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.

Operational Ontology for Oncology (O3): A Professional Society-Based, Multistakeholder, Consensus-Driven Informatics Standard Supporting Clinical and Research Use of Real-World Data From Patients Treated for Cancer.

PURPOSE: The ongoing lack of data standardization severely undermines the potential for automated learning from the vast amount of information routinely archived in electronic health records (EHRs), radiation oncology information systems, treatment planning systems, and other cancer care and outcomes databases. We sought to create a standardized ontology for clinical data, social determinants of health, and other radiation oncology concepts and interrelationships. METHODS AND MATERIALS: The American Association of Physicists in Medicine's Big Data Science Committee was initiated in July 2019 to explore common ground from the stakeholders' collective experience of issues that typically compromise the formation of large inter- and intra-institutional databases from EHRs. The Big Data Science Committee adopted an iterative, cyclical approach to engaging stakeholders beyond its membership to optimize the integration of diverse perspectives from the community. RESULTS: We developed the Operational Ontology for Oncology (O3), which identified 42 key elements, 359 attributes, 144 value sets, and 155 relationships ranked in relative importance of clinical significance, likelihood of availability in EHRs, and the ability to modify routine clinical processes to permit aggregation. Recommendations are provided for best use and development of the O3 to 4 constituencies: device manufacturers, centers of clinical care, researchers, and professional societies. CONCLUSIONS: O3 is designed to extend and interoperate with existing global infrastructure and data science standards. The implementation of these recommendations will lower the barriers for aggregation of information that could be used to create large, representative, findable, accessible, interoperable, and reusable data sets to support the scientific objectives of grant programs. The construction of comprehensive "real-world" data sets and application of advanced analytical techniques, including artificial intelligence, holds the potential to revolutionize patient management and improve outcomes by leveraging increased access to information derived from larger, more representative data sets.

Domain adaptation of automated treatment planning from computed tomography to magnetic resonance.

Objective.Machine learning (ML) based radiation treatment planning addresses the iterative and time-consuming nature of conventional inverse planning. Given the rising importance of magnetic resonance (MR) only treatment planning workflows, we sought to determine if an ML based treatment planning model, trained on computed tomography (CT) imaging, could be applied to MR through domain adaptation.Methods.In this study, MR and CT imaging was collected from 55 prostate cancer patients treated on an MR linear accelerator. ML based plans were generated for each patient on both CT and MR imaging using a commercially available model in RayStation 8B. The dose distributions and acceptance rates of MR and CT based plans were compared using institutional dose-volume evaluation criteria. The dosimetric differences between MR and CT plans were further decomposed into setup, cohort, and imaging domain components.Results.MR plans were highly acceptable, meeting 93.1% of all evaluation criteria compared to 96.3% of CT plans, with dose equivalence for all evaluation criteria except for the bladder wall, penile bulb, small and large bowel, and one rectum wall criteria (p< 0.05). Changing the input imaging modality (domain component) only accounted for about half of the dosimetric differences observed between MR and CT plans. Anatomical differences between the ML training set and the MR linac cohort (cohort component) were also a significant contributor.Significance.We were able to create highly acceptable MR based treatment plans using a CT-trained ML model for treatment planning, although clinically significant dose deviations from the CT based plans were observed. Future work should focus on combining this framework with atlas selection metrics to create an interpretable quality assurance QA framework for ML based treatment planning.

SuPART: supervised projective adapted resonance theory for automatic quality assurance approval of radiotherapy treatment plans.

