Independent knowledge-based treatment planning QA to audit Pinnacle autoplanning

Inter-institutional variability of knowledge-based plan prediction of left whole breast irradiation

PURPOSE

Within a multi-institutional project, we aimed to assess the transferability of knowledge-based (KB) plan prediction models in the case of whole breast irradiation (WBI) for left-side breast irradiation with tangential fields (TF).

METHODS

Eight institutions set KB models, following previously shared common criteria. Plan prediction performance was tested on 16 new patients (2 pts per centre) extracting dose-volume-histogram (DVH) prediction bands of heart, ipsilateral lung, contralateral lung and breast. The inter-institutional variability was quantified by the standard deviations (SDint) of predicted DVHs and mean-dose (Dmean). The transferability of models, for the heart and the ipsilateral lung, was evaluated by the range of geometric Principal Component (PC1) applicability of a model to test patients of the other 7 institutions.

RESULTS

SDint of the DVH was 1.8 % and 1.6 % for the ipsilateral lung and the heart, respectively (20 %-80 % dose range); concerning Dmean, SDint was 0.9 Gy and 0.6 Gy for the ipsilateral lung and the heart, respectively (<0.2 Gy for contralateral organs). Mean predicted doses ranged between 4.3 and 5.9 Gy for the ipsilateral lung and 1.1-2.3 Gy for the heart. PC1 analysis suggested no relevant differences among models, except for one centre showing a systematic larger sparing of the heart, concomitant to a worse PTV coverage, due to high priority in sparing the left anterior descending coronary artery.

CONCLUSIONS

Results showed high transferability among models and low inter-institutional variability of 2% for plan prediction. These findings encourage the building of benchmark models in the case of TF-WBI.

Deep learning-based dose map prediction for high-dose-rate brachytherapy

Background. Creating a clinically acceptable plan in the time-sensitive clinic workflow of brachytherapy is challenging. Deep learning-based dose prediction techniques have been reported as promising solutions with high efficiency and accuracy. However, current dose prediction studies mainly target EBRT which are inappropriate for brachytherapy, the model designed specifically for brachytherapy has not yet well-established.Purpose. To predict dose distribution in brachytherapy using a novel Squeeze and Excitation Attention Net (SE_AN) model.Method. We hypothesized the tracks of192Ir inside applicators are essential for brachytherapy dose prediction. To emphasize the applicator contribution, a novel SE module was integrated into a Cascaded UNet to recalibrate informative features and suppress less useful ones. The Cascaded UNet consists of two stacked UNets, with the first designed to predict coarse dose distribution and the second added for fine-tuning 250 cases including all typical clinical applicators were studied, including vaginal, tandem and ovoid, multi-channel, and free needle applicators. The developed SE_AN was subsequently compared to the classic UNet and classic Cascaded UNet (without SE module) models. The model performance was evaluated by comparing the predicted dose against the clinically approved plans using mean absolute error (MAE) of DVH metrics, includingD2ccandD90%.Results. The MAEs of DVH metrics demonstrated that SE_AN accurately predicted the dose with 0.37 ± 0.25 difference for HRCTVD90%, 0.23 ± 0.14 difference for bladderD2cc, and 0.28 ± 0.20 difference for rectumD2cc. In comparison studies, UNet achieved 0.34 ± 0.24 for HRCTV, 0.25 ± 0.20 for bladder, 0.25 ± 0.21 for rectum, and Cascaded UNet achieved 0.42 ± 0.31 for HRCTV, 0.24 ± 0.19 for bladder, 0.23 ± 0.19 for rectum.Conclusion. We successfully developed a method specifically for 3D brachytherapy dose prediction. Our model demonstrated comparable performance to clinical plans generated by experienced dosimetrists. The developed technique is expected to improve the standardization and quality control of brachytherapy treatment planning.

A personalized DVH prediction model for HDR brachytherapy in cervical cancer treatment

Purpose

Although the knowledge-based dose-volume histogram (DVH) prediction has been largely researched and applied in External Beam Radiation Therapy, it is still less investigated in the domain of brachytherapy. The purpose of this study is to develop a reliable DVH prediction method for high-dose-rate brachytherapy plans.

