Quantifying Unnecessary Normal Tissue Complication Risks due to Suboptimal Planning: A Secondary Study of RTOG 0126

AS-NeSt: A Novel 3D Deep Learning Model for Radiation Therapy Dose Distribution Prediction in Esophageal Cancer Treatment With Multiple Prescriptions

PURPOSE

Implementing artificial intelligence technologies allows for the accurate prediction of radiation therapy dose distributions, enhancing treatment planning efficiency. However, esophageal cancers present unique challenges because of tumor complexity and diverse prescription types. Additionally, limited data availability hampers the effectiveness of existing artificial intelligence models. This study developed a deep learning model, trained on a diverse data set of esophageal cancer prescriptions, to improve dose prediction accuracy.

METHODS AND MATERIALS

We retrospectively collected data from 530 patients with esophageal cancer, including single-target and simultaneous integrated boost prescriptions, for model building. The proposed Asymmetric ResNeSt (AS-NeSt) model features novel 3-dimensional (3D) ResNeSt blocks and an asymmetrical architecture. We constructed a loss function targeting global and local doses and validated the model's performance against existing alternatives. Model-assisted experiments were used to validate its clinical benefits.

RESULTS

The AS-NeSt model maintained an absolute prediction error below 5% for each dosimetric metric. The average Dice similarity coefficient for isodose volumes was 0.93. The model achieved an average relative prediction error of 2.02%, statistically lower than Hierarchically Densely Connected U-net (4.17%), DoseNet (2.35%), and Densely Connected Network (3.65%). It also demonstrated significantly fewer parameters and shorter prediction times. Clinically, the AS-NeSt model raised physicians' ability to accurately preassess appropriate treatment methods before planning from 95.24% to 100%, reduced planning time by over 61% for junior dosimetrists and 52% for senior dosimetrists, and decreased both inter- and intra-dosimetrist discrepancies by more than 50%.

CONCLUSIONS

The AS-NeSt model, developed with innovative 3D ResNeSt blocks and an asymmetrical encoder-decoder structure, has been validated using clinical esophageal cancer patient data. It accurately predicts 3D dose distributions for various prescriptions, including simultaneous integrated boost, showing potential to improve the management of esophageal cancer treatment in a clinical setting.

Neural network dose prediction for cervical brachytherapy: Overcoming data scarcity for applicator-specific models

BACKGROUND

3D neural network dose predictions are useful for automating brachytherapy (BT) treatment planning for cervical cancer. Cervical BT can be delivered with numerous applicators, which necessitates developing models that generalize to multiple applicator types. The variability and scarcity of data for any given applicator type poses challenges for deep learning.

PURPOSE

The goal of this work was to compare three methods of neural network training-a single model trained on all applicator data, fine-tuning the combined model to each applicator, and individual (IDV) applicator models-to determine the optimal method for dose prediction.

METHODS

Models were produced for four applicator types-tandem-and-ovoid (T&O), T&O with 1-7 needles (T&ON), tandem-and-ring (T&R) and T&R with 1-4 needles (T&RN). First, the combined model was trained on 859 treatment plans from 266 cervical cancer patients treated from 2010 onwards. The train/validation/test split was 70%/16%/14%, with approximately 49%/10%/19%/22% T&O/T&ON/T&R/T&RN in each dataset. Inputs included four channels for anatomical masks (high-risk clinical target volume [HRCTV], bladder, rectum, and sigmoid), a mask indicating dwell position locations, and applicator channels for each applicator component. Applicator channels were created by mapping the 3D dose for a single dwell position to each dwell position and summing over each applicator component with uniform dwell time weighting. A 3D Cascade U-Net, which consists of two U-Nets in sequence, and mean squared error loss function were used. The combined model was then fine-tuned to produce four applicator-specific models by freezing the first U-Net and encoding layers of the second and resuming training on applicator-specific data. Finally, four IDV models were trained using only data from each applicator type. Performance of these three model types was compared using the following metrics for the test set: mean error (ME, representing model bias) and mean absolute error (MAE) over all dose voxels and ME of clinical metrics (HRCTV D90% and D2cc of bladder, rectum, and sigmoid), averaged over all patients. A positive ME indicates the clinical dose was higher than predicted. 3D global gamma analysis with the prescription dose as reference value was performed. Dice similarity coefficients (DSC) were computed for each isodose volume.

RESULTS

Fine-tuned and combined models showed better performance than IDV applicator training. Fine-tuning resulted in modest improvements in about half the metrics, compared to the combined model, while the remainder were mostly unchanged. Fine-tuned MAE = 3.98%/2.69%/5.36%/3.80% for T&O/T&R/T&ON/T&RN, and ME over all voxels = -0.08%/-0.89%/-0.59%/1.42%. ME D2cc were bladder = -0.77%/1.00%/-0.66%/-1.53%, rectum = 1.11%/-0.22%/-0.29%/-3.37%, sigmoid = -0.47%/-0.06%/-2.37%/-1.40%, and ME D90 = 2.6%/-4.4%/4.8%/0.0%. Gamma pass rates (3%/3 mm) were 86%/91%/83%/89%. Mean DSCs were 0.92%/0.92%/0.88%/0.91% for isodoses ≤ 150% of prescription.

CONCLUSIONS

3D BT dose was accurately predicted for all applicator types, as indicated by the low MAE and MEs, high gamma scores and high DSCs. Training on all treatment data overcomes challenges with data scarcity in each applicator type, resulting in superior performance than can be achieved by training on IDV applicators alone. This could presumably be explained by the fact that the larger, more diverse dataset allows the neural network to learn underlying trends and characteristics in dose that are common to all treatment applicators. Accurate, applicator-specific dose predictions could enable automated, knowledge-based planning for any cervical brachytherapy treatment.

On the necessity of specialized knowledge-based models for SBRT prostate treatments plans

PURPOSE

Test whether a well-grounded KBP model trained on moderately hypo-fractionated prostate treatments can be used to satisfactorily drive the optimization of SBRT prostate treatments.

MATERIALS AND METHODS

A KBP model (SBRT-model) was developed, trained and validated using the first forty-seven clinically treated VMAT SBRT prostate plans (42.7 Gy/7fx or 36.25 Gy/5fx). The performance and robustness of this model were compared against a high-quality KBP-model (ST-model) that was already clinically adopted for hypo-fractionated (70 Gy/28fx and 60 Gy/20fx) prostate treatments. The two models were compared in terms of their predictions robustness, and the quality of their outcomes were evaluated against a set of reference clinical SBRT plans. Plan quality was assessed using DVH metrics, blinded clinical ranking, and a dedicated Plan Quality Metric algorithm.

RESULTS

The plan libraries of the two models were found to share a high degree of anatomical similarity. The overall quality (APQM%) of the plans obtained both with the ST- and SBRT-models was compatible with that of the original clinical plans, namely (93.7 ± 4.1)% and (91.6 ± 3.9)% vs (92.8.9 ± 3.6)%. Plans obtained with the ST-model showed significantly higher target coverage (PTV V95%): (97.9 ± 0.8)% vs (97.1 ± 0.9)% (p < 0.05). Conversely, plans optimized following the SBRT-model showed a small but not-clinically relevant increase in OAR sparing. ST-model generally provided more reliable predictions than SBRT-model. Two radiation oncologists judged as equivalent the plans based on the KBP prediction, which was also judged better that reference clinical plans.

CONCLUSION

A KBP model trained on moderately fractionated prostate treatment plans provided optimal SBRT prostate plans, with similar or larger plan quality than an embryonic SBRT-model based on a limited number of cases.

Evaluating automatically generated normal tissue contours for safe use in head and neck and cervical cancer treatment planning

PURPOSE

Volumetric-modulated arc therapy (VMAT) is a widely accepted treatment method for head and neck (HN) and cervical cancers; however, creating contours and plan optimization for VMAT plans is a time-consuming process. Our group has created an automated treatment planning tool, the Radiation Planning Assistant (RPA), that uses deep learning models to generate organs at risk (OARs), planning structures and automates plan optimization. This study quantitatively evaluates the quality of contours generated by the RPA tool.

METHODS

For patients with HN (54) and cervical (39) cancers, we retrospectively generated autoplans using the RPA. Autoplans were generated using deep-learning and RapidPlan models developed in-house. The autoplans were, then, applied to the original, physician-drawn contours, which were used as a ground truth (GT) to compare with the autocontours (RPA). Using a "two one-sided tests" (TOST) procedure, we evaluated whether the autocontour normal tissue dose was equivalent to that of the ground truth by a margin, δ, that we determined based on clinical judgement. We also calculated the number of plans that met established clinically accepted dosimetric criteria.

RESULTS

For HN plans, 91.8% and 91.7% of structures met dosimetric criteria for automatic and manual contours, respectively; for cervical plans, 95.6% and 95.7% of structures met dosimetric criteria for automatic and manual contours, respectively. Autocontours were equivalent to the ground truth for 71% and 75% of common DVH metrics for the HN and cervix, respectively.

CONCLUSIONS

This study shows that dosimetrically equivalent normal tissue contours can be created for HN and cervical cancers using deep learning techniques. In general, differences between the contours did not affect the passing or failing of clinical dose tolerances.

Multi-institutional evaluation of a Pareto navigation guided automated radiotherapy planning solution for prostate cancer

BACKGROUND

Current automated planning solutions are calibrated using trial and error or machine learning on historical datasets. Neither method allows for the intuitive exploration of differing trade-off options during calibration, which may aid in ensuring automated solutions align with clinical preference. Pareto navigation provides this functionality and offers a potential calibration alternative. The purpose of this study was to validate an automated radiotherapy planning solution with a novel multi-dimensional Pareto navigation calibration interface across two external institutions for prostate cancer.