Radiotherapy is a common treatment modality for the treatment of cancer, where treatments must be carefully designed to deliver appropriate dose to targets while avoiding healthy organs. The comprehensive multi-disciplinary quality assurance (QA) process in radiotherapy is designed to ensure safe and effective treatment plans are delivered to patients. However, the plan QA process is expensive, often time-intensive, and requires review of large quantities of complex data, potentially leading to human error in QA assessment. We therefore develop an automated machine learning algorithm to identify 'acceptable' plans (plans that are similar to historically approved plans) and 'unacceptable' plans (plans that are dissimilar to historically approved plans). This algorithm is a supervised extension of projective adaptive resonance theory, called SuPART, that learns a set of distinctive features, and considers deviations from them indications of unacceptable plans. We test SuPART on breast and prostate radiotherapy datasets from our institution, and find that SuPART outperforms common classification algorithms in several measures of accuracy. When no falsely approved plans are allowed, SuPART can correctly auto-approve 34% of the acceptable breast and 32% of the acceptable prostate plans, and can also correctly reject 53% of the unacceptable breast and 56% of the unacceptable prostate plans. Thus, usage of SuPART to aid in QA could potentially yield significant time savings.

A pilot study of machine-learning based automated planning for primary brain tumours.

PURPOSE: High-quality radiotherapy (RT) planning for children and young adults with primary brain tumours is essential to minimize the risk of late treatment effects. The feasibility of using automated machine-learning (ML) to aid RT planning in this population has not previously been studied. METHODS AND MATERIALS: We developed a ML model that identifies learned relationships between image features and expected dose in a training set of 95 patients with a primary brain tumour treated with focal radiotherapy to a dose of 54 Gy in 30 fractions. This ML method was then used to create predicted dose distributions for 15 previously-treated brain tumour patients across two institutions, as a testing set. Dosimetry to target volumes and organs-at-risk (OARs) were compared between the clinically-delivered (human-generated) plans versus the ML plans. RESULTS: The ML method was able to create deliverable plans in all 15 patients in the testing set. All ML plans were generated within 30 min of initiating planning. Planning target volume coverage with 95% of the prescription dose was attained in all plans. OAR doses were similar across most structures evaluated; mean doses to brain and left temporal lobe were lower in ML plans than manual plans (mean difference to left temporal, - 2.3 Gy, p = 0.006; mean differences to brain, - 1.3 Gy, p = 0.017), whereas mean doses to right cochlea and lenses were higher in ML plans (+ 1.6-2.2 Gy, p < 0.05 for each). CONCLUSIONS: Use of an automated ML method to aid RT planning for children and young adults with primary brain tumours is dosimetrically feasible and can be successfully used to create high-quality 54 Gy RT plans. Further evaluation after clinical implementation is planned.

Understanding machine learning classifier decisions in automated radiotherapy quality assurance.

The complexity of generating radiotherapy treatments demands a rigorous quality assurance (QA) process to ensure patient safety and to avoid clinically significant errors. Machine learning classifiers have been explored to augment the scope and efficiency of the traditional radiotherapy treatment planning QA process. However, one important gap in relying on classifiers for QA of radiotherapy treatment plans is the lack of understanding behind a specific classifier prediction. We develop explanation methods to understand the decisions of two automated QA classifiers: (1) a region of interest (ROI) segmentation/labeling classifier, and (2) a treatment plan acceptance classifier. For each classifier, a local interpretable model-agnostic explanation (LIME) framework and a novel adaption of team-based Shapley values framework are constructed. We test these methods in datasets for two radiotherapy treatment sites (prostate and breast), and demonstrate the importance of evaluating QA classifiers using interpretable machine learning approaches. We additionally develop a notion of explanation consistency to assess classifier performance. Our explanation method allows for easy visualization and human expert assessment of classifier decisions in radiotherapy QA. Notably, we find that our team-based Shapley approach is more consistent than LIME. The ability to explain and validate automated decision-making is critical in medical treatments. This analysis allows us to conclude that both QA classifiers are moderately trustworthy and can be used to confirm expert decisions, though the current QA classifiers should not be viewed as a replacement for the human QA process.

Magnetic Resonance Imaging for Breast Tumor Bed Delineation: Computed Tomography Comparison and Sequence Variation.