Method

A DVH prediction workflow combining kernel density estimation (KDE), k-nearest neighbor (kNN), and principal component analysis (PCA) was proposed. PCA and kNN were first employed together to select similar patients based on principal component directions. 79 cervical cancer patients with different applicators inserted was included in this study. The KDE model was built based on the relationship between distance-to-target (DTH) and the dose in selected cases, which can be subsequently used to estimate the dose probability distribution in the validation set. Model performance of bladder and rectum was quantified by |ΔD_2cc|, |ΔD_1cc|, |ΔD_0.1cc|, |ΔD_max|, and |ΔD_mean| in the form of mean and standard deviation. The model performance between KDE only and the combination of kNN, PCA, and KDE was compared.

Result

20, 30 patients were selected for rectum and bladder based on KNN and PCA, respectively. The absolute residual between the actual plans and the predicted plans were 0.38 ± 0.29, 0.4 ± 0.32, 0.43 ± 0.36, 0.97 ± 0.66, and 0.13 ± 0.99 for |ΔD_2cc|, |ΔD_1cc|, |ΔD_0.1cc|, |ΔD_max|, and |ΔD_mean| in the bladder, respectively. For rectum, the corresponding results were 0.34 ± 0.27, 0.38 ± 0.33, 0.63 ± 0.57, 1.41 ± 0.99 and 0.23 ± 0.17, respectively. The combination of kNN, PCA, and KDE showed a significantly better prediction performance than KDE only, with an improvement of 30.3% for the bladder and 33.3% for the rectum.

Conclusion

In this study, a knowledge-based machine learning model was proposed and verified to accurately predict the DVH for new patients. This model is proved to be effective in our testing group in the workflow of HDR brachytherapy.

Fast VMAT planning for prostate radiotherapy: dosimetric validation of a deep learning-based initial segment generation method

Objective. To develop and evaluate a deep learning based fast volumetric modulated arc therapy (VMAT) plan generation method for prostate radiotherapy. Approach. A customized 3D U-Net was trained and validated to predict initial segments at 90 evenly distributed control points of an arc, linked to our research treatment planning system (TPS) for segment shape optimization (SSO) and segment weight optimization (SWO). For 27 test patients, the VMAT plans generated based on the deep learning prediction (VMATDL) were compared with VMAT plans generated with a previously validated automated treatment planning method (VMATref). For all test cases, the deep learning prediction accuracy, plan dosimetric quality, and the planning efficiency were quantified and analyzed. Main results. For all 27 test cases, the resulting plans were clinically acceptable. The V 95% for the PTV2 was greater than 99%, and the V 107% was below 0.2%. Statistically significant difference in target coverage was not observed between the VMATref and VMATDL plans (P = 0.3243 > 0.05). The dose sparing effect to the OARs between the two groups of plans was similar. Small differences were only observed for the Dmean of rectum and anus. Compared to the VMATref, the VMATDL reduced 29.3% of the optimization time on average. Significance. A fully automated VMAT plan generation method may result in significant improvement in prostate treatment planning efficiency. Due to the clinically acceptable dosimetric quality and high efficiency, it could potentially be used for clinical planning application and real-time adaptive therapy application after further validation.

Knowledge-based multi-institution plan prediction of whole breast irradiation with tangential fields

PURPOSE

To quantify inter-institute variability of Knowledge-Based (KB) models for right breast cancer patients treated with tangential fields whole breast irradiation (WBI).

MATERIALS AND METHODS

Ten institutions set KB models by using RapidPlan (Varian Inc.), following previously shared methodologies. Models were tested on 20 new patients from the same institutes, exporting DVH predictions of heart, ipsilateral lung, contralateral lung, and contralateral breast. Inter-institute variability was quantified by the inter-institute SD_int of predicted DVHs/Dmean. Association between lung sparing vs PTV coverage strategy was also investigated. The transferability of models was evaluated by the overlap of each model's geometric Principal Component (PC1) when applied to the test patients of the other 9 institutes.