METHODS

The implemented 'Pareto Guided Automated Planning' (PGAP) methodology was developed in RayStation using scripting and consisted of a Pareto navigation calibration interface built upon a 'Protocol Based Automatic Iterative Optimisation' planning framework. 30 previous patients were randomly selected by each institution (IA and IB), 10 for calibration and 20 for validation. Utilising the Pareto navigation interface automated protocols were calibrated to the institutions' clinical preferences. A single automated plan (VMATAuto) was generated for each validation patient with plan quality compared against the previously treated clinical plan (VMATClinical) both quantitatively, using a range of DVH metrics, and qualitatively through blind review at the external institution.

RESULTS

PGAP led to marked improvements across the majority of rectal dose metrics, with Dmean reduced by 3.7 Gy and 1.8 Gy for IA and IB respectively (p < 0.001). For bladder, results were mixed with low and intermediate dose metrics reduced for IB but increased for IA. Differences, whilst statistically significant (p < 0.05) were small and not considered clinically relevant. The reduction in rectum dose was not at the expense of PTV coverage (D98% was generally improved with VMATAuto), but was somewhat detrimental to PTV conformality. The prioritisation of rectum over conformality was however aligned with preferences expressed during calibration and was a key driver in both institutions demonstrating a clear preference towards VMATAuto, with 31/40 considered superior to VMATClinical upon blind review.

CONCLUSIONS

PGAP enabled intuitive adaptation of automated protocols to an institution's planning aims and yielded plans more congruent with the institution's clinical preference than the locally produced manual clinical plans.

A Prospective Study of Machine Learning-Assisted Radiation Therapy Planning for Patients Receiving 54 Gy to the Brain

PURPOSE

The capacity for machine learning (ML) to facilitate radiation therapy (RT) planning for primary brain tumors has not been described. We evaluated ML-assisted RT planning with regard to clinical acceptability, dosimetric outcomes, and planning efficiency for adults and children with primary brain tumors.

METHODS AND MATERIALS

In this prospective study, children and adults receiving 54 Gy fractionated RT for a primary brain tumor were enrolled. For each patient, one ML-assisted RT plan was created and compared with 1 or 2 plans created using standard ("manual") planning procedures. Plans were evaluated by the treating oncologist, who was blinded to the method of plan creation. The primary endpoint was the proportion of ML plans that were clinically acceptable for treatment. Secondary endpoints included the frequency with which ML plans were selected as preferable for treatment, and dosimetric differences between ML and manual plans.

RESULTS

A total of 116 manual plans and 61 ML plans were evaluated across 61 patients. Ninety-four percent of ML plans and 93% of manual plans were judged to be clinically acceptable (P = 1.0). Overall, the quality of ML plans was similar to manual plans. ML plans comprised 34.5% of all plans evaluated and were selected for treatment in 36.1% of cases (P = .82). Similar tumor target coverage was achieved between both planning methods. Normal brain (brain minus planning target volume) received an average of 1 Gy less mean dose with ML plans (compared with manual plans, P < .001). ML plans required an average of 45.8 minutes less time to create, compared with manual plans (P < .001).

CONCLUSIONS

ML-assisted automated planning creates high-quality plans for patients with brain tumors, including children. Plans created with ML assistance delivered slightly less dose to normal brain tissues and can be designed in less time.

Effects of model size and composition on quality of head-and-neck knowledge-based plans

PURPOSE

Knowledge-based planning (KBP) aims to automate and standardize treatment planning. New KBP users are faced with many questions: How much does model size matter, and are multiple models needed to accommodate specific physician preferences? In this study, six head-and-neck KBP models were trained to address these questions.

METHODS

The six models differed in training size and plan composition: The KBPFull (n = 203 plans), KBP101 (n = 101), KBP50 (n = 50), and KBP25 (n = 25) were trained with plans from two head-and-neck physicians. KBPA and KBPB each contained n = 101 plans from only one physician, respectively. An independent set of 39 patients treated to 6000-7000 cGy by a third physician was re-planned with all KBP models for validation. Standard head-and-neck dosimetric parameters were used to compare resulting plans. KBPFull plans were compared to the clinical plans to evaluate overall model quality. Additionally, clinical and KBPFull plans were presented to another physician for blind review. Dosimetric comparison of KBPFull against KBP101 , KBP50 , and KBP25 investigated the effect of model size. Finally, KBPA versus KBPB tested whether training KBP models on plans from one physician only influences the resulting output. Dosimetric differences were tested for significance using a paired t-test (p < 0.05).

RESULTS

Compared to manual plans, KBPFull significantly increased PTV Low D95% and left parotid mean dose but decreased dose cochlea, constrictors, and larynx. The physician preferred the KBPFull plan over the manual plan in 20/39 cases. Dosimetric differences between KBPFull , KBP101 , KBP50 , and KBP25 plans did not exceed 187 cGy on aggregate, except for the cochlea. Further, average differences between KBPA and KBPB were below 110 cGy.

CONCLUSIONS

Overall, all models were shown to produce high-quality plans. Differences between model outputs were small compared to the prescription. This indicates only small improvements when increasing model size and minimal influence of the physician when choosing treatment plans for training head-and-neck KBP models.

Impact of radiation doses on clinical relapse of biochemically recurrent prostate cancer after prostatectomy

The relationship between radiation doses and clinical relapse in patients receiving salvage radiotherapy (SRT) for biochemical recurrence (BCR) after radical prostatectomy (RP) remains unclear. We identified 292 eligible patients treated with SRT between 2005 and 2018 at 15 institutions. Clinical relapse-free survival (cRFS) between the ≥ 66 Gy (n = 226) and < 66 Gy groups (n = 66) were compared using the Log-rank test, followed by univariate and multivariate analyses and a subgroup analysis. After a median follow-up of 73 months, 6-year biochemical relapse-free survival, cRFS, cancer-specific survival, and overall survival rates were 58, 92, 98, and 94%, respectively. Six-year cRFS rates in the ≥ 66 Gy and < 66 Gy groups were 94 and 87%, respectively (p = 0.022). The multivariate analysis revealed that Gleason score ≥ 8, seminal vesicle involvement, PSA at BCR after RP ≥ 0.5 ng/ml, and a dose < 66 Gy correlated with clinical relapse (p = 0.015, 0.012, 0.024, and 0.0018, respectively). The subgroup analysis showed the consistent benefit of a dose ≥ 66 Gy in patients across most subgroups. Doses ≥ 66 Gy were found to significantly, albeit borderline, increase the risk of late grade ≥ 2 GU toxicity compared to doses < 66 Gy (14% vs. 3.2%, p = 0.055). This large multi-institutional retrospective study demonstrated that a higher SRT dose (≥ 66 Gy) resulted in superior cRFS.

Deep learning-based dose prediction to improve the plan quality of volumetric modulated arc therapy for gynecologic cancers

BACKGROUND

In recent years, deep-learning models have been used to predict entire three-dimensional dose distributions. However, the usability of dose predictions to improve plan quality should be further investigated.

PURPOSE

To develop a deep-learning model to predict high-quality dose distributions for volumetric modulated arc therapy (VMAT) plans for patients with gynecologic cancer and to evaluate their usability in driving plan quality improvements.

METHODS

A total of 79 VMAT plans for the female pelvis were used to train (47 plans), validate (16 plans), and test (16 plans) 3D dense dilated U-Net models to predict 3D dose distributions. The models received the normalized CT scan, dose prescription, and target and normal tissue contours as inputs. Three models were used to predict the dose distributions for plans in the test set. A radiation oncologist specializing in the treatment of gynecologic cancers scored the test set predictions using a 5-point scale (5, acceptable as-is; 4, prefer minor edits; 3, minor edits needed; 2, major edits needed; and 1, unacceptable). The clinical plans for which the dose predictions indicated that improvements could be made were reoptimized with constraints extracted from the predictions.

RESULTS

The predicted dose distributions in the test set were of comparable quality to the clinical plans. The mean voxel-wise dose difference was -0.14 ± 0.46 Gy. The percentage dose differences in the predicted target metrics ofD 1 % ${D}_{1{\mathrm{\% }}}$ andD 98 % ${D}_{98{\mathrm{\% }}}$ were -1.05% ± 0.59% and 0.21% ± 0.28%, respectively. The dose differences in the predicted organ at risk mean and maximum doses were -0.30 ± 1.66 Gy and -0.42 ± 2.07 Gy, respectively. A radiation oncologist deemed all of the predicted dose distributions clinically acceptable; 12 received a score of 5, and four received a score of 4. Replanning of flagged plans (five plans) showed that the original plans could be further optimized to give dose distributions close to the predicted dose distributions.

CONCLUSIONS

Deep-learning dose prediction can be used to predict high-quality and clinically acceptable dose distributions for VMAT female pelvis plans, which can then be used to identify plans that can be improved with additional optimization.

The NCS code of practice for the quality assurance of treatment planning systems (NCS-35)

A subcommittee of the Netherlands Commission on Radiation Dosimetry (NCS) was initiated in 2018 with the task to update and extend a previous publication (NCS-15) on the quality assurance of treatment planning systems (TPS) (Bruinviset al2005). The field of treatment planning has changed considerably since 2005. Whereas the focus of the previous report was more on the technical aspects of the TPS, the scope of this report is broader with a focus on a department wide implementation of the TPS. New sections about education, automated planning, information technology (IT) and updates are therefore added. Although the scope is photon therapy, large parts of this report will also apply to all other treatment modalities. This paper is a condensed version of these guidelines; the full version of the report in English is freely available from the NCS website (http://radiationdosimetry.org/ncs/publications). The paper starts with the scope of this report in relation to earlier reports on this subject. Next, general aspects of the commissioning process are addressed, like e.g. project management, education, and safety. It then focusses more on technical aspects such as beam commissioning and patient modeling, dose representation, dose calculation and (automated) plan optimisation. The final chapters deal with IT-related subjects and scripting, and the process of updating or upgrading the TPS.