PURPOSE: Our purpose was to investigate the interobserver variability in breast tumor bed delineation using magnetic resonance (MR) compared with computed tomography (CT) at baseline and to quantify the change in tumor bed volume between pretreatment and end-of-treatment MR for patients undergoing whole breast radiation therapy. METHODS AND MATERIALS: Forty-eight patients with breast cancer planned for whole breast radiation therapy underwent CT and MR (T1, T1 fat-suppression [T1fs], and T2) simulation in the supine treatment position before radiation therapy and MR (T1, T1fs, and T2) at the end of treatment in the same position. Two observers delineated 50 tumor beds on the CT and all MR sequences and assigned cavity visualization scores to the images. The primary endpoint was interobserver variability, measured using the conformity index (CI). RESULTS: The mean cavity visualization scores at baseline were 3.14 (CT), 3.26 (T1), 3.41 (T1fs), and 3.58 (T2). The mean CIs were 0.65, 0.65, 0.72, and 0.68, respectively. T1fs significantly improved interobserver variability compared with CT, T1, or T2 (P < .001, P < .001, and P = .011, respectively). The CI for T1fs was significantly higher than T1 and T2 at the end of treatment (mean 0.72, 0.64, and 0.66, respectively; P < .001). The mean tumor bed volume on the T1fs sequence decreased from 18 cm3 at baseline to 13 cm3 at the end of treatment (P < .01). CONCLUSIONS: T1fs reduced interobserver variability on both pre- and end-of-treatment scans and measured a reduction in tumor bed volume during whole breast radiation therapy. This rapid sequence could be easily used for adaptive boost or partial breast irradiation, especially on MR linear accelerators.

Performance stability evaluation of atlas-based machine learning radiation therapy treatment planning in prostate cancer.

Atlas-based machine learning (ML) for radiation therapy (RT) treatment planning is effective at tailoring dose distributions to account for unique patient anatomies by selecting the most appropriate patients from the training database (atlases) to inform dose prediction for new patients. However, variations in clinical practice between the training dataset and a new patient to be planned may impact ML performance by confounding atlas selection. In this study, we simulated various contouring practices in prostate cancer RT to investigate the impact of changing input data on atlas-based ML treatment planning. We generated 225 ML plans for nine bespoke contouring protocol scenarios (reduced target margins, modified organ-at-risk (OAR) definitions, and inclusion of optional OARs less represented in the training database) on 25 patient datasets by applying a single, previously trained and validated ML model for prostate cancer followed by dose mimicking to create a final deliverable plan. ML treatment plans for each scenario were compared to base ML treatment plans that followed a contouring protocol consistent with the model training data. ML performance was evaluated based on atlas distance metrics that are calculated during ML dose prediction. There were significant changes between atlases selected for the base ML treatment plans and treatment plans when planning target volume margins were reduced and/or optional OARs were included. The deliverability of ML predicted dose distributions based on gamma analysis between predicted and mimicked final deliverable dose showed significant differences for seven out of eight scenarios compared with the base ML treatment plans. Overall, there were small but statistically significant dosimetric changes in predicted and mimicked dose with addition of optional OAR contours. This work presents a framework for benchmarking and performance monitoring of ML treatment planning algorithms in the context of evolving clinical practices.

OpenKBP: The open-access knowledge-based planning grand challenge and dataset.