RESULTS

The overall inter-institute variability of DVH/Dmean ipsilateral lung dose prediction, was less than 2% (20%-80% dose range) and 0.55 Gy respectively (1SD) for a 40 Gy in 15 fraction schedule; it was < 0.2 Gy for other OARs. Institute 6 showed the lowest mean dose prediction value and no overlap between PTV and ipsilateral lung. Once excluded, the predicted ipsilateral lung Dmean was correlated with median PTV D99% (R² = 0.78). PC1 values were always within the range of applicability (90th percentile) for 7 models: for 2 models they were outside in 1/18 cases. For the model of institute 6, it failed in 7/18 cases. The impact of inter-institute variability of dose calculation was tested and found to be almost negligible.

CONCLUSIONS

Results show limited inter-institute variability of plan prediction models translating in high inter-institute interchangeability, except for one of ten institutes. These results encourage future investigations in generating benchmarks for plan prediction incorporating inter-institute variability.

Evaluation of two independent dose prediction methods to personalize the automated radiotherapy planning process for prostate cancer

Background and purpose

Currently, automatic approaches for radiotherapy planning are widely used, however creation of high quality treatment plans is still challenging. In this study, two independent dose prediction methods were used to personalize the initial settings for the automated planning template for optimizing prostate cancer treatment plans. This study evaluated the dose metrics of these plans comparing both methods with the current clinical automated prostate cancer treatment plans.

Material and methods

Datasets of 20 high-risk prostate cancer treatment plans were taken from our clinical database. The prescription dose for these plans was 70 Gy given in fractions of 2.5 Gy. Plans were replanned using the current clinical automated treatment and compared with two personalized automated planning methods. The feasibility dose volume histogram (FDVH) and modified filter back projection (mFBP) methods were used to calculate independent dose predictions. Parameters for the initial objective values of the planning template were extracted from these predictions and used to personalize the optimization of the automated planning process.

Results

The current automated replanned clinical plans and the automated plans optimized with the personalized template methods fulfilled the clinical dose criteria. For both methods a reduction in the average mean dose of the rectal wall was found, from 22.5 to 20.1 Gy for the FDVH and from 22.5 to 19.6 Gy for the mFBP method.

Conclusions

With both dose-prediction methods the initial settings of the template could be personalized. Hereby, the average dose to the rectal wall was reduced compared to the standard template method.

Knowledge-based radiation treatment planning: A data-driven method survey

This paper surveys the data-driven dose prediction methods investigated for knowledge-based planning (KBP) in the last decade. These methods were classified into two major categories-traditional KBP methods and deep-learning (DL) methods-according to their techniques of utilizing previous knowledge. Traditional KBP methods include studies that require geometric or anatomical features to either find the best-matched case(s) from a repository of prior treatment plans or to build dose prediction models. DL methods include studies that train neural networks to make dose predictions. A comprehensive review of each category is presented, highlighting key features, methods, and their advancements over the years. We separated the cited works according to the framework and cancer site in each category. Finally, we briefly discuss the performance of both traditional KBP methods and DL methods, then discuss future trends of both data-driven KBP methods to dose prediction.

Characterization of automatic treatment planning approaches in radiotherapy

•

Auto-Planning is widely used, yet creation of high quality treatment plans remains challenging.

•

Systematic investigation of behavior and optimal use of Auto-Planning.

•

Widely applicable solutions to create optimal plans.

•

Auto-Planning outperforms manual plans in DVH metrics and blind comparisons.

Background and purpose

Automatic approaches are widely implemented to automate dose optimization in radiotherapy treatment planning. This study systematically investigates how to configure automatic planning in order to create the best possible plans.