A comparative study of deep learning-based knowledge-based planning methods for 3D dose distribution prediction of head and neck

PURPOSE

In this paper, we compare four novel knowledge-based planning (KBP) algorithms using deep learning to predict three-dimensional (3D) dose distributions of head and neck plans using the same patients' dataset and quantitative assessment metrics.

METHODS

A dataset of 340 oropharyngeal cancer patients treated with intensity-modulated radiation therapy was used in this study, which represents the AAPM OpenKBP - 2020 Grand Challenge dataset. Four 3D convolutional neural network architectures were built. The models were trained on 64% of the data set and validated on 16% for voxel-wise dose predictions: U-Net, attention U-Net, residual U-Net (Res U-Net), and attention Res U-Net. The trained models were then evaluated for their performance on a test data set (20% of the data) by comparing the predicted dose distributions against the ground-truth using dose statistics and dose-volume indices.

RESULTS

The four KBP dose prediction models exhibited promising performance with an averaged mean absolute dose error within the body contour <3 Gy on 68 plans in the test set. The average difference in predicting the D99 index for all targets was 0.92 Gy (p = 0.51) for attention Res U-Net, 0.94 Gy (p = 0.40) for Res U-Net, 2.94 Gy (p = 0.09) for attention U-Net, and 3.51 Gy (p = 0.08) for U-Net. For the OARs, the values for theD m a x ${D_{max}}$ andD m e a n ${D_{mean}}$ indices were 2.72 Gy (p < 0.01) for attention Res U-Net, 2.94 Gy (p < 0.01) for Res U-Net, 1.10 Gy (p < 0.01) for attention U-Net, 0.84 Gy (p < 0.29) for U-Net.

CONCLUSION

All models demonstrated almost comparable performance for voxel-wise dose prediction. KBP models that employ 3D U-Net architecture as a base could be deployed for clinical use to improve cancer patient treatment by creating plans with consistent quality and making the radiotherapy workflow more efficient.

Improving plan quality in cervical brachytherapy using a simple knowledge-based prediction tool for OAR dose (D2cm3)

PURPOSE

Toxicity from cervical brachytherapy has been demonstrated to correlate with the D2cm3 of the bladder, rectum, and bowel. This suggests a simplified version of knowledge-based planning investigating the relationship of the overlap distance for 2cm3 and the D2cm3 from planning may be possible. This work demonstrates the feasibility of simple knowledge-based planning to predict the D2cm3, detect suboptimal plans, and improve plan quality.

METHODS AND MATERIALS

The overlap volume histogram (OVH) method was used to determine the distance for 2cm3 of overlap between the OAR and CTV_HR. Linear plots modeled the OAR D2cm3 and 2cm3 overlap distance. Two datasets of 20 patients (plans from 43 insertions in each dataset) were used to create two independent models, and the performance of each model was compared using cross-validation. Doses were scaled to ensure consistent CTV_HR D90 values. The predicted D2cm3 is entered as the maximum constraint in the inverse planning algorithm.

RESULTS

Mean bladder D2cm3 decreased by 2.9% for the models from each dataset, mean rectal D2cm3 decreased 14.9% for the model from dataset 1 and 6.0% for the model from dataset 2, mean sigmoid D2cm3 decreased 10.7% for the model from dataset 1 and 6.1% for the model from dataset 2, mean bowel D2cm3 decreased 4.1% for the model from dataset 1 but no statistically significant difference was observed for the model from dataset 2.

CONCLUSIONS

A simplified knowledge-based planning method was used to predict D2cm3 and was able to automate optimization of brachytherapy plans for locally advanced cervical cancer.

Dosimetric evaluation of high-Z inhomogeneity with modern algorithms: A collaborative study

PURPOSE

To evaluate modern dose calculation algorithms with high-Z prosthetic devices used in radiation treatment.

METHODS

A bilateral hip prosthetic patient was selected to see the effect of modern algorithms from the commercial system for plan comparisons. The CT data with dose constraints were sent to various institutions for dose calculations. The dosimetric parameters, D98%, D90%, D50% and D2% were compared. A water phantom with an actual prosthetic device was used to measure the dose using a parallel plate ionization chamber.

RESULTS

Dosimetric variability in PTV coverage was significant (>10%) among various treatment planning algorithms. The comparison of PTV dosimetric parameters, D98%, D90%, D50% and D2% as well as organs at risk (OAR) have large discrepancies compared to our previous publication with older algorithms (https://doi.org/10.1016/j.ejmp.2022.02.007) but provides realistic dose distribution with better homogeneity index (HI). Backscatter and forward scatter attenuation of the prosthesis was measured showing differences <15.7% at the interface among various algorithms.

CONCLUSIONS

Modern algorithms dose distributions have improved greatly compared to older generation algorithms. However, there is still significant differences at high-Z-tissue interfaces compared to the measurements. To ensure accuracy, it's important to take precautions avoiding placing any prosthesis in the beam direction and using type C algorithms.

Toward Systematic Assessment and Improvement of Radiation Therapy Plan Quality of Cooperative Group Trial Submissions: A Report From the Children's Oncology Group

PURPOSE

This study evaluates the quality of plans used for the treatment of patients in the Children's Oncology Group study ACNS1123. Plan quality is quantified based on a scoring system specific to the protocol. In this way, the distribution of plan quality scores is determined that can be used to identify plan quality issues for this study and for future plan quality improvement.

METHODS AND MATERIALS

ACNS1123 stratum 1 patients (70) were evaluated. This included 50 photon and 20 proton plans. Digital Imaging and Communications in Medicine (DICOM) structure and dose data were obtained from the Children's Oncology Group. A commercially available plan quality scoring algorithm was used to create a scoring system we designed using the protocol dosimetric requirements. The whole ventricle and boost planning target volumes (PTVs) could earn a maximum of 70 points, whereas the organs at risk could earn 30 points (total maximum score of 100 points). The scoring algorithm adjusted scores based on the difficulty in achieving the structure dose requirements, which depended on the proximity of the PTVs and the dose gradients achieved relative to the organs at risk. The distribution of plan scores was used to determine the mean, median, and range of scores.

RESULTS

The median adjusted plan quality scores for the 20 proton and 50 photon plans were 83.3 and 86.9, respectively. The range of adjusted scores (maximum to minimum) was 50 points. The average score adjustment was 7.4 points. Photon and proton plans performed almost equally. Average plan quality by individual structure revealed that the brain stem, PTV boost, and cochlea lost the most points.

CONCLUSIONS

This report is the first to systematically analyze overall radiation therapy plan quality scores for an entire cohort of patients treated in a cooperative group clinical trial. The methodology demonstrated a large variation in plan quality in this trial. Future clinical trials could potentially use this method to reduce plan quality variability, which may improve outcomes.

Dose prescription and reporting in stereotactic body radiotherapy: A multi-institutional study

BACKGROUND AND PURPOSE

Radiation dose prescriptions are foundational for optimizing treatment efficacy and limiting treatment-related toxicity. We sought to assess the lack of standardization of SBRT dose prescriptions across institutions.

MATERIALS & METHODS

Dosimetric data from 1298 patients from 9 academic institutions treated with IMRT and VMAT were collected. Dose parameters D100, D98, D95, D50, and D2 were used to assess dosimetric variability.

RESULTS

Disease sites included lung (48.3 %) followed by liver (29.7 %), prostate (7.5 %), spine (6.8 %), brain (4.1 %), and pancreas (2.5 %). The PTV volume in lung varied widely with bimodality into two main groups (22.0-28.7 cm3) and (48.0-67.1 cm3). A hot spot ranging from 120-150 % was noted in nearly half of the patients, with significant variation across institutions. A D50 ≥ 110 % was found in nearly half of the institutions. There was significant dosimetric variation across institutions.

CONCLUSIONS

The SBRT prescriptions in the literature or in treatment guidelines currently lack nuance and hence there is significant variation in dose prescriptions across academic institutions. These findings add greater importance to the identification of dose parameters associated with improved clinical outcome comparisons as we move towards more hypofractionated treatments. There is a need for standardized reporting to help institutions in adapting treatment protocols based on the outcome of clinical trials. Dosimetric parameters are subsequently needed for uniformity and thereby standardizing planning guidelines to maximize efficacy, mitigate toxicity, and reduce treatment disparities are urgently needed.

Automated treatment planning framework for brachytherapy of cervical cancer using 3D dose predictions

Objective. To lay the foundation for automated knowledge-based brachytherapy treatment planning using 3D dose estimations, we describe an optimization framework to convert brachytherapy dose distributions directly into dwell times (DTs).Approach. A dose rate kernelḋ(r,θ,φ)was produced by exporting 3D dose for one dwell position from the treatment planning system and normalizing by DT. By translating and rotating this kernel to each dwell position, scaling by DT and summing over all dwell positions, dose was computed (Dcalc). We used a Python-coded COBYLA optimizer to iteratively determine the DTs that minimize the mean squared error betweenDcalcand reference doseDref, computed using voxels withDref80%-120% of prescription. As validation of the optimization, we showed that the optimizer replicates clinical plans whenDref= clinical dose in 40 patients treated with tandem-and-ovoid (T&O) or tandem-and-ring (T&R) and 0-3 needles. Then we demonstrated automated planning in 10 T&O usingDref= dose predicted from a convolutional neural network developed in past work. Validation and automated plans were compared to clinical plans using mean absolute differences (MAD=1N∑n=1Nabsxn-xn') over all voxels (xn= Dose,N= #voxels) and DTs (xn= DT,N= #dwell positions), mean differences (MD) in organD2ccand high-risk CTV D90 over all patients (where positive indicates higher clinical dose), and mean Dice similarity coefficients (DSC) for 100% isodose contours.Main results. Validation plans agreed well with clinical plans (MADdose= 1.1%, MADDT= 4 s or 0.8% of total plan time,D2ccMD = -0.2% to 0.2% and D90 MD = -0.6%, DSC = 0.99). For automated plans, MADdose= 6.5% and MADDT= 10.3 s (2.1%). The slightly higher clinical metrics in automated plans (D2ccMD = -3.8% to 1.3% and D90 MD = -5.1%) were due to higher neural network dose predictions. The overall shape of the automated dose distributions were similar to clinical doses (DSC = 0.91).Significance. Automated planning with 3D dose predictions could provide significant time savings and standardize treatment planning across practitioners, regardless of experience.