PURPOSE: To advance fair and consistent comparisons of dose prediction methods for knowledge-based planning (KBP) in radiation therapy research. METHODS: We hosted OpenKBP, a 2020 AAPM Grand Challenge, and challenged participants to develop the best method for predicting the dose of contoured computed tomography (CT) images. The models were evaluated according to two separate scores: (a) dose score, which evaluates the full three-dimensional (3D) dose distributions, and (b) dose-volume histogram (DVH) score, which evaluates a set DVH metrics. We used these scores to quantify the quality of the models based on their out-of-sample predictions. To develop and test their models, participants were given the data of 340 patients who were treated for head-and-neck cancer with radiation therapy. The data were partitioned into training ( n = 200 ), validation ( n = 40 ), and testing ( n = 100 ) datasets. All participants performed training and validation with the corresponding datasets during the first (validation) phase of the Challenge. In the second (testing) phase, the participants used their model on the testing data to quantify the out-of-sample performance, which was hidden from participants and used to determine the final competition ranking. Participants also responded to a survey to summarize their models. RESULTS: The Challenge attracted 195 participants from 28 countries, and 73 of those participants formed 44 teams in the validation phase, which received a total of 1750 submissions. The testing phase garnered submissions from 28 of those teams, which represents 28 unique prediction methods. On average, over the course of the validation phase, participants improved the dose and DVH scores of their models by a factor of 2.7 and 5.7, respectively. In the testing phase one model achieved the best dose score (2.429) and DVH score (1.478), which were both significantly better than the dose score (2.564) and the DVH score (1.529) that was achieved by the runner-up models. Lastly, many of the top performing teams reported that they used generalizable techniques (e.g., ensembles) to achieve higher performance than their competition. CONCLUSION: OpenKBP is the first competition for knowledge-based planning research. The Challenge helped launch the first platform that enables researchers to compare KBP prediction methods fairly and consistently using a large open-source dataset and standardized metrics. OpenKBP has also democratized KBP research by making it accessible to everyone, which should help accelerate the progress of KBP research. The OpenKBP datasets are available publicly to help benchmark future KBP research.

Clinical integration of machine learning for curative-intent radiation treatment of patients with prostate cancer.

Machine learning (ML) holds great promise for impacting healthcare delivery; however, to date most methods are tested in 'simulated' environments that cannot recapitulate factors influencing real-world clinical practice. We prospectively deployed and evaluated a random forest algorithm for therapeutic curative-intent radiation therapy (RT) treatment planning for prostate cancer in a blinded, head-to-head study with full integration into the clinical workflow. ML- and human-generated RT treatment plans were directly compared in a retrospective simulation with retesting (n = 50) and a prospective clinical deployment (n = 50) phase. Consistently throughout the study phases, treating physicians assessed ML- and human-generated RT treatment plans in a blinded manner following a priori defined standardized criteria and peer review processes, with the selected RT plan in the prospective phase delivered for patient treatment. Overall, 89% of ML-generated RT plans were considered clinically acceptable and 72% were selected over human-generated RT plans in head-to-head comparisons. RT planning using ML reduced the median time required for the entire RT planning process by 60.1% (118 to 47 h). While ML RT plan acceptability remained stable between the simulation and deployment phases (92 versus 86%), the number of ML RT plans selected for treatment was significantly reduced (83 versus 61%, respectively). These findings highlight that retrospective or simulated evaluation of ML methods, even under expert blinded review, may not be representative of algorithm acceptance in a real-world clinical setting when patient care is at stake.

Rapid Adaptation of Breast Radiation Therapy Use During the Coronavirus Disease 2019 Pandemic at a Large Academic Cancer Center in Canada.

PURPOSE: Mitigation strategies to balance the risk of coronavirus disease 2019 (COVID-19) infection against oncologic risk in patients with breast cancer undergoing radiation therapy have been deployed. To this end, shorter hypofractionated regimens have been recommended where appropriate, with prioritization of radiation therapy by oncologic risk and omission or deferral of radiation therapy for lower risk cases. Timely adoption of these measures reduces COVID-19 risk to both patients and health care workers and preserves resources. Herein, we present our early response and adaptation of breast radiation therapy utilization during the COVID-19 pandemic at a large academic cancer center in Canada. METHODS AND MATERIALS: A state of emergency was announced in Ontario on March 17, 2020, owing to the COVID-19 pandemic. Emergency guidelines were instituted. To examine our response, the number of weekly breast radiation therapy starts, type of breast radiation therapy, and patient age were compared from March 1 to April 30, 2020 to the same period in 2019. RESULTS: After the declaration of emergency in Ontario, there was a decrease of 39% in radiation therapy starts in 2020 compared with 2019 (79 vs 129, P < .001). There was a relative increase in the proportion of patients receiving regional nodal irradiation (RNI) in 2020 compared with 2019 (46% vs 29%, respectively), with the introduction of hypofractionated RNI in 2020 (27 of 54 cases, 50%). A smaller proportion of patients starting radiation therapy were aged >50 years in 2020, 66% (78 of 118) versus 83% (132 of 160) in 2019, P = .0027. CONCLUSIONS: A significant reduction in breast radiation therapy starts was noted during the early response to the COVID-19 pandemic, with prioritization of radiation therapy to patients associated with higher oncologic risk requiring RNI. A quick response to a health care crisis is critical and is of particular importance for higher volume cancer sites where the potential effect on resources is greater.

