Standardizing Normal Tissue Contouring for Radiation Therapy Treatment Planning: An ASTRO Consensus Paper

Retinopathy, Optic Neuropathy, and Cataract in Childhood Cancer Survivors Treated With Radiation Therapy: A PENTEC Comprehensive Review

PURPOSE

Few reports describe the risks of late ocular toxicities after radiation therapy (RT) for childhood cancers despite their effect on quality of life. The Pediatric Normal Tissue Effects in the Clinic (PENTEC) ocular task force aims to quantify the radiation dose dependence of select late ocular adverse effects. Here, we report results concerning retinopathy, optic neuropathy, and cataract in childhood cancer survivors who received cranial RT.

METHODS AND MATERIALS

A systematic literature search was performed using the PubMed, MEDLINE, and Cochrane Library databases for peer-reviewed studies published from 1980 to 2021 related to childhood cancer, RT, and ocular endpoints including dry eye, keratitis/corneal injury, conjunctival injury, cataract, retinopathy, and optic neuropathy. This initial search yielded abstracts for 2947 references, 269 of which were selected as potentially having useful outcomes and RT data. Data permitting, treatment and outcome data were used to generate normal tissue complication probability models.

RESULTS

We identified sufficient RT data to generate normal tissue complication probability models for 3 endpoints: retinopathy, optic neuropathy, and cataract formation. Based on limited data, the model for development of retinopathy suggests 5% and 50% risk of toxicity at 42 and 62 Gy, respectively. The model for development of optic neuropathy suggests 5% and 50% risk of toxicity at 57 and 64 Gy, respectively. More extensive data were available to evaluate the risk of cataract, separated into self-reported versus ophthalmologist-diagnosed cataract. The models suggest 5% and 50% risk of self-reported cataract at 12 and >40 Gy, respectively, and 50% risk of ophthalmologist-diagnosed cataract at 9 Gy (>5% long-term risk at 0 Gy in patients treated with chemotherapy only).

CONCLUSIONS

Radiation dose effects in the eye are inadequately studied in the pediatric population. Based on limited published data, this PENTEC comprehensive review establishes relationships between RT dose and subsequent risks of retinopathy, optic neuropathy, and cataract formation.

Impact of Relative Biologic Effectiveness for Proton Therapy for Head and Neck and Skull-Base Tumors: A Technical and Clinical Review

Proton therapy has emerged as a crucial tool in the treatment of head and neck and skull-base cancers, offering advantages over photon therapy in terms of decreasing integral dose and reducing acute and late toxicities, such as dysgeusia, feeding tube dependence, xerostomia, secondary malignancies, and neurocognitive dysfunction. Despite its benefits in dose distribution and biological effectiveness, the application of proton therapy is challenged by uncertainties in its relative biological effectiveness (RBE). Overcoming the challenges related to RBE is key to fully realizing proton therapy's potential, which extends beyond its physical dosimetric properties when compared with photon-based therapies. In this paper, we discuss the clinical significance of RBE within treatment volumes and adjacent serial organs at risk in the management of head and neck and skull-base tumors. We review proton RBE uncertainties and its modeling and explore clinical outcomes. Additionally, we highlight technological advancements and innovations in plan optimization and treatment delivery, including linear energy transfer/RBE optimizations and the development of spot-scanning proton arc therapy. These advancements show promise in harnessing the full capabilities of proton therapy from an academic standpoint, further technological innovations and clinical outcome studies, however, are needed for their integration into routine clinical practice.

NRG Oncology Assessment of Artificial Intelligence Deep Learning-Based Auto-segmentation for Radiation Therapy: Current Developments, Clinical Considerations, and Future Directions

Deep learning neural networks (DLNN) in Artificial intelligence (AI) have been extensively explored for automatic segmentation in radiotherapy (RT). In contrast to traditional model-based methods, data-driven AI-based models for auto-segmentation have shown high accuracy in early studies in research settings and controlled environment (single institution). Vendor-provided commercial AI models are made available as part of the integrated treatment planning system (TPS) or as a stand-alone tool that provides streamlined workflow interacting with the main TPS. These commercial tools have drawn clinics' attention thanks to their significant benefit in reducing the workload from manual contouring and shortening the duration of treatment planning. However, challenges occur when applying these commercial AI-based segmentation models to diverse clinical scenarios, particularly in uncontrolled environments. Contouring nomenclature and guideline standardization has been the main task undertaken by the NRG Oncology. AI auto-segmentation holds the potential clinical trial participants to reduce interobserver variations, nomenclature non-compliance, and contouring guideline deviations. Meanwhile, trial reviewers could use AI tools to verify contour accuracy and compliance of those submitted datasets. In recognizing the growing clinical utilization and potential of these commercial AI auto-segmentation tools, NRG Oncology has formed a working group to evaluate the clinical utilization and potential of commercial AI auto-segmentation tools. The group will assess in-house and commercially available AI models, evaluation metrics, clinical challenges, and limitations, as well as future developments in addressing these challenges. General recommendations are made in terms of the implementation of these commercial AI models, as well as precautions in recognizing the challenges and limitations.

ACR-ARS Practice Parameter for Radiation Oncology

BACKGROUND

This practice parameter was revised collaboratively by the American College of Radiology (ACR), and the American Radium Society. This practice parameter provides updated reference literature regarding radiation oncology practice and its key personnel.