Feasibility-guided automated planning for stereotactic treatments of prostate cancer

Significant improvements in plan quality using automated planning have been previously demonstrated. The aim of this study was to develop an optimal automated class solution for stereotactic radiotherapy (SBRT) planning of prostate cancer using the new Feasibility module implemented in the pinnacle evolution. Twelve patients were retrospectively enrolled in this planning study. Five plans were designed for each patient. Four plans were automatically generated using the 4 proposed templates for SBRT optimization implemented in the new pinnacle evolution treatment planning systems, differing for different settings of dose-fallout (low, medium, high and veryhigh). Based on the obtained results, the fifth plan (feas) was generated customizing the template with the optimal criteria obtained from the previous step and integrating in the template the "a-priori" knowledge of OARs sparing based on the Feasibility module, able to estimate the best possible dose-volume histograms of OARs before starting optimization. Prescribed dose was 35 Gy to the prostate in 5 fractions. All plans were generated with a full volumetric-modulated arc therapy arc and 6MV flattening filter-free beams, and optimized to ensure the same target coverage (95% of the prescription dose to 98% of the target). Plans were assessed according to dosimetric parameters and planning and delivery efficiency. Differences among the plans were evaluated using a Kruskal-Wallis 1-way analysis of variance. The requests for more aggressive objectives for dose falloff parameters (from low to veryhigh) translated in a statistically significant improvement of dose conformity, but at the expense of a dose homogeneity. The best automated plans in terms of best trade-off between target coverage and OARs sparing among the 4 plans automatically generated by the SBRT module were the high plans. The veryhigh plans reported a significant increase of high-doses to prostate, rectum, and bladder that was considered dosimetrically and clinically unacceptable. The feas plans were optimized on the basis on high plans, reporting significant reduction of rectum irradiation; Dmean, and V18 decreased by 19% to 23% (p = 0.031) and 4% to 7% (p = 0.059), respectively. No statistically significant differences were found in femoral heads and penile bulb irradiation for all dosimetric metrics. feas plans showed a significant increase of MU/Gy (mean: 368; p = 0.004), reflecting an increased level of fluence modulation. Thanks to the new efficient optimization engines implemented in pinnacle evolution (L-BFGS and layered graph), mean planning time was decreased to less than 10 minutes for all plans and all techniques. The integration of dose-volume histograms a-priori knowledge provided by the feasibility module in the automated planning process for SBRT planning has shown to significantly improve plan quality compared to generic protocol values as inputs.

The effect of integrating knowledge-based planning with multicriteria optimization in treatment planning for prostate SBRT

Knowledge-based planning (KBP) and multicriteria optimization (MCO) are two powerful tools to assist treatment planners in achieving optimal target coverage and organ-at-risk (OAR) sparing. The purpose of this work is to investigate if integrating MCO with conventional KBP can further improve treatment plan quality for prostate cancer stereotactic body radiation therapy (SBRT). A two-phase study was designed to investigate the impact of MCO and KBP in prostate SBRT treatment planning. The first phase involved the creation of a KBP model based on thirty clinical SBRT plans, generated by manual optimization (KBP_M). A ten-patient validation cohort was used to compare manual, MCO, and KBP_M optimization techniques. The next phase involved replanning the original model cohort with additional tradeoff optimization via MCO to create a second model, KBP_MCO. Plans were then generated using linear integration (KBP_M+MCO), non-linear integration (KBP_MCO), and a combination of integration methods (KBP_MCO+MCO). All plans were analyzed for planning target volume (PTV) coverage, OAR constraints, and plan quality metrics. Comparisons were generated to evaluate plan and model quality. Phase 1 highlighted the necessity of KBP and MCO in treatment planning, as both optimization methods improved plan quality metrics (Conformity and Heterogeneity Indices) and reduced mean rectal dose by 2 Gy, as compared to manual planning. Integrating MCO with KBP did not further improve plan quality, as little significance was seen over KBP or MCO alone. Principal component score (PCS) fitting showed KBP_MCO improved bladder and rectum estimated and modeled dose correlation by 5% and 22%, respectively; however, model improvements did not significantly impact plan quality. KBP and MCO have shown to reduce OAR dose while maintaining desired PTV coverage in this study. Further integration of KBP and MCO did not show marked improvements in treatment plan quality while requiring increased time in model generation and optimization time.

Automated Contouring and Planning in Radiation Therapy: What Is 'Clinically Acceptable'?

Developers and users of artificial-intelligence-based tools for automatic contouring and treatment planning in radiotherapy are expected to assess clinical acceptability of these tools. However, what is 'clinical acceptability'? Quantitative and qualitative approaches have been used to assess this ill-defined concept, all of which have advantages and disadvantages or limitations. The approach chosen may depend on the goal of the study as well as on available resources. In this paper, we discuss various aspects of 'clinical acceptability' and how they can move us toward a standard for defining clinical acceptability of new autocontouring and planning tools.

Implementation of Machine Learning Models to Ensure Radiotherapy Quality for Multicenter Clinical Trials: Report from a Phase III Lung Cancer Study

The outcome of the patient and the success of clinical trials involving RT is dependent on the quality assurance of the RT plans. Knowledge-based Planning (KBP) models using data from a library of high-quality plans have been utilized in radiotherapy to guide treatment. In this study, we report on the use of these machine learning tools to guide the quality assurance of multicenter clinical trial plans. The data from 130 patients submitted to RTOG1308 were included in this study. Fifty patient cases were used to train separate photon and proton models on a commercially available platform based on principal component analysis. Models evaluated 80 patient cases. Statistical comparisons were made between the KBP plans and the original plans submitted for quality evaluation. Both photon and proton KBP plans demonstrate a statistically significant improvement of quality in terms of organ-at-risk (OAR) sparing. Proton KBP plans, a relatively emerging technique, show more improvements compared with photon plans. The KBP proton model is a useful tool for creating proton plans that adhere to protocol requirements. The KBP tool was also shown to be a useful tool for evaluating the quality of RT plans in the multicenter clinical trial setting.

Dose Escalation for Pancreas SBRT: Potential and Limitations of using Daily Online Adaptive Radiation Therapy and an Iterative Isotoxicity Automated Planning Approach

Purpose

To determine the dosimetric limitations of daily online adaptive pancreas stereotactic body radiation treatment by using an automated dose escalation approach.

Methods and Materials

We collected 108 planning and daily computed tomography (CT) scans from 18 patients (18 patients × 6 CT scans) who received 5-fraction pancreas stereotactic body radiation treatment at MD Anderson Cancer Center. Dose metrics from the original non-dose-escalated clinical plan (non-DE), the dose-escalated plan created on the original planning CT (DE-ORI), and the dose-escalated plan created on daily adaptive radiation therapy CT (DE-ART) were analyzed. We developed a dose-escalation planning algorithm within the radiation treatment planning system to automate the dose-escalation planning process for efficiency and consistency. In this algorithm, the prescription dose of the dose-escalation plan was escalated before violating any organ-at-risk (OAR) dose constraint. Dose metrics for 3 targets (gross target volume [GTV], tumor vessel interface [TVI], and dose-escalated planning target volume [DE-PTV]) and 9 OARs (duodenum, large bowel, small bowel, stomach, spinal cord, kidneys, liver, and skin) for the 3 plans were compared. Furthermore, we evaluated the effectiveness of the online adaptive dose-escalation planning process by quantifying the effect of the interfractional dose distribution variations among the DE-ART plans.

Results

The median D_95% dose to the GTV/TVI/DE-PTV was 33.1/36.2/32.4 Gy, 48.5/50.9/40.4 Gy, and 53.7/58.2/44.8 Gy for non-DE, DE-ORI, and DE-ART, respectively. Most OAR dose constraints were not violated for the non-DE and DE-ART plans, while OAR constraints were violated for the majority of the DE-ORI patients due to interfractional motion and lack of adaptation. The maximum difference per fraction in D_95%, due to interfractional motion, was 2.5 ± 2.7 Gy, 3.0 ± 2.9 Gy, and 2.0 ± 1.8 Gy for the TVI, GTV, and DE-PTV, respectively.

Conclusions

Most patients require daily adaptation of the radiation planning process to maximally escalate delivered dose to the pancreatic tumor without exceeding OAR constraints. Using our automated approach, patients can receive higher target dose than standard of care without violating OAR constraints.

Domain knowledge driven 3D dose prediction using moment-based loss function

Objective. To propose a novel moment-based loss function for predicting 3D dose distribution for the challenging conventional lung intensity modulated radiation therapy plans. The moment-based loss function is convex and differentiable and can easily incorporate clinical dose volume histogram (DVH) domain knowledge in any deep learning (DL) framework without computational overhead. Approach. We used a large dataset of 360 (240 for training, 50 for validation and 70 for testing) conventional lung patients with 2 Gy × 30 fractions to train the DL model using clinically treated plans at our institution. We trained a UNet like convolutional neural network architecture using computed tomography, planning target volume and organ-at-risk contours as input to infer corresponding voxel-wise 3D dose distribution. We evaluated three different loss functions: (1) the popular mean absolute error (MAE) loss, (2) the recently developed MAE + DVH loss, and (3) the proposed MAE + moments loss. The quality of the predictions was compared using different DVH metrics as well as dose-score and DVH-score, recently introduced by the AAPM knowledge-based planning grand challenge. Main results. Model with (MAE + moment) loss function outperformed the model with MAE loss by significantly improving the DVH-score (11%, p < 0.01) while having similar computational cost. It also outperformed the model trained with (MAE + DVH) by significantly improving the computational cost (48%) and the DVH-score (8%, p < 0.01). Significance. DVH metrics are widely accepted evaluation criteria in the clinic. However, incorporating them into the 3D dose prediction model is challenging due to their non-convexity and non-differentiability. Moments provide a mathematically rigorous and computationally efficient way to incorporate DVH information in any DL architecture. The code, pretrained models, docker container, and Google Colab project along with a sample dataset are available on our DoseRTX GitHub (https://github.com/nadeemlab/DoseRTX)

Artificial intelligence in radiotherapy

Radiotherapy is a discipline closely integrated with computer science. Artificial intelligence (AI) has developed rapidly over the past few years. With the explosive growth of medical big data, AI promises to revolutionize the field of radiotherapy through highly automated workflow, enhanced quality assurance, improved regional balances of expert experiences, and individualized treatment guided by multi-omics. In addition to independent researchers, the increasing number of large databases, biobanks, and open challenges significantly facilitated AI studies on radiation oncology. This article reviews the latest research, clinical applications, and challenges of AI in each part of radiotherapy including image processing, contouring, planning, quality assurance, motion management, and outcome prediction. By summarizing cutting-edge findings and challenges, we aim to inspire researchers to explore more future possibilities and accelerate the arrival of AI radiotherapy.