Materials and methods

Automatic plans were generated using protocol based automatic iterative optimization. Starting from a simple automation protocol which consisted of the constraints for targets and organs at risk (OAR), the performance of the automatic approach was evaluated in terms of target coverage, OAR sparing, conformity, beam complexity, and plan quality. More complex protocols were systematically explored to improve the quality of the automatic plans. The protocols could be improved by adding a dose goal on the outer 2 mm of the PTV, by setting goals on strategically chosen subparts of OARs, by adding goals for conformity, and by limiting the leaf motion. For prostate plans, development of an automated post-optimization procedure was required to achieve precise control over the dose distribution. Automatic and manually optimized plans were compared for 20 head and neck (H&N), 20 prostate, and 20 rectum cancer patients.

Results

Based on simple automation protocols, the automatic optimizer was not always able to generate adequate treatment plans. For the improved final configurations for the three sites, the dose was lower in automatic plans compared to the manual plans in 12 out of 13 considered OARs. In blind tests, the automatic plans were preferred in 80% of cases.

Conclusions

With adequate, advanced, protocols the automatic planning approach is able to create high-quality treatment plans.

Evaluation of fully automated a priori MCO treatment planning in VMAT for head-and-neck cancer

PURPOSE

Automated planning techniques aim to reduce manual planning time and inter-operator variability without compromising the plan quality which is particularly challenging for head-and-neck (HN) cancer radiotherapy. The objective of this study was to evaluate the performance of an a priori-multicriteria plan optimization algorithm on a cohort of HN patients.

METHODS

A total of 14 nasopharyngeal carcinoma (upper-HN) and 14 "middle-lower indications" (lower-HN) previously treated in our institution were enrolled in this study. Automatically generated plans (autoVMAT) were compared to manual VMAT or Helical Tomotherapy planning (manVMAT-HT) by assessing differences in dose delivered to targets and organs at risk (OARs), calculating plan quality indexes (PQIs) and performing blinded comparisons by clinicians. Quality control of the plans and measurements of the delivery times were also performed.

RESULTS

For the 14 lower-HN patients, with equivalent planning target volume (PTV) dosimetric criteria and dose homogeneity, significant decrease in the mean doses to the oral cavity, esophagus, trachea and larynx were observed for autoVMAT compared to manVMAT-HT. Regarding the 14 upper-HN cases, the PTV coverage was generally significantly superior for autoVMAT which was also confirmed with higher calculated PQIs on PTVs for 13 out of 14 patients, whereas PQIs calculated on OARs were generally equivalent. Number of MUs and total delivery time were significantly higher for autoVMAT compared to manVMAT. All plans were considered clinically acceptable by clinicians.

CONCLUSIONS

Overall superiority of autoVMAT compared to manVMAT-HT plans was demonstrated for HN cancer. The obtained plans were operator-independent and required no post-optimization or manual intervention.

A Review on Application of Deep Learning Algorithms in External Beam Radiotherapy Automated Treatment Planning

Treatment planning plays an important role in the process of radiotherapy (RT). The quality of the treatment plan directly and significantly affects patient treatment outcomes. In the past decades, technological advances in computer and software have promoted the development of RT treatment planning systems with sophisticated dose calculation and optimization algorithms. Treatment planners now have greater flexibility in designing highly complex RT treatment plans in order to mitigate the damage to healthy tissues better while maximizing radiation dose to tumor targets. Nevertheless, treatment planning is still largely a time-inefficient and labor-intensive process in current clinical practice. Artificial intelligence, including machine learning (ML) and deep learning (DL), has been recently used to automate RT treatment planning and has gained enormous attention in the RT community due to its great promises in improving treatment planning quality and efficiency. In this article, we reviewed the historical advancement, strengths, and weaknesses of various DL-based automated RT treatment planning techniques. We have also discussed the challenges, issues, and potential research directions of DL-based automated RT treatment planning techniques.

Treatment plan quality assessment for radiotherapy of rectal cancer patients using prediction of organ-at-risk dose metrics

Background and purpose

Radiotherapy centers frequently lack simple tools for periodic treatment plan verification and feedback on current plan quality. It is difficult to measure treatment quality over different years or during the planning process. Here, we implemented plan quality assurance (QA) by developing a database of dose-volume histogram (DVH) metrics and a prediction model. These tools were used to assess automatically optimized treatment plans for rectal cancer patients, based on cohort analysis.