METHODS

This practice parameter was developed according to the process described under the heading The Process for Developing ACR Practice Parameters and Technical Standards on the ACR website ( https://www.acr.org/Clinical-Resources/Practice-Parameters-and-Technical-Standards ) by the Committee on Practice Parameters-Radiation Oncology of the ACR Commission on Radiation Oncology in collaboration with the American Radium Society.

RESULTS

This practice parameter provides a comprehensive update to the reference literature regarding radiation oncology practice in general. The overall roles of the radiation oncologist, the Qualified Medical Physicist, and other specialized personnel involved in the delivery of external-beam radiation therapy are discussed. The use of radiation therapy requires detailed attention to equipment, patient and personnel safety, equipment maintenance and quality assurance, and continuing staff education. Because the practice of radiation oncology occurs in a variety of clinical environments, the judgment of a qualified radiation oncologist should be used to apply these practice parameters to individual practices. Radiation oncologists should follow the guiding principle of limiting radiation exposure to patients and personnel while accomplishing therapeutic goals.

CONCLUSION

This practice parameter can be used as an effective tool to guide radiation oncology practice by successfully incorporating the close interaction and coordination among radiation oncologists, medical physicists, dosimetrists, nurses, and radiation therapists.

Uncovering the armpit of SBRT: An institutional experience with stereotactic radiation of axillary metastases

Purpose/objectives

The growing use of stereotactic body radiotherapy (SBRT) in metastatic cancer has led to its use in varying anatomic locations. The objective of this study was to review our institutional SBRT experience for axillary metastases (AM), focusing on outcomes and process.

Materials/methods

Patients treated with SBRT to AM from 2014 to 2022 were reviewed. Cumulative incidence functions were used to estimate the incidence of local failure (LF), with death as competing risk. Kaplan-Meier method was used to estimate progression-free (PFS) and overall survival (OS). Univariate regression analysis examined predictors of LF.

Results

We analyzed 37 patients with 39 AM who received SBRT. Patients were predominantly female (60 %) and elderly (median age: 72). Median follow-up was 14.6 months. Common primary cancers included breast (43 %), skin (19 %), and lung (14 %). Treatment indication included oligoprogression (46 %), oligometastases (35 %) and symptomatic progression (19 %). A minority had prior overlapping radiation (18 %) or surgery (11 %). Most had prior systemic therapy (70 %).Significant heterogeneity in planning technique was identified; a minority of patient received 4-D CT scans (46 %), MR-simulation (21 %), or contrast (10 %). Median dose was 40 Gy (interquartile range (IQR): 35-40) in 5 fractions, (BED10 = 72 Gy). Seventeen cases (44 %) utilized a low-dose elective volume to cover remaining axilla.At first assessment, 87 % had partial or complete response, with a single progression. Of symptomatic patients (n = 14), 57 % had complete resolution and 21 % had improvement. One and 2-year LF rate were 16 % and 20 %, respectively. Univariable analysis showed increasing BED reduced risk of LF. Median OS was 21.0 months (95 % [Confidence Interval (CI)] 17.3-not reached) and median PFS was 7.0 months (95 % [CI] 4.3-11.3). Two grade 3 events were identified, and no grade 4/5.

Conclusion

Using SBRT for AM demonstrated low rates of toxicity and LF, and respectable symptom improvement. Variation in treatment delivery has prompted development of an institutional protocol to standardize technique and increase efficiency. Limited followup may limit detection of local failure and late toxicity.

Open RT Structures: A Solution for TG-263 Accessibility

PURPOSE

Consistency of nomenclature within radiation oncology is increasingly important as big data efforts and data sharing become more feasible. Automation of radiation oncology workflows depends on standardized contour nomenclature that enables toxicity and outcomes research, while also reducing medical errors and facilitating quality improvement activities. Recommendations for standardized nomenclature have been published in the American Association of Physicists in Medicine (AAPM) report from Task Group 263 (TG-263). Transitioning to TG-263 requires creation and management of structure template libraries and retraining of staff, which can be a considerable burden on clinical resources. Our aim is to develop a program that allows users to create TG-263-compliant structure templates in English, Spanish, or French to facilitate data sharing.

METHODS AND MATERIALS

Fifty-three premade structure templates were arranged by treated organ based on an American Society for Radiation Oncology (ASTRO) consensus paper. Templates were further customized with common target structures, relevant organs at risk (OARs) (eg, spleen for anatomically relevant sites such as the gastroesophageal junction or stomach), subsite- specific templates (eg, partial breast, whole breast, intact prostate, postoperative prostate, etc) and brachytherapy templates. An informal consensus on OAR and target coloration was also achieved, although color selections are fully customizable within the program.

RESULTS

The resulting program is usable on any Windows system and generates template files in practice-specific Digital Imaging and Communications In Medicine (DICOM) or XML formats, extracting standardized structure nomenclature from an online database maintained by members of the TG-263U1, which ensures continuous access to up-to-date templates.

CONCLUSIONS

We have developed a tool to easily create and name DICOM radiation therapy (DICOM-RT) structures sets that are TG-263-compliant for all planning systems using the DICOM standard. The program and source code are publicly available via GitHub to encourage feedback from community users for improvement and guide further development.

Custom-Trained Deep Learning-Based Auto-Segmentation for Male Pelvic Iterative CBCT on C-Arm Linear Accelerators

PURPOSE

The purpose of this investigation was to evaluate the clinical applicability of a commercial artificial intelligence-driven deep learning auto-segmentation (DLAS) tool on enhanced iterative cone beam computed tomography (iCBCT) acquisitions for intact prostate and prostate bed treatments.

