clinical trial setting may have a profound impact on the quality of trial results due to the increase in consistency and standardization of planning, especially for treatment sites or techniques that are non-standard. The KBP model will be made available on the Center for Innovation in Radiation Oncology website.

Evaluation of Knowledge-Based Versus Manual Treatment Planning of Whole-Pelvic Volumetric Modulated Arc Therapy With Simultaneous Integrated Boost for Node-Positive Prostate Cancer

The aim of this study is to evaluate the effectiveness and usability of knowledge-based planning (KBP) software in whole-pelvic volumetric modulated arc therapy with simultaneous integrated boost (WP-SIB-VMAT) for node-positive prostate cancer (NP-PC). A commercial KBP software was used for KBP model construction and plan optimization. Twenty-two planning data of the patients with NP-PC who had been treated with WP-SIB-VMAT in our department were used for KBP model construction. Another 32 planning data of the patients with NP-PC who had been treated with whole-pelvic fixed-gantry intensity modulated radiation therapy with SIB in our department were used for validation. The structure sets included high-, intermediate-, low-risk PTVs, and 5 organs at risk (OARs): femurs, large bowel, small bowel, bladder, and rectum. The patients were numbered according to the date of starting irradiation. Experienced medical physicist “A” and radiation oncologist “B” manually performed the optimization of WP-SIB-VMAT in patient 01-16 (Manual A), and patient 17-32 (Manual B), respectively. Resident “C” performed the optimization of WP-SIB-VMAT in patient 01-32 with use of the KBP model. He followed the rule that adjustments of optimizing objectives for PTVs with automatically generated priorities and line objectives for OARs were forbidden. For adjustment of dose to OARs, he was allowed to manually add new objectives and structures against anatomical contours. All optimizations were performed to satisfy the clinical protocol in our department. We measured the required time for optimization, and assessed the dose distributions. Two-tailed Wilcoxon signed-rank sum tests were used to identify significant (p < 0.05) differences in the required time and the mean doses to OARs. The median required time for optimization was significantly shorter in KBP than in manual planning. Similarly, except for the rectum, the median mean doses to OARs were significantly lower in KBP. The median mean dose to the rectum in Manual A plans was significantly lower than in KBP plans. Although dose coverage in protruded region of low-risk PTV, especially in obturator lymph node region, was tended to be lower in KBP plans, the dose distributions of these were considered to be clinically acceptable. No significant change was observed in KBP plans when the number of plans included in the model was increased up to 40.Abstract 3576MedianManual AKBPP valueManual BKBPP valueTime [min]48.534.0<0.0565.531.0<0.05Femurs Dmean [Gy]25.522.8<0.0525.622.7<0.05Large bowel Dmean [Gy]25.022.7<0.0525.021.7<0.05Small bowel Dmean [Gy]19.817.2<0.0521.218.5<0.05Bladder Dmean [Gy]45.343.8<0.0544.944.0<0.05Rectum Dmean [Gy]40.542.4<0.0545.142.1<0.05 Open table in a new tab Although minor manual adjustments were required to achieve the clinical goals in some cases, the KBP software generated comparable plans in significantly shorter time than manual optimization approach in WP-SIB-VMAT planning for NP-PC.

Evaluating inter-campus plan consistency using a knowledge based planning model

Background and purposeWe investigate whether knowledge based planning (KBP) can identify systematic variations in intensity modulated radiotherapy (IMRT) plans between multiple campuses of a single institution. Material and methodsA KBP model was constructed from 58 prior main campus (MC) esophagus IMRT radiotherapy plans and then applied to 172 previous patient plans across MC and 4 regional sites (RS). The KBP model predicts DVH bands for each organ at risk which were compared to the previously planned DVHs for that patient. ResultsRS1’s plans were the least similar to the model with less heart and stomach sparing, and more variation in liver dose, compared to MC. RS2 produced plans most similar to those expected from the model. RS3 plans displayed more variability from the model prediction but overall, the DVHs were no worse than those of MC. RS4 did not present any statistically significant results due to the small sample size (n=11). ConclusionsKBP can retrospectively highlight subtle differences in planning practices, even between campuses of the same institution. This information can be used to identify areas needing increased consistency in planning output and subsequently improve consistency and quality of care.