Material and methods

A treatment plan QA framework was established and an overlap volume histogram based model was used to predict DVH parameters for cohorts of patients treated in 2018 and 2019 and grouped according to planning technique. A training cohort of 22 re-optimized treatment plans was used to make the prediction model. The prediction model was validated on 95 automatically generated treatment plans (automatically optimized cohort) and 93 manually optimized plans (manually optimized cohort).

Results

For the manually optimized cohort, on average the prediction deviated less than 0.3 ± 1.4 Gy and −4.3 ± 5.5 Gy, for the mean doses to the bowel bag and bladder, respectively; for the automatically optimized cohort a smaller deviation was observed: −0.1 ± 1.1 Gy and −0.2 ± 2.5 Gy, respectively. The interquartile range of DVH parameters was on average smaller for the automatically optimized cohort, indicating less variation within each parameter compared to manual planning.

Conclusion

An automated framework to monitor treatment quality with a DVH prediction model was successfully implemented clinically and revealed less variation in DVH parameters for automated in comparison to manually optimized plans. The framework also allowed for individual feedback and DVH estimation.

Overview of artificial intelligence-based applications in radiotherapy: Recommendations for implementation and quality assurance

Artificial Intelligence (AI) is currently being introduced into different domains, including medicine. Specifically in radiation oncology, machine learning models allow automation and optimization of the workflow. A lack of knowledge and interpretation of these AI models can hold back wide-spread and full deployment into clinical practice. To facilitate the integration of AI models in the radiotherapy workflow, generally applicable recommendations on implementation and quality assurance (QA) of AI models are presented. For commonly used applications in radiotherapy such as auto-segmentation, automated treatment planning and synthetic computed tomography (sCT) the basic concepts are discussed in depth. Emphasis is put on the commissioning, implementation and case-specific and routine QA of AI models needed for a methodical introduction in clinical practice.

Knowledge-Based Assessment of Focal Dose Escalation Treatment Plans in Prostate Cancer

PURPOSE

In a randomized focal dose escalation radiation therapy trial for prostate cancer (FLAME), up to 95 Gy was prescribed to the tumor in the dose-escalated arm, with 77 Gy to the entire prostate in both arms. As dose constraints to organs at risk had priority over dose escalation and suboptimal planning could occur, we investigated how well the dose to the tumor was boosted. We developed an anatomy-based prediction model to identify plans with suboptimal tumor dose and performed replanning to validate our model.

METHODS AND MATERIALS

We derived dose-volume parameters from planned dose distributions of 539 FLAME trial patients in 4 institutions and compared them between both arms. In the dose-escalated arm, we determined overlap volume histograms and derived features representing patient anatomy. We predicted tumor D98% with a linear regression on anatomic features and performed replanning on 21 plans.

RESULTS

In the dose-escalated arm, the median tumor D50% and D98% were 93.0 and 84.7 Gy, and 99% of the tumors had a dose escalation greater than 82.4 Gy (107% of 77 Gy). In both arms organs at risk constraints were met. Five out of 73 anatomic features were found to be predictive for tumor D98%. Median predicted tumor D98% was 4.4 Gy higher than planned D98%. Upon replanning, median tumor D98% increased by 3.0 Gy. A strong correlation between predicted increase in D98% and realized increase upon replanning was found (ρ = 0.86).

CONCLUSIONS

Focal dose escalation in prostate cancer was feasible with a dose escalation to 99% of the tumors. Replanning resulted in an increased tumor dose that correlated well with the prediction model. The model was able to identify tumors on which a higher boost dose could be planned. The model has potential as a quality assessment tool in focal dose escalated treatment plans.

Can the Student Outperform the Master? A Plan Comparison Between Pinnacle Auto-Planning and Eclipse knowledge-Based RapidPlan Following a Prostate-Bed Plan Competition

Purpose:

Pinnacle Auto-Planning and Eclipse RapidPlan are 2 major commercial automated planning engines that are fundamentally different: Auto-Planning mimics real planners in the iterative optimization, while RapidPlan generates static dose objectives from estimations predicted based on a prior knowledge base. This study objectively compared their performances on intensity-modulated radiotherapy planning for prostate fossa and lymphatics adopting the plan quality metric used in the 2011 American Association of Medical Dosimetrists Plan Challenge.