METHODS AND MATERIALS

DLAS models were trained using 116 iCBCT data sets with manually delineated organs at risk (bladder, femoral heads, and rectum) and target volumes (intact prostate and prostate bed) adhering to institution-specific contouring guidelines. An additional 25 intact prostate and prostate bed iCBCT data sets were used for model testing. Segmentation accuracy relative to a reference structure set was quantified using various geometric comparison metrics and qualitatively evaluated by trained physicists and physicians. These results were compared with those obtained for an additional DLAS-based model trained on planning computed tomography (pCT) data sets and for a deformable image registration (DIR)-based automatic contour propagation method.

RESULTS

In most instances, statistically significant differences in the Dice similarity coefficient (DSC), 95% directed Hausdorff distance, and mean surface distance metrics were observed between the models, as the iCBCT-trained DLAS model outperformed the pCT-trained DLAS model and DIR-based method for all organs at risk and the intact prostate target volume. Mean DSC values for the proposed method were ≥0.90 for these volumes of interest. The iCBCT-trained DLAS model demonstrated a relatively suboptimal performance for the prostate bed segmentation, as the mean DSC value was <0.75 for this target contour. Overall, 90% of bladder, 93% of femoral head, 67% of rectum, and 92% of intact prostate contours generated by the proposed method were deemed clinically acceptable based on qualitative scoring, and approximately 63% of prostate bed contours required moderate or major manual editing to adhere to institutional contouring guidelines.

CONCLUSIONS

The proposed method presents the potential for improved segmentation accuracy and efficiency compared with the DIR-based automatic contour propagation method as commonly applied in CBCT-based dose evaluation and calculation studies.

Summary of Cardiac Computed Tomographic Imaging in Cardio-Oncology: An Expert Consensus Document of the Society of Cardiovascular Computed Tomography

PURPOSE

The purpose of this document is to develop a summary of recommendations from the "Cardiac Computed Tomographic Imaging in Cardio-Oncology: An Expert Consensus Document of the Society of Cardiovascular Computed Tomography (SCCT)" document and provide commentary on key recommendations that are relevant to radiation oncology.

METHODS

In July 2019, the SCCT convened a multidisciplinary panel of experts to develop a consensus document based on a literature search and a formal consensus process, which was separately published in 2022. A new panel consisting of the radiation oncologist from the original guideline and additional radiation oncologists was formed to address SCCT recommendations and their implications for radiation oncology.

SUMMARY

The SCCT consensus document included 6 core sections. Two of these sections were identified as particularly relevant to radiation oncologists. These include evaluation of shared risk factors and role of cardiac computed tomography in risk stratification of patients with cancer (section 1) and the role of cardiac computed tomography in the evaluation of the effects of radiation therapy (section 4). These recommendations are summarized, with additional commentary on the role of radiation oncologists as individual practitioners and radiation oncology practices as a whole in evaluation of coronary artery calcifications on computed tomography images; assessment of the effects of radiation therapy on cardiovascular risk after treatment; and management of patients at elevated risk of cardiovascular sequelae of treatment. Radiation oncologists should be aware of the recommendations in the SCCT consensus document and consider those elements that relate to their practice. This summary document calls attention to the key roles and limitations of radiation oncologists and radiation oncology practices in managing cardiotoxicity risk and highlights the need for ongoing study on the effects of radiation therapy on the heart, cardiac substructures, and long-term risk of cardiotoxicity related to treatment.

Achieving Exceptional Cochlea Delineation in Radiotherapy Scans: The Impact of Optimal Window Width and Level Settings

Introduction Radiation therapy (RT) aims to maximize the dose to the target volume while minimizing the dose to organs at risk (OAR), which is crucial for optimal treatment outcomes and minimal side effects. The complex anatomy of the head and neck regions, including the cochlea, presents challenges in radiotherapy. Accurate delineation of the cochlea is essential to prevent toxicities such as sensorineural hearing loss. Educational interventions, including seminars, atlases, and multidisciplinary discussions, can improve accuracy and interobserver agreement in contouring. This study seeks to provide radiation oncology practitioners with the necessary window width and window level settings in computed tomography (CT) scans to accurately and precisely delineate the cochlea, using a pre-and post-learning phase approach to assess the change in accuracy. Methods and materials The study used the ProKnow Contouring Accuracy Program (ProKnow, LLC, Florida, United States), which employs the StructSure method and the Dice coefficient to assess the precision of a user's contour compared to an expert contour. The StructSure method offers superior sensitivity and accuracy, while the Dice coefficient is a more rudimentary and less sensitive approach. Two datasets of CT scans, one for each left and right cochlea, were used. The author delineated the cochlea before and after applying the proposed technique for window width and window level, comparing the results with those of the expert and general population. The study included a step-by-step method for cochlea delineation using window width and window level settings. Data analysis was performed using IBM SPSS Statistics for Windows, Version 26.0 (Released 2019; IBM Corp., Armonk, New York, United States). Results The implementation of the proposed step-by-step method for adjusting window width and window level led to significant improvements in contouring accuracy and delineation quality in radiation therapy planning. Comparing pre- and post-intervention scenarios, the author exhibited increased StructSure scores (right cochlea: 88.81 to 99.15; left cochlea: 88.45 to 99.85) and Dice coefficient scores (right cochlea: 0.62 to 0.80; left cochlea: 0.73 to 0.86). The author consistently demonstrated higher contouring accuracy and greater similarity to expert contours compared to the group's mean scores both before and after the intervention. These results suggest that the proposed method enhances the precision of cochlea delineation in radiotherapy planning. Conclusion In conclusion, this study demonstrated that a step-by-step instructional approach for adjusting window width and window level significantly improved cochlea delineation accuracy in radiotherapy contouring. The findings hold potential clinical implications for reducing radiation-related side effects and improving patient outcomes. This study supports the integration of the instructional technique into radiation oncology training and encourages further exploration of advanced imaging processing and artificial intelligence applications in radiotherapy contouring.