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.

Assessing the practicality of using a single knowledge‐based planning model for multiple linac vendors

Purpose

Knowledge‐based planning (KBP) has been shown to be an effective tool in quality control for intensity‐modulated radiation therapy treatment planning and generating high‐quality plans. Previous studies have evaluated its ability to create consistent plans across institutions and between planners within the same institution as well as its use as teaching tool for inexperienced planners. This study evaluates whether planning quality is consistent when using a KBP model to plan across different treatment machines.

Materials and methods

This study used a RapidPlan model (Varian Medical Systems) provided by the vendor, to which we added additional planning objectives, maximum dose limits, and planning structures, such that a clinically acceptable plan is achieved in a single optimization. This model was used to generate and optimize volumetric‐modulated arc therapy plans for a cohort of 50 patients treated for head‐neck cancer. Plans were generated using the following treatment machines: Varian 2100, Elekta Versa HD, and Varian Halcyon. A noninferiority testing methodology was used to evaluate the hypothesis that normal and target metrics in our autoplans were no worse than a set of clinically‐acceptable baseline plans by a margin of 1.8 Gy or 3% dose‐volume. The quality of these plans were also compared through the use of common clinical dose‐volume histogram criteria.

Results

The Versa HD met our noninferiority criteria for 23 of 34 normal and target metrics; while the Halcyon and Varian 2100 machines met our criteria for 24 of 34 and 26 of 34 metrics, respectively. The experimental plans tended to have less volume coverage for prescription dose planning target volume and larger hotspot volumes. However, comparable plans were generated across different treatment machines.

Conclusions

These results support the use of a head‐neck RapidPlan models in centralized planning workflows that support clinics with different linac models/vendors, although some fine‐tuning for targets may be necessary.

Knowledge-based three-dimensional dose prediction for tandem-and-ovoid brachytherapy

PURPOSE

The purpose of this work was to develop a knowledge-based dose prediction system using a convolution neural network (CNN) for cervical brachytherapy treatments with a tandem-and-ovoid applicator.

METHODS

A 3D U-NET CNN was utilized to make voxel-wise dose predictions based on organ-at-risk (OAR), high-risk clinical target volume (HRCTV), and possible source location geometry. The model comprised 395 previously treated cases: training (273), validation (61), test (61). To assess voxel prediction accuracy, we evaluated dose differences in all cohorts across the dose range of 20-130% of prescription, mean(SD) and standard deviation (σ), as well as isodose dice similarity coefficients for clinical and/or predicted dose distributions. We examined discrete Dose-Volume Histogram(DVH) metrics utilized for brachytherapy plan quality assessment (HRCTV D90%, and bladder and/or rectum and/or sigmoid D2cc) with ΔD_x=D_x,actual-D_x,predicted Pearson correlation coefficient, standard deviation, and mean further quantifying model performance.

RESULTS

Ranges of voxel-wise dose difference accuracy (δD¯±σ) for 20-130% dose interval in training (test) sets ranged from [-0.5% ± 2.0% to +2.0% ± 14.0%] ([-0.1% ± 4.0% to +4.0% ± 26.0%]) in all voxels, [-1.7% ± 5.1% to -3.5% ± 12.8%] ([-2.9% ± 4.8% to -2.6% ± 18.9%]) in HRCTV, [-0.02% ± 2.40% to +3.2% ± 12.0%] ([-2.5% ± 3.6% to +0.8% ± 12.7%]) in bladder, [-0.7% ± 2.4% to +15.5% ± 11.0%] ([-0.9% ± 3.2% to +27.8% ± 11.6%]) in rectum, and [-0.7% ± 2.3% to +10.7% ± 15.0%] ([-0.4% ± 3.0% to +18.4% ± 11.4%]) in sigmoid. Isodose dice similarity coefficients ranged from [0.96,0.91] for training and [0.94,0.87] for test cohorts. Relative DVH metric prediction in the training (test) set were HRCTV ΔD¯₉₀±σ_ΔD=-0.19 ± 0.55Gy(-0.09 ± 0.67 Gy), bladder ΔD¯_2cc±σ_ΔD= -0.06 ± 0.54Gy(-0.17 ± 0.67 Gy), rectum ΔD¯_2cc±σ_ΔD= -0.03 ± 0.36Gy(-0.04 ± 0.46 Gy), and sigmoid ΔD¯_2cc±σ_ΔD= -0.01 ± 0.34Gy(0.00 ± 0.44 Gy).

CONCLUSIONS

A 3D knowledge-based dose predictions provide voxel-level and DVH metric estimates that could be used for treatment plan quality control and data-driven plan guidance.

Toward automatic beam angle selection for pencil-beam scanning proton liver Treatments: A deep learning-based approach

BACKGROUND

Dose deposition characteristics of proton radiation can be advantageous over photons. Proton treatment planning however poses additional challenges for the planners. Proton therapy is usually delivered with only a small number of beam angles, and the quality of a proton treatment plan is largely determined by the beam angles employed. Finding the optimal beam angles for a proton treatment plan requires time and experience, motivating the investigation of automatic beam angle selection methods.

PURPOSE

A deep learning-based approach to automatic beam angle selection is proposed for proton pencil-beam scanning treatment planning of liver lesions.

METHODS

We cast beam-angle selection as a multi-label classification problem. To account for angular boundary discontinuity, the underlying convolution neural network is trained with the proposed Circular Earth Mover's Distance based regularization and multi-label circular-smooth label technique. Furthermore, an analytical algorithm emulating proton treatment planners' clinical practice is employed in post-processing to improve the output of the model. Forty-nine patients that received proton liver treatments between 2017 and 2020 were randomly divided into training (n = 31), validation (n = 7), and test sets (n = 11). AI-selected beam angles were compared with those angles selected by human planners, and the dosimetric outcome was investigated by creating plans using knowledge-based treatment planning.

RESULTS

For 7 of the 11 cases in the test set, AI-selected beam angles agreed with those chosen by human planners to within 20 degrees (median angle difference = 10°; mean = 18.6°). Moreover, out of the total 22 beam angles predicted by the model, 15 (68%) were within 10 degrees of the human-selected angles. The high correlation in beam angles resulted in comparable dosimetric statistics between proton treatment plans generated using AI- and human-selected angles. For the cases with beam angle differences exceeding 20°, the dosimetric analysis showed similar plan quality although with different emphases on organ-at-risk sparing.

CONCLUSIONS

This pilot study demonstrated the feasibility of a novel deep learning-based beam angle selection technique. Testing on liver cancer patients showed that the resulting plans were clinically viable with comparable dosimetric quality to those using human-selected beam angles. In tandem with auto-contouring and knowledge-based treatment planning tools, the proposed model could represent a pathway for nearly fully automated treatment planning in proton therapy. This article is protected by copyright. All rights reserved.

Impact of Dose Escalation on the Efficacy of Salvage Radiotherapy for Recurrent Prostate Cancer-A Risk-Adjusted, Matched-Pair Analysis

Previous randomized trials have not provided conclusive evidence about dose escalations and associated toxicities for salvage radiotherapy (SRT) in prostate cancer. Here, we retrospectively analyzed whether dose escalations influenced progression-free survival in 554 patients that received salvage radiotherapy for relapses or persistently elevated prostate cancer antigen (PSA) after a radical prostatectomy. Patients received SRT between 1997 and 2017 at two University Hospitals in Germany. We compared patient groups that received radiation doses <7000 cGy (n = 225) or ≥7000 cGy (n = 329) to analyze the influence of radiation dose on progression-free survival. In a second matched-pair analysis of 216 pairs, we evaluated prognostic factors (pT2 vs. pT3−4, Gleason score [GS] ≤ 7 vs. GS ≥ 8, R0 vs. R1, and pre-SRT PSA <0.5 vs. ≥0.5 ng/mL). After a median follow-up of 6.8 (4.2−9.2) years, we found that escalated doses significantly improved progression-free survival (p = 0.0042). A multivariate analysis indicated that an escalated dose, lower tumor stages (pT2 vs. pT3/4), and lower GSs (≤7 vs. 8−10) were associated with improved progression-free survival. There was no significant effect on overall survival. Our data suggested that escalating the radiation dose to ≥7000 cGy for SRT after a prostatectomy significantly improved progression-free survival. Longer follow-ups are needed for a comprehensive recommendation.

Neural-network dose-prediction for rectal spacer stratification in dose-escalated prostate radiotherapy

Purpose

To develop a knowledge‐based decision‐support system capable of stratifying patients for rectal spacer (RS) insertion based on neural network predicted rectal dose, reducing the need for time‐ and resource‐intensive radiotherapy (RT) planning.