Methods:

All plans used an identical intensity-modulated radiotherapy beam setup and a simultaneous integrated boost prescription (68 Gy/56 Gy to prostate fossa/lymphatics). Auto-Planning was used to retrospectively plan on 20 patients, which were subsequently employed as the library to build an RapidPlan model. To compare the 2 engines’ performances, a test set including 10 patients and the Plan Challenge patient was planned by both Auto-Planning (master) and RapidPlan (student) without manual intervention except for a common dose normalization and evaluated using the plan quality metric that included 14 quantitative submetrics ranging over target coverage, spillage, and organ at risk doses. Plan quality metric scores were compared between the Auto-Planning and RapidPlan plans using the Mann-Whitney U test.

Results:

There was no significant difference between the overall performance of the 2 engines on the 11 test cases (P = .509). Among the 14 submetrics, Auto-Planning and RapidPlan showed no significant difference on most submetrics except for 2. On the Plan Challenge case, Auto-Planning scored 129.9 and RapidPlan scored 130.3 out of 150, as compared with the average score of 116.9 ± 16.4 (range: 58.2-142.5) among the 125 Plan Challenge participants.

Conclusion:

Using an innovative study design, an objective comparison has been conducted between 2 major commercial automated inverse planning engines. The 2 engines performed comparably with each other and both yielded plans at par with average human planners. Using a constant-performing planner (Auto-Planning) to train and to compare, RapidPlan was found to yield plans no better than but as good as its library plans.

Artificial Intelligence in Radiotherapy: A Philosophical Perspective

The increasing uptake of machine learning solutions for segmentation and planning leaves no doubt that artificial intelligence (AI) will soon be providing input into a range of radiotherapy procedures. Although this promises to deliver increased speed and accuracy, the future role of AI in relation to radiotherapy should be thought through carefully. There is currently a gap between published developments and widespread adoption, which provides some space to prepare the workforce and to consider the implications on practice. It is rare to find philosophical input into a medical journal, but the advent of AI makes this perspective increasingly important. Philosophical insight can help explore the potential impact of AI, in particular, on human creativity and oversight. Without this perspective, we run the risk of focusing solely on the immediate logistical impact on patients and departments. This commentary identifies three key aspects of radiotherapy that the authors feel would suffer most under AI control: creativity, innovation, and patient safety, which all demand uniquely human attributes. The article also provides insight from a philosophical perspective with regard to human consciousness, ethics, and empathy. Philosophically we should, perhaps, retain ethical concerns about the widening role of AI in radiotherapy beyond simple quantitative interpretation and image processing. As developments continue, we have time to determine how our roles will evolve and to establish a framework for ensuring appropriate human input into patient care. Most importantly, we must start to embed a philosophical approach to adoption of AI technology from the outset if we are to prepare ourselves for the challenge that lies ahead.

Evaluation of auto-planning in IMRT and VMAT for head and neck cancer

PURPOSE

The purposes of this work are to (a) investigate whether the use of auto-planning and multiple iterations improves quality of head and neck (HN) radiotherapy plans; (b) determine whether delivery methods such as step-and-shoot (SS) and volumetric modulated arc therapy (VMAT) impact plan quality; (c) report on the observations of plan quality predictions of a commercial feasibility tool.

MATERIALS AND METHODS

Twenty HN cases were retrospectively selected from our clinical database for this study. The first ten plans were used to test setting up planning goals and other optimization parameters in the auto-planning module. Subsequently, the other ten plans were replanned with auto-planning using step-and-shoot (AP-SS) and VMAT (AP-VMAT) delivery methods. Dosimetric endpoints were compared between the clinical plans and the corresponding AP-SS and AP-VMAT plans. Finally, predicted dosimetric endpoints from a commercial program were assessed.