Clinical Validation of Siemens' Syngo.via Automatic Contouring System

Purpose

The manual delineation of organs at risk is a process that requires a great deal of time both for the technician and for the physician. Availability of validated software tools assisted by artificial intelligence would be of great benefit, as it would significantly improve the radiation therapy workflow, reducing the time required for segmentation. The purpose of this article is to validate the deep learning-based autocontouring solution integrated in syngo.via RT Image Suite VB40 (Siemens Healthineers, Forchheim, Germany).

Methods and Materials

For this purpose, we have used our own specific qualitative classification system, RANK, to evaluate more than 600 contours corresponding to 18 different automatically delineated organs at risk. Computed tomography data sets of 95 different patients were included: 30 patients with lung, 30 patients with breast, and 35 male patients with pelvic cancer. The automatically generated structures were reviewed in the Eclipse Contouring module independently by 3 observers: an expert physician, an expert technician, and a junior physician.

Results

There is a statistically significant difference between the Dice coefficient associated with RANK 4 compared with the coefficient associated with RANKs 2 and 3 (P < .001). In total, 64% of the evaluated structures received the maximum score, 4. Only 1% of the structures were classified with the lowest score, 1. The time savings for breast, thorax, and pelvis were 87.6%, 93.5%, and 82.2%, respectively.

Conclusions

Siemens' syngo.via RT Image Suite offers good autocontouring results and significant time savings.

Head and Neck Radiation Therapy Patterns of Practice Variability Identified as a Challenge to Real-World Big Data: Results From the Learning from Analysis of Multicentre Big Data Aggregation (LAMBDA) Consortium

Purpose

Outside of randomized clinical trials, it is difficult to develop clinically relevant evidence-based recommendations for radiation therapy (RT) practice guidelines owing to lack of comprehensive real-world data. To address this knowledge gap, we formed the Learning from Analysis of Multicenter Big Data Aggregation consortium to cooperatively implement RT data standardization, develop software solutions for data analysis, and recommend clinical practice change based on real-world data analyzed. The first phase of this "Big Data" study aimed at characterizing variability in clinical practice patterns of dosimetric data for organs at risk (OARs) that would undermine subsequent use of large-scale, electronically aggregated data to characterize associations with outcomes. Evidence from this study was used as the basis for practical recommendations to improve data quality.

Methods and Materials

Dosimetric details of patients with head and neck cancer treated with radiation therapy between 2014 and 2019 were analyzed. Institutional patterns of practice were characterized, including structure nomenclature, volumes, and frequency of contouring. Dose volume histogram (DVH) distributions were characterized and compared with institutional constraints and literature values.

Results

Plans for 4664 patients treated to a mean plan dose of 64.4 ± 13.2 Gy in 32 ± 4 fractions were aggregated. Before implementation of TG-263 guidelines in each institution, there was variability in OAR nomenclature across institutions and structures. With evidence from this study, we identified a targeted and practical set of recommendations aimed at improving the quality of real-world data.

Conclusions

Quantifying similarities and differences among institutions for OAR structures and DVH metrics is the launching point for next steps to investigate potential relationships between DVH parameters and patient outcomes.

Quality and Safety Considerations in Intensity Modulated Radiation Therapy: An ASTRO Safety White Paper Update

PURPOSE

This updated report on intensity modulated radiation therapy (IMRT) is part of a series of consensus-based white papers previously published by the American Society for Radiation Oncology (ASTRO) addressing patient safety. Since the first white papers were published, IMRT went from widespread use to now being the main delivery technique for many treatment sites. IMRT enables higher radiation doses to be delivered to more precise targets while minimizing the dose to uninvolved normal tissue. Due to the associated complexity, IMRT requires additional planning and safety checks before treatment begins and, therefore, quality and safety considerations for this technique remain important areas of focus.

METHODS AND MATERIALS

ASTRO convened an interdisciplinary task force to assess the original IMRT white paper and update content where appropriate. Recommendations were created using a consensus-building methodology, and task force members indicated their level of agreement based on a 5-point Likert scale, from "strongly agree" to "strongly disagree." A prespecified threshold of ≥75% of raters who select "strongly agree" or "agree" indicated consensus.

CONCLUSIONS

This IMRT white paper primarily focuses on quality and safety processes in planning and delivery. Building on the prior version, this consensus paper incorporates revised and new guidance documents and technology updates. IMRT requires an interdisciplinary team-based approach, staffed by appropriately trained individuals as well as significant personnel resources, specialized technology, and implementation time. A comprehensive quality assurance program must be developed, using established guidance, to ensure IMRT is performed in a safe and effective manner. Patient safety in the delivery of IMRT is everyone's responsibility, and professional organizations, regulators, vendors, and end-users must work together to ensure the highest levels of safety.