An Innovative Learning Tool for Radiation Therapy Treatment Plan Evaluation: Implementation and Evaluation.

PURPOSE: To design, develop, and evaluate an interactive simulation-based learning tool for treatment plan evaluation for radiation oncology and medical physics residents to address gaps in learning. METHODS AND MATERIALS: We first conducted a needs assessment for optimal learning tool design and case selection. Next, we generated a curated database of cases with clinically unacceptable treatment plans accessible through an in-house developed interactive web-based digital imaging and communications in medicine-radiation therapy viewer. We then developed an interactive user module that allows case selection, learner participation, and immediate feedback, including the final clinically acceptable plan. We pilot tested this case bank learning tool with current radiation oncology and medical physics residents within our institution. Afterward, residents completed an evaluation of tool design, content, and perceived impact on learning and provided suggestions for improvement. RESULTS: We generated 70 cases and learning modules for the case bank, encompassing various clinical sites, levels of difficulty, and classified errors. Residents positively endorsed the learning tool, including design, content, and perceived impact on learning. The learning tool's interactivity was perceived to provide increased educational value compared with other current learning methods. CONCLUSIONS: We created a high-fidelity simulation platform for treatment plan evaluation linked to a curated case bank. Evaluation of the pilot deployment demonstrated a benefit for resident learning and competency attainment. Future directions include external validation and expansion.

The Role of Partial Breast Radiation in the Previously Radiated Breast.

OBJECTIVES: The aim of this study was to analyze breast cancer patients who previously had mantle-field or breast radiation (RT) followed by retreatment with external beam partial breast irradiation (EB PBI). MATERIALS AND METHODS: We retrospectively reviewed all women with newly diagnosed early-stage breast cancer treated with lumpectomy and partial breast irradiation between 2007 and 2017 who had undergone prior chest or breast RT. RESULTS: Of 11 patients recorded, 8 (73%) had Hodgkin lymphoma, and 3 (27%) had ipsilateral breast cancer diagnosis. Median age at initial and second diagnosis was 28 and 48 years, respectively. The lymphoma patients received a dose of 35 Gy in 16 to 20 fractions to a classic mantle-upper abdomen field. Patients with an initial diagnosis of breast cancer received whole-breast RT (2 with 50 Gy/25 fractions, 1 with 40 Gy in 16 fractions). Median time from initial to second diagnosis was 22.6 years (range, 13.5 to 32.6 y). All had early-stage (I to II) invasive ductal carcinoma and were treated with lumpectomy or repeat lumpectomy and EB PBI. Four received a dose of 45 Gy/25 fractions, 4 to 50 Gy/25 fractions, and 3 to 42.4 Gy/16 fractions. All patients received adjuvant systemic treatment. Two patients had toxicity, 1 had grade 1 induration, and the other had grade 2 fat atrophy and grade 1 fibrosis. One patient developed a contralateral breast cancer. No locoregional recurrences were reported at the median follow-up of 4.6 years (range, 0.6 to 10.5 y). CONCLUSION: EB PBI after lumpectomy seems to be a safe and effective RT treatment option for selected patients with prior RT and localized early-stage breast cancer.

Vulnerabilities of radiomic signature development: The need for safeguards.