MO-G-201-02: Comparing Sample Size Requirements for Knowledge-Based Treatment Planning

Purpose: To compare how training set size affects the accuracy of a knowledge-based planning (KBP) model applied to prostate and head and neck (HN) cancer. Methods: We selected a KBP model from the literature that uses distance-to-target histograms and organ volumes to predict an achievable dose-volume-histogram (DVH) curve for each organ-at-risk (OAR). We trained both the prostate and HN model using training set sizes of n=10, 20, 30, 50,75, and 100. We set aside 100 randomly selected treatment plans from each of the two respective cohorts of 218 to serve as a validation set for all experiments. For each value of n, we randomly selected 100 different training sets with replacement from the remaining 118 plans. Each of the 100 training sets was used to train a model for each value of n and for both prostate and HN. To evaluate the models we predicted DVH curves for each of the 100 plans in the validation set. To estimate the minimum required sample size, we used the rank-sum test to determine if the median error for each sample size from 10 to 75 was equal to the median error for the maximum sample size of 100. Results: In general, larger sample sizes were required for HN compared to prostate. For prostate, a minimum training set size of 30 plans was needed to accurately predict the bladder DVH, while at least 75 plans were needed for the rectum. For HN, the minimum training set size was 100 for the larynx esophagus and spinal cord, 75 for the left parotid and mandible, and only 50 for the right parotid. Conclusion: The minimum sample size required for accurate treatment plan generation using KBP is OAR and site dependent. Adequate sample sizes are essential for successful clinical implementation of KBP models. This research was funded in part by the Natural Sciences and Engineering Research Council of Canada.

SU‐G‐TeP4‐14: Quality Control of Treatment Planning Using Knowledge‐Based Planning Across a System of Radiation Oncology Practices

Purpose:There is potentially a wide variation in plan quality for a certain disease site, even for clinics located in the same system of hospitals. We have used a prostate‐specific knowledge‐based planning (KBP) model as a quality control tool to investigate the variation in prostate treatment planning across a network of affiliated radiation oncology departments.Methods:A previously created KBP model was applied to 10 patients each from 4 community‐based clinics (Clinics A, B, C, and D). The KBP model was developed using RapidPlan (Eclipse v13.5, Varian Medical Systems) from 60 prostate/prostate bed IMRT plans that were originally planned using an in‐house treatment planning system at the central institution of the community‐based clinics. The dosimetric plan quality (target coverage and normal‐tissue sparing) of each model‐generated plan was compared to the respective clinically‐used plan. Each community‐based clinic utilized the same planning goals to develop the clinically‐used plans that were used at the main institution.Results:Across all 4 clinics, the model‐generated plans decreased the mean dose to the rectum by varying amounts (on average, 12.5, 2.6, 4.5, and 2.7 Gy for Clinics A, B, C, and D, respectively). The mean dose to the bladder also decreased with the model‐generated plans (5.4, 2.3, 3.0, and 4.1 Gy, respectively). The KBP model also identified that target coverage (D95%) improvements were possible for for Clinics A, B, and D (0.12, 1.65, and 2.75%) while target coverage decreased by 0.72% for Clinic C, demonstrating potentially different trade‐offs made in clinical plans at different institutions.Conclusion:Quality control of dosimetric plan quality across a system of radiation oncology practices is possible with knowledge‐based planning. By using a quality KBP model, smaller community‐based clinics can potentially identify the areas of their treatment plans that may be improved, whether it be in normal‐tissue sparing or improved target coverage.M. Matuszak has research funding for KBP from Varian Medical Systems

Knowledge-based planning for stereotactic body radiation therapy (SBRT) of the liver.

375 Background: SBRT is emerging as a treatment option for patients with unresectable liver tumors. However, generating high quality liver SBRT plans is technically challenging and user-dependent. Aiming for high tumor doses and low normal tissue doses can demand lengthy planning times and result in plans of inconsistent quality. This study investigates knowledge-based planning (KBP) as a standardized method to ensure efficacy, safety, and efficiency for SBRT plans and allow for broader use of this therapy. Methods: SBRT treatment plans were manually optimized for 55 liver cancer cases by an expert liver dosimetrist in a commercial treatment planning system (Varian Eclipse v13.6). Each volumetric modulated arc therapy plan was approved by a physician using strict criteria for target coverage and normal tissue sparing. The plans were used to create a custom model in a KBP system (RapidPlan, Varian Eclipse v13.6) designed to improve both efficiency and standardization of quality. To validate the model, 15 new cases were optimized manually by an expert liver dosimetrist and then semi-automatically using the KBP model. The validation plans were compared based on target coverage, normal tissue sparing, and planning time. Results: Compared to manual plans created by an expert liver dosimetrist, KBP-generated plans showed similar target coverage and improved normal tissue sparing with similar planning times. Mean and minimum target doses were similar, as was D98, p &gt; 0.2 for all. Normal tissue complication probability for liver damage was marginally lower with KBP, mean 3 vs. 1%, p = 0.07. Doses to adjacent organs including stomach, heart, and bowel were similar. Manual planning required a median and mean time of 15 and 20 minutes, respectively, range 8-55 min. KBP required similar times of 12 and 19 min, range 8-50 min. 9 of 15 KBP cases were automated, while 6 plans required dosimetrist improvement. Conclusions: Using KBP, high quality plans for liver SBRT can be created automatically or semi-automatically. These plans are comparable to those generated by an expert liver dosimetrist. KBP could be used to standardize treatments between institutions, particularly when experience with liver SBRT is limited.