Improving Quality Metrics in Radiation Oncology: Implementation of Pretreatment Peer Review for Stereotactic Body Radiation Therapy in Patients with Thoracic Cancer

Purpose

Traditional peer reviews occur weekly, and can take place up to 1 week after the start of treatment. The American Society for Radiation Oncology peer-review white paper identified stereotactic body radiation therapy (SBRT) as a high priority for contour/plan review before the start of treatment, considering both the rapid-dose falloff and short treatment course. Yet, peer-review goals for SBRT must also balance physician time demands and the desire to avoid routine treatment delays that would occur in the setting of a 100% pretreatment (pre-Tx) review compliance requirement or prolonging the standard treatment planning timeline. Herein, we report on our pilot experience of a pre-Tx peer review of thoracic SBRT cases.

Methods and Materials

From March 2020 to August 2021, patients undergoing thoracic SBRT were identified for pre-Tx review, and placed on a quality checklist. We implemented twice-weekly meetings for detailed pre-Tx review of organ-at-risk/target contours and dose constraints in the treatment planning system for SBRT cases. Our quality metric goal was to peer review ≥90% of SBRT cases before exceeding 25% of the dose delivered. We used a statistical process control chart with sigma limits (ie, standard deviations [SDs]) to access compliance rates with pre-Tx review implementation.

Results

We identified 252 patients treated with SBRT to 294 lung nodules. When comparing pre-Tx review completion from initial rollout to full implementation, our rates improved from 19% to 79% (ie, from 1 sigma limit [SDs]) below to >2 sigma limits (SDs) above. Additionally, early completion of any form of contour/plan review (defined as any pre-Tx or standard review completed before exceeding 25% of the dose delivered) increased from 67% to 85% (March 2020-November 2020) to 76% to 94% (December 2020-August 2021).

Conclusions

We successfully implemented a sustainable workflow for detailed pre-Tx contour/plan review for thoracic SBRT cases in the context of twice-weekly disease site-specific peer-review meetings. We reached our quality improvement objective to peer review ≥90% of SBRT cases before exceeding 25% of the dose delivered. This process was feasible to conduct in an integrated network of sites across our system.

Clinical evaluation of deep learning and atlas-based auto-segmentation for critical organs at risk in radiation therapy

INTRODUCTION

Contouring organs at risk (OARs) is a time-intensive task that is a critical part of radiation therapy. Atlas-based automatic segmentation has shown some success at reducing this time burden on practitioners; however, this method often requires significant manual editing to reach a clinically accurate standard. Deep learning (DL) auto-segmentation has recently emerged as a promising solution. This study compares the accuracy of DL and atlas-based auto-segmentation in relation to clinical 'gold standard' reference contours.

METHODS

Ninety CT datasets (30 head and neck, 30 thoracic, 30 pelvic) were automatically contoured using both atlas and DL segmentation techniques. Sixteen critical OARs were then quantitatively measured for accuracy using the Dice similarity coefficient (DSC) and Hausdorff distance (HD). Qualitative analysis was performed to visually classify the accuracy of each structure into one of four explicitly defined categories. Additionally, the time to edit atlas and DL contours to a clinically acceptable level was recorded for a subset of 9 OARs.

RESULTS

Of the 16 OARs analysed, DL delivered statistically significant improvements over atlas segmentation in 13 OARs measured with DSC, 12 OARs measured with HD, and 12 OARs measured qualitatively. The mean editing time for the subset of DL contours was 50%, 23% and 61% faster (all P < 0.05) than that of atlas segmentation for the head and neck, thorax, and pelvis respectively.

CONCLUSIONS

Deep learning segmentation comprehensively outperformed atlas-based contouring for the majority of evaluated OARs. Improvements were observed in geometric accuracy and visual acceptability, while editing time was reduced leading to increased workflow efficiency.

Image-based data mining applies to data collected from children

PURPOSE

Image-based data mining (IBDM) is a novel voxel-based method for analyzing radiation dose responses that has been successfully applied in adult data. Because anatomic variability and side effects of interest differ for children compared to adults, we investigated the feasibility of IBDM for pediatric analyses.

METHODS

We tested IBDM with CT images and dose distributions collected from 167 children (aged 10 months to 20 years) who received proton radiotherapy for primary brain tumors. We used data from four reference patients to assess IBDM sensitivity to reference selection. We quantified spatial-normalization accuracy via contour distances and deviations of the centers-of-mass of brain substructures. We performed dose comparisons with simplified and modified clinical dose distributions with a simulated effect, assessing their accuracy via sensitivity, positive predictive value (PPV) and Dice similarity coefficient (DSC).

RESULTS

Spatial normalizations and dose comparisons were insensitive to reference selection. Normalization discrepancies were small (average contour distance < 2.5 mm, average center-of-mass deviation < 6 mm). Dose comparisons identified differences (p < 0.01) in 81% of simplified and all modified clinical dose distributions. The DSCs for simplified doses were high (peak frequency magnitudes of 0.9-1.0). However, the PPVs and DSCs were low (maximum 0.3 and 0.4, respectively) in the modified clinical tests.

CONCLUSIONS

IBDM is feasible for childhood late-effects research. Our findings may inform cohort selection in future studies of pediatric radiotherapy dose responses and facilitate treatment planning to reduce treatment-related toxicities and improve quality of life among childhood cancer survivors.