Methods

Forty‐four patients treated for prostate cancer were enrolled into a clinical trial (NCT03238170). Dose‐escalated prostate RT plans were manually created for 30 patients with simulated boost volumes using a conventional treatment planning system (TPS) and used to train a hierarchically dense 3D convolutional neural network to rapidly predict RT dose distributions. The network was used to predict rectal doses for 14 unseen test patients, with associated toxicity risks calculated according to published data. All metrics obtained using the network were compared to conventionally planned values.

Results

The neural network stratified patients with an accuracy of 100% based on optimal rectal dose–volume histogram constraints and 78.6% based on mandatory constraints. The network predicted dose‐derived grade 2 rectal bleeding risk within 95% confidence limits of ‐1.9% to +1.7% of conventional risk estimates (risk range 3.5%–9.9%) and late grade 2 fecal incontinence risk within ‐0.8% to +1.5% (risk range 2.3%–5.7%). Prediction of high‐resolution 3D dose distributions took 0.7 s.

Conclusions

The feasibility of using a neural network to provide rapid decision support for RS insertion prior to RT has been demonstrated, and the potential for time and resource savings highlighted. Directly after target and healthy tissue delineation, the network is able to (i) risk stratify most patients with a high degree of accuracy to prioritize which patients would likely derive greatest benefit from RS insertion and (ii) identify patients close to the stratification threshold who would require conventional planning.

Adherence to contouring and treatment planning requirements within a multicentric trial -results of the quality assurance of the SAKK 09/10 trial

PURPOSE

To evaluate the results of the radiation therapy (RT) quality assurance (QA) program of the phase III randomized "XXXX-Anonymized for Review" trial in biochemically recurrent prostate cancer (PC) patients after prostatectomy.

METHODS AND MATERIALS

Within the "XXXX-Anonymized for Review" trial testing 64Gy versus 70Gy salvage RT, a central collection of treatment plans were performed, which were thoroughly reviewed by a dedicated medical physicist and radiation oncologist. Adherence to the treatment protocol and specifically to the European Organization for the Research and Treatment of Cancer (EORTC) guidelines for target volume definition (classified as deviation observed yes vs. no) and its potential correlation with acute and late toxicity (Common Terminology Criteria for Adverse Events (CTCAE) v4.0) and freedom from biochemical progression (FFBP) were investigated.

RESULTS

The treatment plans of 344 patients treated between February 2011 and April 2014 depicted important deviations to the EORTC guidelines and to the recommendations per trial protocol. For example, in up to half of the cases, the delineated structures deviated from the protocol (e.g., prostate bed (PB) in 48.8%, rectal wall (RW) in 41%). In addition, variations in clinical (CTV) - and planning target volume (PTV) occurred frequently (e.g., CTV and PTV deviations in up to 42.4% and 25.9%, respectively). The detected deviations showed a significant association with a lower risk of grade ≥ 2 gastrointestinal (GI) acute toxicity when CTV not overlapped RW vs. CTV overlapping RW, (OR 0.43; CI [0.22, 0.85]; p= 0.014), and a higher rate of grade ≥ 2 late genitourinary (GU) toxicity in case of the CTV overlapped with RW, (OR 2.58; CI [1.17, 5.72]; p= 0.019). A marginally significant lower risk of grade ≥ 2 late GU toxicity in patients when PB not overlapping RW versus overlapping RW was observed (OR 0.51; CI [0.25, 1.03]; p= 0.06). In addition, a marginally significant decrease of FFBP in patients with PTV not including surgical clips as potential markers of the limits of the prostate bed, (HR 1.44; CI [0.96, 2.17]; p= 0.07) was observed.

CONCLUSIONS

Despite a thorough QA program, the central review of a phase-III trial showed limited adherence to treatment protocol recommendations which was associated with a higher risk of toxicity by means of acute or late GI or GU toxicity and showed a trend towards worse FFBP. Data from this QA review may help refine future QA programs and prostate bed delineation guidelines.

Validation of automated complex head and neck treatment planning with pencil beam scanning proton therapy

Background

Pencil beam scanning (PBS) proton therapy offers dosimetric advantages for several treatment sites, including head and neck (H&N). However, to achieve the optimal target coverage and robustness, these plans can be complex and time consuming to develop and optimize. Automating the treatment planning process can ensure a high‐quality and standardized plan, reduce burden to the planner, and decrease time‐to‐treatment. We utilized in‐house scripting to automate a four‐field multi‐field optimization (MFO) H&N planning technique.

Methods and materials

Ten bilateral H&N patients were planned in RayStation v6 with a four‐field modified‐X beam configuration using MFO planning. Automation included creation of avoidance structures to control spot placement and development of standardized beams, PBS spot settings, robust optimization objectives, and patient‐specific predicted planning constraints. Each patient was planned both with and without automation to evaluate differences in planning time, perceived effort and plan quality, plan robustness, and OAR sparing.

Results

On average, scripted plans required 3.2 h, compared to 4.3 h without the script. There was no difference in target coverage or plan robustness with or without automation. Automation significantly reduced mean dose to the oral cavity, parotids, esophagus, trachea, and larynx. Perceived effort was scaled from 1 (minimum effort) to 100 (maximum effort), and automation reduced perceived effort by 42% (p < 0.05). Two non‐scripted plans required re‐planning due to errors.

Conclusions

Automation of this multi‐beam, the MFO proton planning process reduced planning time and improved OAR sparing compared to the same planning process without scripting. Scripting generation of complex structures and planning objectives reduced burden on the planner. With most current treatment planning software, this automation is simple to implement and can standardize quality of care across all treatment planners.

Dose Prediction Models Based on Geometric and Plan Optimization Parameter for Adjuvant Radiotherapy Planning Design in Cervical Cancer Radiotherapy

The prediction of an additional space for the dose sparing of organs at risk (OAR) in radiotherapy is still difficult. In this pursuit, the present study was envisaged to find out the factors affecting the bladder and rectum dosimetry of cervical cancer. Additionally, the relationship between the dose-volume histogram (DVH) parameters and the geometry and plan dose-volume optimization parameters of the bladder/rectum was established to develop the dose prediction models and guide the planning design for lower OARs dose coverage directly. Thirty volume modulated radiation therapy (VMAT) plans from cervical cancer patients were randomly chosen to build the dose prediction models. The target dose coverage was evaluated. Dose prediction models were established by univariate and multiple linear regression among the dosimetric parameters of the bladder/rectum, the geometry parameters (planning target volume (PTV), volume of bladder/rectum, overlap volume of bladder/rectum (OV), and overlapped volume as a percentage of bladder/rectum volume (OP)), and corresponding plan dose-volume optimization parameters of the nonoverlapping structures (the structure of bladder/rectum outside the PTV (NOS)). Finally, the accuracy of the prediction models was evaluated by tracking d = (predicted dose-actual dose)/actual in additional ten VMAT plans. V ₃₀, V ₃₅, and V ₄₀ of the bladder and rectum were found to be multiple linearly correlated with the relevant OP and corresponding dose-volume optimization parameters of NOS (regression R ² > 0.99, P < 0.001). The variations of these models were less than 0.5% for bladder and rectum. Percentage of bladder and rectum within the PTV and the dose-volume optimization parameters of NOS could be used to predict the dose quantitatively. The parameters of NOS as a limited condition could be used in the plan optimization instead of limiting the dose and volume of the entire OAR traditionally, which made the plan optimization more unified and convenient and strengthened the plan quality and consistency.

Knowledge-based dose prediction models to inform gynecologic brachytherapy needle supplementation for locally advanced cervical cancer

PURPOSE

The use of interstitial needles, combined with intracavitary applicators, enables customized dose distributions and is beneficial for complex cases, but increases procedure time. Overall, applicator selection is not standardized and depends on physician expertise and preference. The purpose of this study is to determine whether dose prediction models can guide needle supplementation decision-making for cervical cancer.

MATERIALS AND METHODS

Intracavitary knowledge-based models for organ-at-risk (OAR) dose estimation were trained and validated for tandem-and-ring/ovoids (T&R/T&O) implants. Models were applied to hybrid cases with 1-3 implanted needles to predict OAR dose without needles. As a reference, 70/67 hybrid T&R/T&O cases were replanned without needles, following a standardized procedure guided by dose predictions. If a replanned dose exceeded the dose objective, the case was categorized as requiring needles. Receiver operating characteristic (ROC) curves of needle classification accuracy were generated. Optimal classification thresholds were determined from the Youden Index.

RESULTS

Needle supplementation reduced dose to OARs. However, 67%/39% of replans for T&R/T&O met all dose constraints without needles. The ROC for T&R/T&O models had an area-under-curve of 0.89/0.86, proving high classification accuracy. The optimal threshold of 99%/101% of the dose limit for T&R/T&O resulted in classification sensitivity and specificity of 78%/86% and 85%/78%.

CONCLUSIONS

Needle supplementation reduced OAR dose for most cases but was not always required to meet standard dose objectives, particularly for T&R cases. Our knowledge-based dose prediction model accurately identified cases that could have met constraints without needle supplementation, suggesting that such models may be beneficial for applicator selection.

Knowledge-Based Planning for Intact Cervical Cancer

Cervical cancer radiotherapy is often complicated by significant variability in the quality and consistency of treatment plans. Knowledge-based planning (KBP), which utilizes prior patient data to correlated achievable optimal dosimetry with patient-specific anatomy, has demonstrated promise as a quality control tool for controlling this variability, with consequences for patient outcomes, as well as for the reliability of data from multi-institutional clinical trials. In this article we highlight the application of KBP-based quality control to cervical cancer radiotherapy. We discuss the potential impact of KBP on multi-institutional clinical trials to standardize cervical cancer treatment planning across diverse clinics, and discuss challenges and progress in the implementation of KBP for brachytherapy treatment planning. Additionally, we briefly discuss secondary applications of KBP for cervical cancer. The emerging picture from these studies indicates several exciting opportunities for increasing the utilization of KBP in day-to-day cervical cancer radiotherapy.