PURPOSE: Refinement of radiomic results and methodologies is required to ensure progression of the field. In this work, we establish a set of safeguards designed to improve and support current radiomic methodologies through detailed analysis of a radiomic signature. METHODS: A radiomic model (MW2018) was fitted and externally validated using features extracted from previously reported lung and head and neck (H&N) cancer datasets using gross-tumour-volume contours, as well as from images with randomly permuted voxel index values; i.e. images without meaningful texture. To determine MW2018's added benefit, the prognostic accuracy of tumour volume alone was calculated as a baseline. RESULTS: MW2018 had an external validation concordance index (c-index) of 0.64. However, a similar performance was achieved using features extracted from images with randomized signal intensities (c-index = 0.64 and 0.60 for H&N and lung, respectively). Tumour volume had a c-index = 0.64 and correlated strongly with three of the four model features. It was determined that the signature was a surrogate for tumour volume and that intensity and texture values were not pertinent for prognostication. CONCLUSION: Our experiments reveal vulnerabilities in radiomic signature development processes and suggest safeguards that can be used to refine methodologies, and ensure productive radiomic development using objective and independent features.

American Association of Physicists in Medicine Task Group 263: Standardizing Nomenclatures in Radiation Oncology.

A substantial barrier to the single- and multi-institutional aggregation of data to supporting clinical trials, practice quality improvement efforts, and development of big data analytics resource systems is the lack of standardized nomenclatures for expressing dosimetric data. To address this issue, the American Association of Physicists in Medicine (AAPM) Task Group 263 was charged with providing nomenclature guidelines and values in radiation oncology for use in clinical trials, data-pooling initiatives, population-based studies, and routine clinical care by standardizing: (1) structure names across image processing and treatment planning system platforms; (2) nomenclature for dosimetric data (eg, dose-volume histogram [DVH]-based metrics); (3) templates for clinical trial groups and users of an initial subset of software platforms to facilitate adoption of the standards; (4) formalism for nomenclature schema, which can accommodate the addition of other structures defined in the future. A multisociety, multidisciplinary, multinational group of 57 members representing stake holders ranging from large academic centers to community clinics and vendors was assembled, including physicists, physicians, dosimetrists, and vendors. The stakeholder groups represented in the membership included the AAPM, American Society for Radiation Oncology (ASTRO), NRG Oncology, European Society for Radiation Oncology (ESTRO), Radiation Therapy Oncology Group (RTOG), Children's Oncology Group (COG), Integrating Healthcare Enterprise in Radiation Oncology (IHE-RO), and Digital Imaging and Communications in Medicine working group (DICOM WG); A nomenclature system for target and organ at risk volumes and DVH nomenclature was developed and piloted to demonstrate viability across a range of clinics and within the framework of clinical trials. The final report was approved by AAPM in October 2017. The approval process included review by 8 AAPM committees, with additional review by ASTRO, European Society for Radiation Oncology (ESTRO), and American Association of Medical Dosimetrists (AAMD). This Executive Summary of the report highlights the key recommendations for clinical practice, research, and trials.

Guided undersampling classification for automated radiation therapy quality assurance of prostate cancer treatment.

PURPOSE: To test the use of well-studied and widely used classification methods alongside newly developed data-filtering techniques specifically designed for imbalanced-data classification in order to demonstrate proof of principle for an automated radiation therapy (RT) quality assurance process on prostate cancer treatment. METHODS: A series of acceptable (majority class, n = 61) and erroneous (minority class, n = 12) RT plans as well as a disjoint set of acceptable plans used to develop features (n = 273) were used to develop a dataset for testing. A series of five widely used imbalanced-data classification algorithms were tested with a modularized guided undersampling procedure that includes ensemble-outlier filtering and normalized-cut sampling. RESULTS: Hybrid methods including either ensemble-outlier filtering or both filtering and normalized-cut sampling yielded the strongest performance in identifying unacceptable treatment plans. Specifically, five methods demonstrated superior performance in both area under the receiver operating characteristics curve and false positive rate when the true positive rate is equal to one. Furthermore, ensemble-outlier filtering significantly improved results in all but one hybrid method (p < 0.01). Finally, ensemble-outlier filtering methods identified four minority instances that were considered outliers in over 96% of cross-validation iterations. Such instances may be considered distinct planning errors and merit additional inspection, providing potential areas of improvement for the planning process. CONCLUSIONS: Traditional imbalanced-data classification methods combined with ensemble-outlier filtering and normalized-cut sampling provide a powerful framework for identifying erroneous RT treatment plans. The proposed methodology yielded strong classification performance and identified problematic instances with high accuracy.