NCCN Guidelines® Insights: Hodgkin Lymphoma, Version 2.2022

Hodgkin lymphoma (HL) is an uncommon malignancy of B-cell origin. Classical HL (cHL) and nodular lymphocyte-predominant HL are the 2 main types of HL. The cure rates for HL have increased so markedly with the advent of modern treatment options that overriding treatment considerations often relate to long-term toxicity. These NCCN Guidelines Insights discuss the recent updates to the NCCN Guidelines for HL focusing on (1) radiation therapy dose constraints in the management of patients with HL, and (2) the management of advanced-stage and relapsed or refractory cHL.

General and custom deep learning autosegmentation models for organs in head and neck, abdomen, and male pelvis

PURPOSE

To reduce workload and inconsistencies in organ segmentation for radiation treatment planning, we developed and evaluated general and custom autosegmentation models on computed tomography (CT) for three major tumor sites using a well-established deep convolutional neural network (DCNN).

METHODS

Five CT-based autosegmentation models for 42 organs at risk (OARs) in head and neck (HN), abdomen (ABD), and male pelvis (MP) were developed using a full three-dimensional (3D) DCNN architecture. Two types of deep learning (DL) models were separately trained using either general diversified multi-institutional datasets or custom well-controlled single-institution datasets. To improve segmentation accuracy, an adaptive spatial resolution approach for small and/or narrow OARs and a pseudo scan extension approach, when CT scan length is too short to cover entire organs, were implemented. The performance of the obtained models was evaluated based on accuracy and clinical applicability of the autosegmented contours using qualitative visual inspection and quantitative calculation of dice similarity coefficient (DSC), mean distance to agreement (MDA), and time efficiency.

RESULTS

The five DL autosegmentation models developed for the three anatomical sites were found to have high accuracy (DSC ranging from 0.8 to 0.98) for 74% OARs and marginally acceptable for 26% OARs. The custom models performed slightly better than the general models, even with smaller custom datasets used for the custom model training. The organ-based approaches improved autosegmentation accuracy for small or complex organs (e.g., eye lens, optic nerves, inner ears, and bowels). Compared with traditional manual contouring times, the autosegmentation times, including subsequent manual editing, if necessary, were substantially reduced by 88% for MP, 80% for HN, and 65% for ABD models.

CONCLUSIONS

The obtained autosegmentation models, incorporating organ-based approaches, were found to be effective and accurate for most OARs in the male pelvis, head and neck, and abdomen. We have demonstrated that our multianatomical DL autosegmentation models are clinically useful for radiation treatment planning.

Evaluation of the impact of teaching on delineation variation during a virtual stereotactic ablative radiotherapy contouring workshop

Introduction:

Variation in delineation of target volumes/organs at risk (OARs) is well recognised in radiotherapy and may be reduced by several methods including teaching. We evaluated the impact of teaching on contouring variation for thoracic/pelvic stereotactic ablative radiotherapy (SABR) during a virtual contouring workshop.

Materials and methods:

Target volume/OAR contours produced by workshop participants for three cases were evaluated against reference contours using DICE similarity coefficient (DSC) and line domain error (LDE) metrics. Pre- and post-workshop DSC results were compared using Wilcoxon signed ranks test to determine the impact of teaching during the workshop.

Results:

Of 50 workshop participants, paired pre- and post-workshop contours were available for 21 (42%), 20 (40%) and 22 (44%) participants for primary lung cancer, pelvic bone metastasis and pelvic node metastasis cases, respectively. Statistically significant improvements post-workshop in median DSC and LDE results were observed for 6 (50%) and 7 (58%) of 12 structures, respectively, although the magnitude of DSC/LDE improvement was modest in most cases. An increase in median DSC post-workshop ≥0·05 was only observed for GTVbone, IGTVlung and SacralPlex, and reduction in median LDE > 1 mm was only observed for GTVbone, CTVbone and SacralPlex. Post-workshop, median DSC values were >0·7 for 75% of structures. For 92% of the structures, post-workshop contours were considered to be acceptable or within acceptable variation following review by the workshop faculty.

Conclusions:

This study has demonstrated that virtual SABR contouring training is feasible and was associated with some improvements in contouring variation for multiple target volumes/OARs.

Evaluation of deep learning-based autosegmentation in breast cancer radiotherapy

Purpose

To study the performance of a proposed deep learning-based autocontouring system in delineating organs at risk (OARs) in breast radiotherapy with a group of experts.

Methods

Eleven experts from two institutions delineated nine OARs in 10 cases of adjuvant radiotherapy after breast-conserving surgery. Autocontours were then provided to the experts for correction. Overall, 110 manual contours, 110 corrected autocontours, and 10 autocontours of each type of OAR were analyzed. The Dice similarity coefficient (DSC) and Hausdorff distance (HD) were used to compare the degree of agreement between the best manual contour (chosen by an independent expert committee) and each autocontour, corrected autocontour, and manual contour. Higher DSCs and lower HDs indicated a better geometric overlap. The amount of time reduction using the autocontouring system was examined. User satisfaction was evaluated using a survey.