A comparison of two methodologies for radiotherapy treatment plan optimization and QA for clinical trials

Background and purpose

The efficacy of clinical trials and the outcome of patient treatment are dependent on the quality assurance (QA) of radiation therapy (RT) plans. There are two widely utilized approaches that include plan optimization guidance created based on patient‐specific anatomy. This study examined these two techniques for dose‐volume histogram predictions, RT plan optimizations, and prospective QA processes, namely the knowledge‐based planning (KBP) technique and another first principle (FP) technique.

Methods

This analysis included 60, 44, and 10 RT plans from three Radiation Therapy Oncology Group (RTOG) multi‐institutional trials: RTOG 0631 (Spine SRS), RTOG 1308 (NSCLC), and RTOG 0522 (H&N), respectively. Both approaches were compared in terms of dose prediction and plan optimization. The dose predictions were also compared to the original plan submitted to the trials for the QA procedure.

Results

For the RTOG 0631 (Spine SRS) and RTOG 0522 (H&N) plans, the dose predictions from both techniques have correlation coefficients of >0.9. The RT plans that were re‐optimized based on the predictions from both techniques showed similar quality, with no statistically significant differences in target coverage or organ‐at‐risk sparing. The predictions of mean lung and heart doses from both methods for RTOG1308 patients, on the other hand, have a discrepancy of up to 14 Gy.

Conclusions

Both methods are valuable tools for optimization guidance of RT plans for Spine SRS and Head and Neck cases, as well as for QA purposes. On the other hand, the findings suggest that KBP may be more feasible in the case of inoperable lung cancer patients who are treated with IMRT plans that have spatially unevenly distributed beam angles.

ORBIT-RT: A Real-Time, Open Platform for Knowledge-Based Quality Control of Radiotherapy Treatment Planning

PURPOSE

Access to knowledge-based treatment plan quality control has been hindered by the complexity of developing models and integration with different treatment planning systems (TPS). Online Real-time Benchmarking Information Technology for RadioTherapy (ORBIT-RT) provides a free, web-based platform for knowledge-based dose estimation that can be used by clinicians worldwide to benchmark the quality of their radiotherapy plans.

MATERIALS AND METHODS

The ORBIT-RT platform was developed to satisfy four primary design criteria: web-based access, TPS independence, Health Insurance Portability and Accountability Act compliance, and autonomous operation. ORBIT-RT uses a cloud-based server to automatically anonymize a user's Digital Imaging and Communications in Medicine for RadioTherapy (DICOM-RT) file before upload and processing of the case. From there, ORBIT-RT uses established knowledge-based dose-volume histogram (DVH) estimation methods to autonomously create DVH estimations for the uploaded DICOM-RT. ORBIT-RT performance was evaluated with an independent validation set of 45 volumetric modulated arc therapy prostate plans with two key metrics: (i) accuracy of the DVH estimations, as quantified by their error, DVH_clinical - DVH_prediction and (ii) time to process and display the DVH estimations on the ORBIT-RT platform.

RESULTS

ORBIT-RT organ DVH predictions show < 1% bias and 3% error uncertainty at doses > 80% of prescription for the prostate validation set. The ORBIT-RT extensions require 3.0 seconds per organ to analyze. The DICOM upload, data transfer, and DVH output display extend the entire system workflow to 2.5-3 minutes.

CONCLUSION

ORBIT-RT demonstrated fast and fully autonomous knowledge-based feedback on a web-based platform that takes only anonymized DICOM-RT as input. The ORBIT-RT system can be used for real-time quality control feedback that provides users with objective comparisons for final plan DVHs.

Personalising treatment plan quality review with knowledge-based planning in the TROG 15.03 trial for stereotactic ablative body radiotherapy in primary kidney cancer

INTRODUCTION

Quality assurance (QA) of treatment plans in clinical trials improves protocol compliance and patient outcomes. Retrospective use of knowledge-based-planning (KBP) in clinical trials has demonstrated improved treatment plan quality and consistency. We report the results of prospective use of KBP for real-time QA of treatment plan quality in the TROG 15.03 FASTRACK II trial, which evaluates efficacy of stereotactic ablative body radiotherapy (SABR) for kidney cancer.

METHODS

A KBP model was generated based on single institution data. For each patient in the KBP phase (open to the last 31 patients in the trial), the treating centre submitted treatment plans 7 days prior to treatment. A treatment plan was created by using the KBP model, which was compared with the submitted plan for each organ-at-risk (OAR) dose constraint. A report comparing each plan for each OAR constraint was provided to the submitting centre within 24 h of receiving the plan. The centre could then modify the plan based on the KBP report, or continue with the existing plan.

RESULTS

Real-time feedback using KBP was provided in 24/31 cases. Consistent plan quality was in general achieved between KBP and the submitted plan. KBP review resulted in replan and improvement of OAR dosimetry in two patients. All centres indicated that the feedback was a useful QA check of their treatment plan.

CONCLUSION

KBP for real-time treatment plan review was feasible for 24/31 cases, and demonstrated ability to improve treatment plan quality in two cases. Challenges include integration of KBP feedback into clinical timelines, interpretation of KBP results with respect to clinical trade-offs, and determination of appropriate plan quality improvement criteria.

Wide-Scale Clinical Implementation of Knowledge-Based Planning: An Investigation of Workforce Efficiency, Need for Post-automation Refinement, and Data-Driven Model Maintenance

PURPOSE

Our purpose was to investigate the effect of automated knowledge-based planning (KBP) on real-world clinical workflow efficiency, assess whether manual refinement of KBP plans improves plan quality across multiple disease sites, and develop a data-driven method to periodically improve KBP automated planning routines.

METHODS AND MATERIALS

Using clinical knowledge-based automated planning routines for prostate, prostatic fossa, head and neck, and hypofractionated lung disease sites in a commercial KBP solution, workflow efficiency was compared in terms of planning time in a pre-KBP (n = 145 plans) and post-KBP (n = 503) patient cohort. Post-KBP, planning was initialized with KBP (KBP-only) and subsequently manually refined (KBP + human). Differences in planning time were tested for significance using a 2-tailed Mann-Whitney U test (P < .05, null hypothesis: planning time unchanged). Post-refinement plan quality was assessed using site-specific dosimetric parameters of the original KBP-only plan versus KBP + human; 2-tailed paired t test quantified statistical significance (Bonferroni-corrected P < .05, null hypothesis: no dosimetric difference after refinement). If KBP + human significantly improved plans across the cohort, optimization objectives were changed to create an updated KBP routine (KBP'). Patients were replanned with KBP' and plan quality was compared with KBP + human as described previously.

RESULTS

KBP significantly reduced planning time in all disease sites: prostate (median: 7.6 hrs → 2.1 hrs; P < .001), prostatic fossa (11.1 hrs → 3.7 hrs; P = .001), lung (9.9 hrs → 2.0 hrs; P < .001), and head and neck (12.9 hrs → 3.5 hrs; P <.001). In prostate, prostatic fossa, and lung disease sites, organ-at-risk dose changes in KBP + human versus KBP-only were minimal (<1% prescription dose). In head and neck, KBP + human did achieve clinically relevant dose reductions in some parameters. The head and neck routine was updated (KBP'_HN) to incorporate dose improvements from manual refinement. The only significant dosimetric differences to KBP + human after replanning with KBP'_HN were in favor of the new routine.

CONCLUSIONS

KBP increased clinical efficiency by significantly reducing planning time. On average, human refinement offered minimal dose improvements over KBP-only plans. In the single disease site where KBP + human was superior to KBP-only, differences were eliminated by adjusting optimization parameters in a revised KBP routine.

Personalized Treatment Planning Automation in Prostate Cancer Radiation Oncology: A Comprehensive Dosimetric Study

Background

In radiation oncology, automation of treatment planning has reported the potential to improve plan quality and increase planning efficiency. We performed a comprehensive dosimetric evaluation of the new Personalized algorithm implemented in Pinnacle³ for full planning automation of VMAT prostate cancer treatments.

Material and Methods

Thirteen low-risk prostate (without lymph-nodes irradiation) and 13 high-risk prostate (with lymph-nodes irradiation) treatments were retrospectively taken from our clinical database and re-optimized using two different automated engines implemented in the Pinnacle treatment system. These two automated engines, the currently used Autoplanning and the new Personalized are both template-based algorithms that use a wish-list to formulate the planning goals and an iterative approach able to mimic the planning procedure usually adopted by experienced planners. In addition, the new Personalized module integrates a new engine, the Feasibility module, able to generate an “a priori” DVH prediction of the achievability of planning goals. Comparison between clinically accepted manually generated (MP) and automated plans generated with both Autoplanning (AP) and Personalized engines (Pers) were performed using dose-volume histogram metrics and conformity indexes. Three different normal tissue complication probabilities (NTCPs) models were used for rectal toxicity evaluation. The planning efficiency and the accuracy of dose delivery were assessed for all plans.

Results

For similar targets coverage, Pers plans reported a significant increase of dose conformity and less irradiation of healthy tissue, with significant dose reduction for rectum, bladder, and femurs. On average, Pers plans decreased rectal mean dose by 11.3 and 8.3 Gy for low-risk and high-risk cohorts, respectively. Similarly, the Pers plans decreased the bladder mean doses by 7.3 and 7.6 Gy for low-risk and high-risk cohorts, respectively. The integral dose was reduced by 11–16% with respect to MP plans. Overall planning times were dramatically reduced to about 7 and 15 min for Pers plans. Despite the increased complexity, all plans passed the 3%/2 mm γ-analysis for dose verification.

Conclusions

The Personalized engine provided an overall increase of plan quality, in terms of dose conformity and sparing of normal tissues for prostate cancer patients. The Feasibility “a priori” DVH prediction module provided OARs dose sparing well beyond the clinical objectives. The new Pinnacle Personalized algorithms outperformed the currently used Autoplanning ones as solution for treatment planning automation.