SU‐E‐J‐244: Development and Validation of a Knowledge Based Planning Model for External Beam Radiation Therapy of Locally Advanced Non‐Small Cell Lung Cancer

Purpose:The study aims to develop and validate a knowledge based planning (KBP) model for external beam radiation therapy of locally advanced non‐small cell lung cancer (LA‐NSCLC).Methods:RapidPlan™ technology was used to develop a lung KBP model. Plans from 65 patients with LA‐NSCLC were used to train the model. 25 patients were treated with VMAT, and the other patients were treated with IMRT. Organs‐at‐risk (OARs) included right lung, left lung, heart, esophagus, and spinal cord. DVH and geometric distribution DVH were extracted from the treated plans. The model was trained using principal component analysis and step‐wise multiple regression. Box plot and regression plot tools were used to identify geometric outliers and dosimetry outliers and help fine‐tune the model. The validation was performed by (a) comparing predicted DVH boundaries to actual DVHs of 63 patients and (b) using an independent set of treatment planning data.Results:63 out of 65 plans were included in the final KBP model with PTV volume ranging from 102.5cc to 1450.2cc. Total treatment dose prescription varied from 50Gy to 70Gy based on institutional guidelines. One patient was excluded due to geometric outlier where 2.18cc of spinal cord was included in PTV. The other patient was excluded due to dosimetric outlier where the dose sparing to spinal cord was heavily enforced in the clinical plan. Target volume, OAR volume, OAR overlap volume percentage to target, and OAR out‐of‐field volume were included in the trained model. Lungs and heart had two principal component scores of GEDVH, whereas spinal cord and esophagus had three in the final model. Predicted DVH band (mean ±1 standard deviation) represented 66.2±3.6% of all DVHs.Conclusion:A KBP model was developed and validated for radiotherapy of LA‐NSCLC in a commercial treatment planning system. The clinical implementation may improve the consistency of IMRT/VMAT planning.

SU‐E‐T‐530: Knowledge‐Based Treatment Planning and Its Potential Role in the Transition Between Treatment Planning Systems

Purpose:Commissioning a treatment planning system (TPS) involves many tasks, including making sure users have sufficient training and experience to create quality plans. We investigated the role that knowledge‐based planning (KBP) can play in aiding a clinic's transition to a new TPS.Methods:60 clinically treated prostate and prostate bed IMRT plans were exported from an in‐house TPS and used to create a KBP‐model in a newly introduced commercial TPS (Eclipse v13.5, Varian Medical Systems). To determine the benefit that KBP may have in a TPS transition, the model was tested on two groups. Group 1 consisted of the first 10 patients treated in the commercial TPS after the transition from the in‐house TPS, Group 2 consisted of 10 patients planned in the commercial TPS, but without the KBP model, after 8 months of clinical use. The KBP‐generated plan for each patient was compared to the clinically‐used plan in terms of quality and planning efficiency.Results:On average, the KBP‐generated plans provided better target coverage for group 1 than the clinical plans,and about equivalent coverage for group 2. The average absolute difference (KBP‐clinical) for D95 for the PTV was 0.48±0.49% and −0.11±0.48% for groups 1 and 2, respectively. For the OARs, the KBP‐generated plans produced lower doses for every normal tissue objective except the maximum dose to 0.1cc of rectum (0.50±0.27Gy and 0.22±0.17Gy for groups 1 and 2, respectively). The time needed for KBP‐generated plans ranged from 6– 15min compared to 30–150 and 15–60min for groups 1 and 2, respectively.Conclusion:Knowledge‐based planning is a promising tool to aid in transitions to new TPSs. Our study indicates that high‐quality treatment plans could have been generated in the new TPS more efficiently compared to not using KBP. Even after 8 months of clinical use, KBP still showed a quality and efficiency increase compared to manual planning.Partially supported by Varian Medical Systems