Results

Manual contours, corrected autocontours, and autocontours had a similar accuracy in the average DSC value (0.88 vs. 0.90 vs. 0.90). The accuracy of autocontours ranked the second place, based on DSCs, and the first place, based on HDs among the manual contours. Interphysician variations among the experts were reduced in corrected autocontours, compared to variations in manual contours (DSC: 0.89–0.90 vs. 0.87–0.90; HD: 4.3–5.8 mm vs. 5.3–7.6 mm). Among the manual delineations, the breast contours had the largest variations, which improved most significantly with the autocontouring system. The total mean times for nine OARs were 37 min for manual contours and 6 min for corrected autocontours. The results of the survey revealed good user satisfaction.

Conclusions

The autocontouring system had a similar performance in OARs as that of the experts’ manual contouring. This system can be valuable in improving the quality of breast radiotherapy and reducing interphysician variability in clinical practice.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13014-021-01923-1.

Implementation and evaluation of an online anatomy, radiology and contouring bootcamp for radiation therapists

BACKGROUND

As new treatments and technologies have been introduced in radiation oncology, the clinical roles of radiation therapists (RTs) have expanded. However, there are few formal learning opportunities for RTs. An online, anatomy, radiology and contouring bootcamp (ARC Bootcamp) originally designed for medical residents was identified as a prospective educational tool for RTs. The purpose of this study was to evaluate an RT edition of the ARC Bootcamp on knowledge, contouring, and confidence, as well as to identify areas for future modification.

METHODS

Fifty licensed RTs were enrolled in an eight-week, multidisciplinary, online RT ARC Bootcamp. Contouring practice was available throughout the course using an online contouring platform. Outcomes were evaluated using a pre-course and post-course multiple-choice quiz (MCQ), contouring evaluation and qualitative self-efficacy and satisfaction survey.

RESULTS

Of the fifty enrolled RTs, 30 completed the course, and 26 completed at least one of the post-tests. Nineteen contouring dice similarity coefficient (DSC) scores were available for paired pre- and post-course analysis. RTs demonstrated a statistically significant increase in mean DSC scoring pooled across all contouring structures (mean ± SD improvement: 0.09 ± 0.18 on a scale from 0 to 1, p=0.020). For individual contouring structures, 3/15 reached significance in contouring improvement. MCQ scores were available for 26 participants and increased after RT ARC Bootcamp participation with a mean ± SD pre-test score of 18.6 ± 4.2 (46.5%); on a 40-point scale vs. post-test score of 24.5 ± 4.3 (61.4%) (p < 0.001). RT confidence in contouring, anatomy knowledge and radiographic identification improved after course completion (p < 0.001). Feedback from RTs recommended more contouring instruction, less in-depth anatomy review and more time to complete the course.

CONCLUSIONS

The RT ARC Bootcamp was an effective tool for improving anatomy and radiographic knowledge among RTs. The course demonstrated improvements in contouring and overall confidence. However, only approximately half of the enrolled RTs completed the course, limiting statistical power. Future modifications will aim to increase relevance to RTs and improve completion rates.

Delineation of organs at risk

The delineation of organs at risk is the basis of radiotherapy oncologists' work. Indeed, the knowledge of this delineation enables to better identify the target volumes and to optimize dose distribution, involving the prognosis of the patients but also their future. The learning of this delineation must continue throughout the clinician's career. Some contour changes have appeared with better imaging, some volumes are now required due to development of knowledge of side effects. In addition, the increasing survival time of patients requires to be more systematic and precise in the delineations, both to avoid complications until now exceptional but also because re-irradiations are becoming more and more frequent. We present the update of the recommendations of the French Society for Radiation Oncology (SFRO) on new findings or adaptations to volumes at risk.

Medical Physics Practice Guideline (MPPG) 11.a: Plan and chart review in external beam radiotherapy and brachytherapy

A therapeutic medical physicist is responsible for reviewing radiation therapy treatment plans and patient charts, including initial treatment plans and new chart review, on treatment chart (weekly) review, and end of treatment chart review for both external beam radiation and brachytherapy. Task group report TG 275 examined this topic using a risk‐based approach to provide a thorough analysis and guidance for best practice. Considering differences in resources and workflows of various clinical practice settings, the Professional Council of the American Association of Physicists in Medicine assembled this task group to develop a practice guideline on the same topic to provide a minimum standard that balances an appropriate level of safety and resource utilization. This medical physics practice guidelines (MPPG) thus provides a concise set of recommendations for medical physicists and other clinical staff regarding the review of treatment plans and patient charts while providing specific recommendations about who to be involved, and when/what to check in the chart review process. The recommendations, particularly those related to the initial plan review process, are critical for preventing errors and ensuring smooth clinical workflow. We believe that an effective review process for high‐risk items should include multiple layers with collective efforts across the department. Therefore, in this report, we make specific recommendations for various roles beyond medical physicists. The recommendations of this MPPG have been reviewed and endorsed by the American Society of Radiologic Technologists and the American Association of Medical Dosimetrists.

A first radiotherapy application of functional bulboclitoris anatomy, a novel female sexual organ-at-risk, and organ-sparing feasibility study

OBJECTIVE

The bulboclitoris (clitoris and vestibular bulbs) is the primary organ responsible for female sexual arousal and orgasm. Effects of radiotherapy on the bulboclitoris are unknown, as its structure/function has yet to be described in radiotherapy, and it overlaps only partially with the external genitalia structure. Our aim was to: describe bulboclitoris structure, function and delineation; compare volume of and dose delivered to the bulboclitoris vs external genitalia; and, compare bulboclitoris-sparing IMRT (BCS-IMRT) to standard IMRT (S-IMRT) to determine reoptimization feasibility.