Assessment of a conventional volumetric-modulated arc therapy knowledge-based planning model applied to the new Halcyon© O-ring linac in locoregional breast cancer radiotherapy

INTRODUCTION

The aim of this study was to evaluate the performance of a knowledge-based planning (KBP) model for breast cancer trained on plans performed on a conventional linac with 6 MV FF (flattening filter) beams and volumetric-modulated arc therapy (VMAT) for plans performed on the new jawless Halcyon© system with 6 MV FFF (flattening filter-free) beams.

MATERIALS AND METHODS

Based on the RapidPlan© (RP) KBP optimization engine, a DVH Estimation Model was first trained using 56 VMAT left-sided breast cancer treatment plans performed on a conventional linac, and validated on another 20 similar cases (without manual intervention). To determine the capacity of the model for Halcyon©, an additional cohort of 20 left-sided breast cancer plans was generated with RP and analyzed for both TrueBeam© and Halcyon© machines. Plan qualities between manual vs RP (followed by manual intervention) Halcyon© plans set were compared qualitatively by blinded review by radiation oncologists for 10 new independent plans.

RESULTS

Halcyon© plans generated with the VMAT model trained with conventional linac plans showed comparable target dose distribution compared to TrueBeam© plans. Organ sparingwas comparable between the 2 devices with a slight decrease in heart dose for Halcyon© plans. Nine out of ten automatically generated Halcyon© plans were preferentially chosen by the radiation oncologists over the manually generated Halcyon© plans.

CONCLUSION

A VMAT KBP model driven by plans performed on a conventional linac with 6 MV FF beams provides high quality plans performed with 6 MV FFF beams on the new Halcyon© linac.

Prediction of Three-Dimensional Radiotherapy Optimal Dose Distributions for Lung Cancer Patients With Asymmetric Network

The iterative design of radiotherapy treatment plans is time-consuming and labor-intensive. In order to provide a guidance to treatment planning, Asymmetric network (A-Net) is proposed to predict the optimal 3D dose distribution for lung cancer patients. A-Net was trained and tested in 392 lung cancer cases with the prescription doses of 50Gy and 60Gy. In A-Net, the encoder and decoder are asymmetric, able to preserve input information and to adapt the limitation of GPU memory. Squeeze and excitation (SE) units are used to improve the data-fitting ability. A loss function involving both the dose distribution and prescription dose as ground truth are designed. In the experiment, A-Net is separately trained and tested in the 50Gy and 60Gy dataset and most of the metrics A-Net achieve similar performance as HD-Unet and 3D-Unet, and some metrics slightly better. In the 50Gy-and-60Gy-combined dataset, most of the A-Net's metrics perform better than the other two. In conclusion, A-Net can accurately predict the IMRT dose distribution in the three datasets of 50Gy and 50Gy-and-60Gy-combined dataset.

Quality assurance-based optimization (QAO): Towards improving patient-specific quality assurance in volumetric modulated arc therapy plans using machine learning

INTRODUCTION

Previous literature has shown general trade-offs between plan complexity and resulting quality assurance (QA) outcomes. However, existing solutions for controlling this trade-off do not guarantee corresponding improvements in deliverability. Therefore, this work explored the feasibility of an optimization framework for directly maximizing predicted QA outcomes of plans without compromising the dosimetric quality of plans designed with an established knowledge-based planning (KBP) technique.

MATERIALS AND METHODS

A support vector machine (SVM) was developed - using a database of 500 previous VMAT plans - to predict gamma passing rates (GPRs; 3%/3mm percent dose-difference/distance-to-agreement with local normalization) based on selected complexity features. A heuristic, QA-based optimization (QAO) framework was devised by utilizing the SVM model to iteratively modify mechanical treatment features most commonly associated with suboptimal GPRs. Specifically, leaf gaps (LGs) <50 mm were widened by random amounts, which impacts all aperture-based complexity features. 13 prostate KBP-guided VMAT plans were optimized via QAO using user-specified maximum LG displacements before corresponding changes in predicted GPRs and dose were assessed.

RESULTS

Predicted GPRs increased by an average of 1.14 ± 1.25% (p = 0.006) with QAO using a 3 mm maximum random LG displacement. There were small differences in dose, resulting in similarly small changes in tumor control probability (maximum increase = 0.05%) and normal tissue complication probabilities in the bladder, rectum, and femoral heads (maximum decrease = 0.2% in the rectum).

CONCLUSION

This study explored the feasibility of QAO and warrants future investigations of further incorporating QA endpoints into plan optimization.

A practical method to quantify knowledge-based DVH prediction accuracy and uncertainty with reference cohorts

The adoption of knowledge-based dose-volume histogram (DVH) prediction models for assessing organ-at-risk (OAR) sparing in radiotherapy necessitates quantification of prediction accuracy and uncertainty. Moreover, DVH prediction error bands should be readily interpretable as confidence intervals in which to find a percentage of clinically acceptable DVHs. In the event such DVH error bands are not available, we present an independent error quantification methodology using a local reference cohort of high-quality treatment plans, and apply it to two DVH prediction models, ORBIT-RT and RapidPlan, trained on the same set of 90 volumetric modulated arc therapy (VMAT) plans. Organ-at-risk DVH predictions from each model were then generated for a separate set of 45 prostate VMAT plans. Dose-volume histogram predictions were then compared to their analogous clinical DVHs to define prediction errorsV c l i n , i - V p r e d , i (ith plan), from which prediction bias μ, prediction error variation σ, and root-mean-square error R M S E pred ≡ 1 N ∑ i V c l i n , i - V p r e d , i 2 ≅ σ 2 + μ 2 could be calculated for the cohort. The empirical R M S E pred was then contrasted to the model-provided DVH error estimates. For all prostate OARs, above 50% Rx dose, ORBIT-RT μ and σ were comparable to or less than those of RapidPlan. Above 80% Rx dose, μ < 1% and σ < 3-4% for both models. As a result, above 50% Rx dose, ORBIT-RT R M S E pred was below that of RapidPlan, indicating slightly improved accuracy in this cohort. Because μ ≈ 0, R M S E pred is readily interpretable as a canonical standard deviation σ, whose error band is expected to correctly predict 68% of normally distributed clinical DVHs. By contrast, RapidPlan's provided error band, although described in literature as a standard deviation range, was slightly less predictive than R M S E pred (55-70% success), while the provided ORBIT-RT error band was confirmed to resemble an interquartile range (40-65% success) as described. Clinicians can apply this methodology using their own institutions' reference cohorts to (a) independently assess a knowledge-based model's predictive accuracy of local treatment plans, and (b) interpret from any error band whether further OAR dose sparing is likely attainable.

Personalized automation of treatment planning in head-neck cancer: A step forward for quality in radiation therapy?

PURPOSE

To perform a comprehensive dosimetric and clinical evaluation of the new Pinnacle Personalized automated planning system for complex head-and-neck treatments.

METHODS

Fifteen consecutive head-neck patients were enrolled. Radiotherapy was prescribed using VMAT with simultaneous integrated boost strategy. Personalized planning integrates the Feasibility engine able to supply an "a priori" DVH prediction of the achievability of planning goals. Comparison between clinically accepted manually-generated (MP) and automated (AP) plans was performed using dose-volume histograms and a blinded clinical evaluation by two radiation oncologists. Planning time between MP and AP was compared. Dose accuracy was validated using the PTW Octavius-4D phantom together with the 1500 2D-array.

RESULTS

For similar targets coverage, AP plans reported less irradiation of healthy tissue, with significant dose reduction for spinal cord, brainstem and parotids. On average, the mean dose to parotids and maximal doses to spinal cord and brainstem were reduced by 13-15% (p < 0.001), 9% (p < 0.001) and 16% (p < 0.001), respectively. The integral dose was reduced by 16% (p < 0.001). The dose conformity for the three PTVs was significantly higher with AP plans (p < 0.001). The two oncologists chose AP plans in more than 80% of cases. Overall planning times were reduced to <30 min for automated optimization. All AP plans passed the 3%/2 mm γ-analysis by more than 95%.

CONCLUSION

Complex head-neck plans created using Personalized automated engine provided an overall increase of plan quality, in terms of dose conformity and sparing of normal tissues. The Feasibility module allowed OARs dose sparing well beyond the clinical objectives.

Evaluation of a generalized knowledge-based planning performance for VMAT irradiation of breast and locoregional lymph nodes-Internal mammary and/or supraclavicular regions

PURPOSE

To evaluate the performance of eleven Knowledge-Based (KB) models for planning optimization (RapidPlantm (RP), Varian) of Volumetric Modulated Arc Therapy (VMAT) applied to whole breast comprehensive of nodal stations, internal mammary and/or supraclavicular regions.

METHODS AND MATERIALS

Six RP models have been generated and trained based on 120 VMAT plans data set with different criteria. Two extra-structures were delineated: a PTV for the optimization and a ring structure. Five more models, twins of the previous models, have been created without the need of these structures.

RESULTS

All models were successfully validated on an independent cohort of 40 patients, 30 from the same institute that provided the training patients and 10 from an additional institute, with the resulting plans being of equal or better quality compared with the clinical plans. The internal validation shows that the models reduce the heart maximum dose of about 2 Gy, the mean dose of about 1 Gy and the V20Gy of 1.5 Gy on average. Model R and L together with model B without optimization structures ensured the best outcomes in the 20% of the values compared to other models. The external validation observed an average improvement of at least 16% for the V5Gy of lungs in RP plans. The mean heart dose and for the V20Gy for lung IPSI were almost halved. The models reduce the maximum dose for the spinal canal of more than 2 Gy on average.

CONCLUSIONS

All KB models allow a homogeneous plan quality and some dosimetric gains, as we saw in both internal and external validation. Sub-KB models, developed by splitting right and left breast cases or including only whole breast with locoregional lymph nodes, have shown good performances, comparable but slightly worse than the general model. Finally, models generated without the optimization structures, performed better than the original ones.