RESULTS

All AP-SS and AP-VMAT plans met the clinical dose constraints. With auto-planning, the dose coverage of the low dose planning target volume (PTV) was improved while the dose coverage of the high dose PTV was maintained. Compared to the clinical plans, the doses to critical organs, such as the brainstem, parotid, larynx, esophagus, and oral cavity were significantly reduced in the AP-VMAT (P < 0.05); the AP-SS plans had similar homogeneity indices (HI) and conformality indices (CI) and the AP-VMAT plans had comparable HI and improved CI. Good agreement in dosimetric endpoints between predictions and AP-VMAT plans were observed in five of seven critical organs.

CONCLUSION

With improved planning quality and efficiency, auto-planning module is an effective tool to enable planners to generate HN IMRT plans that are meeting institution specific planning protocols. DVH prediction is feasible in improving workflow and plan quality.

Adapting automated treatment planning configurations across international centres for prostate radiotherapy

Background and purpose

Automated configurations are increasingly utilised for radiotherapy treatment planning. This study investigates whether automated treatment planning configurations are adaptable across clinics with different treatment planning protocols for prostate radiotherapy.

Material and methods

The study comprised three participating centres, each with pre-existing locally developed prostate AutoPlanning configurations using the Pinnacle³® treatment planning system. Using a three-patient training dataset circulated from each centre, centres modified local prostate configurations to generate protocol compliant treatment plans for the other two centres. Each centre applied modified configurations on validation datasets distributed from each centre (10 patients from 3 centres). Plan quality was assessed through DVH analysis and protocol compliance.

Results

All treatment plans were clinically acceptable, based off relevant treatment protocol. Automated planning configurations from Centre’s A and B recorded 2 and 18 constraint and high priority deviations respectively. Centre C configurations recorded no high priority deviations. Centre A configurations produced treatment plans with superior dose conformity across all patient PTVs (mean = 1.14) compared with Centre’s B and C (mean = 1.24 and 1.22). Dose homogeneity was consistent between all centre’s configurations (mean = 0.083, 0.077, and 0.083 respectively).

Conclusions

This study demonstrates that automated treatment planning configurations can be shared and implemented across multiple centres with simple adaptations to local protocols.

Knowledge-Based Statistical Inference Method for Plan Quality Quantification

Aim:

The aim of the study is to develop a geometrically adaptive and statistically robust plan quality inference method.

Methods and Materials:

We propose a knowledge-based plan quality inference method that references to similar plans in the historical database for patient-specific plan quality evaluation. First, a novel plan similarity metric with high-dimension geometrical difference quantification is utilized to retrieve similar plans. Subsequently, dosimetric statistical inferences are obtained from the selected similar plans. Two plan quality metrics—dosimetric result probability and dose deviation index—are proposed to quantify plan quality among prior similar plans. To evaluate the performance of the proposed method, we exported 927 clinically approved head and neck treatment plans. Eight organs at risk, including brain stem, cord, larynx, mandible, pharynx, oral cavity, left parotid and right parotid, were analyzed. Twelve suboptimal plans identified by dosimetric result probability were replanned to validate the capability of the proposed methods in identifying inferior plans.

Results:

After replanning, left and right parotid median doses are reduced by 31.7% and 18.2%, respectively; 83% of these cases would not be identified as suboptimal without the proposed similarity plan selection. Analysis of population plan quality reveals that average parotid sparing has been improving significantly over time (21.7% dosimetric result probability reduction from year 2006-2007 to year 2016-2017). Notably, the increasing dose sparing over time in retrospective plan quality analysis is strongly correlated with the increasing dose prescription ratios to the 2 planning targets, revealing the collective trend in planning conventions.

Conclusions:

The proposed similar plan retrieval and analysis methodology has been proven to be predictive of the current plan quality. Therefore, the proposed workflow can potentially be applied in the clinics as a real-time plan quality assurance tool. The proposed metrics can also serve the purpose of plan quality analytics in finding connections and historical trends in the clinical treatment planning workflow.