Fully automated treatment planning for head and neck radiotherapy using a voxel-based dose prediction and dose mimicking method.

Recent works in automated radiotherapy treatment planning have used machine learning based on historical treatment plans to infer the spatial dose distribution for a novel patient directly from the planning image. We present a probabilistic, atlas-based approach which predicts the dose for novel patients using a set of automatically selected most similar patients (atlases). The output is a spatial dose objective, which specifies the desired dose-per-voxel, and therefore replaces the need to specify and tune dose-volume objectives. Voxel-based dose mimicking optimization then converts the predicted dose distribution to a complete treatment plan with dose calculation using a collapsed cone convolution dose engine. In this study, we investigated automated planning for right-sided oropharaynx head and neck patients treated with IMRT and VMAT. We compare four versions of our dose prediction pipeline using a database of 54 training and 12 independent testing patients by evaluating 14 clinical dose evaluation criteria. Our preliminary results are promising and demonstrate that automated methods can generate comparable dose distributions to clinical. Overall, automated plans achieved an average of 0.6% higher dose for target coverage evaluation criteria, and 2.4% lower dose at the organs at risk criteria levels evaluated compared with clinical. There was no statistically significant difference detected in high-dose conformity between automated and clinical plans as measured by the conformation number. Automated plans achieved nine more unique criteria than clinical across the 12 patients tested and automated plans scored a significantly higher dose at the evaluation limit for two high-risk target coverage criteria and a significantly lower dose in one critical organ maximum dose. The novel dose prediction method with dose mimicking can generate complete treatment plans in 12-13 min without user interaction. It is a promising approach for fully automated treatment planning and can be readily applied to different treatment sites and modalities.

Voxel-based dose prediction with multi-patient atlas selection for automated radiotherapy treatment planning.

Automating the radiotherapy treatment planning process is a technically challenging problem. The majority of automated approaches have focused on customizing and inferring dose volume objectives to be used in plan optimization. In this work we outline a multi-patient atlas-based dose prediction approach that learns to predict the dose-per-voxel for a novel patient directly from the computed tomography planning scan without the requirement of specifying any objectives. Our method learns to automatically select the most effective atlases for a novel patient, and then map the dose from those atlases onto the novel patient. We extend our previous work to include a conditional random field for the optimization of a joint distribution prior that matches the complementary goals of an accurately spatially distributed dose distribution while still adhering to the desired dose volume histograms. The resulting distribution can then be used for inverse-planning with a new spatial dose objective, or to create typical dose volume objectives for the canonical optimization pipeline. We investigated six treatment sites (633 patients for training and 113 patients for testing) and evaluated the mean absolute difference in all DVHs for the clinical and predicted dose distribution. The results on average are favorable in comparison to our previous approach (1.91 versus 2.57). Comparing our method with and without atlas-selection further validates that atlas-selection improved dose prediction on average in whole breast (0.64 versus 1.59), prostate (2.13 versus 4.07), and rectum (1.46 versus 3.29) while it is less important in breast cavity (0.79 versus 0.92) and lung (1.33 versus 1.27) for which there is high conformity and minimal dose shaping. In CNS brain, atlas-selection has the potential to be impactful (3.65 versus 5.09), but selecting the ideal atlas is the most challenging.