METHODS

Our expert team (anatomist, pelvic radiologist, radiation oncologist) reviewed bulboclitoris anatomy and developed contouring guidance for radiotherapy. 20 female patients with anal cancer treated with chemoradiation were analyzed. Sexual organs at risk (OARs) included the external genitalia and the bulboclitoris. Volumes, dice similarity coefficients (DSCs) and dose received using S-IMRT were compared. Plans were reoptimized using BCS-IMRT. Dose-volume histograms (DVHs) for PTVs and all OARs were compared for BCS-IMRT vs S-IMRT.

RESULTS

Bulboclitoris structure, function and delineation are described herein. The bulboclitoris occupies 20cc (IQR:12-24), largely distinct from the external genitalia (DSC <0.05). BCS-IMRT was superior to S-IMRT in reducing the dose to the bulboclitoris, with the greatest reductions in V30 and V40, with no significant changes in dose to other OARs or PTV 1/V95.

CONCLUSION

The bulboclitoris can be contoured on planning imaging, largely distinct from the external genitalia. Compared with S-IMRT, BCS-IMRT dramatically reduced dose to the bulboclitoris in anal cancer planning. BCS-IMRT might safely reduce sexual toxicity compared with standard approaches.

ADVANCES IN KNOWLEDGE

The structure and function of the bulboclitoris, the critical primary organ responsible for female sexual arousal and orgasm, has yet to be described in the radiotherapy literature. Structure, function and delineation of the bulboclitoris are detailed, delineation and bulboclitoris-sparing IMRT were feasible, and sparing reduces the dose to the bulboclitoris nearly in half in female patients receiving IMRT for anal cancer, warranting further clinical study.

Spatial descriptions of radiotherapy dose: normal tissue complication models and statistical associations

For decades, dose-volume information for segmented anatomy has provided the essential data for correlating radiotherapy dosimetry with treatment-induced complications. Dose-volume information has formed the basis for modelling those associations via normal tissue complication probability (NTCP) models and for driving treatment planning. Limitations to this approach have been identified. Many studies have emerged demonstrating that the incorporation of information describing the spatial nature of the dose distribution, and potentially its correlation with anatomy, can provide more robust associations with toxicity and seed more general NTCP models. Such approaches are culminating in the application of computationally intensive processes such as machine learning and the application of neural networks. The opportunities these approaches have for individualising treatment, predicting toxicity and expanding the solution space for radiation therapy are substantial and have clearly widespread and disruptive potential. Impediments to reaching that potential include issues associated with data collection, model generalisation and validation. This review examines the role of spatial models of complication and summarises relevant published studies. Sources of data for these studies, appropriate statistical methodology frameworks for processing spatial dose information and extracting relevant features are described. Spatial complication modelling is consolidated as a pathway to guiding future developments towards effective, complication-free radiotherapy treatment.

Multi-View Data Integration Methods for Radiotherapy Structure Name Standardization

Simple Summary

Structure names associated with radiotherapy treatments need standardization to develop data pipelines enabling personalized treatment plans. Automatic classification of structure names based on the currently available TG-263 nomenclature can help with data aggregation from both retrospective and future data sources. The aim of our proposed machine learning-based data integration methods is to achieve highly accurate structure name classification to automate the data aggregation process. Our multi-view models can overcome the challenges of integrating different data types associated with radiotherapy structures, such as the physician-given text labels and geometric or image data. The models exhibited high accuracy when tested on multi-center and multi-institutional lung and prostate cancer patients data and outperformed the models built on any single data type. This highlights the importance of combining different types of data in building generalizable models for structure name standardization.

Abstract

Standardization of radiotherapy structure names is essential for developing data-driven personalized radiotherapy treatment plans. Different types of data are associated with radiotherapy structures, such as the physician-given text labels, geometric (image) data, and Dose-Volume Histograms (DVH). Prior work on structure name standardization used just one type of data. We present novel approaches to integrate complementary types (views) of structure data to build better-performing machine learning models. We present two methods, namely (a) intermediate integration and (b) late integration, to combine physician-given textual structure name features and geometric information of structures. The dataset consisted of 709 prostate cancer and 752 lung cancer patients across 40 radiotherapy centers administered by the U.S. Veterans Health Administration (VA) and the Department of Radiation Oncology, Virginia Commonwealth University (VCU). We used randomly selected data from 30 centers for training and ten centers for testing. We also used the VCU data for testing. We observed that the intermediate integration approach outperformed the models with a single view of the dataset, while late integration showed comparable performance with single-view results. Thus, we demonstrate that combining different views (types of data) helps build better models for structure name standardization to enable big data analytics in radiation oncology.

Estimation of planning organ at risk volumes for ocular structures in dogs undergoing three-dimensional image-guided periocular radiotherapy with rigid bite block immobilization

Planning organ at risk volume (PRV) estimates have been reported as methods for sparing organs at risk (OARs) during radiation therapy, especially for hypofractioned and/or dose‐escalated protocols. The objectives of this retrospective, analytical, observational study were to evaluate peri‐ocular OAR shifts and derive PRVs in a sample of dogs undergoing radiation therapy for periocular tumors. Inclusion criteria were as follows: dogs irradiated for periocular tumors, with 3D‐image‐guidance and at least four cone‐beam CTs (CBCTs) used for position verification, and positioning in a rigid bite block immobilization device. Peri‐ocular OARs were contoured on each CBCT and the systematic and random error of the shifts in relation to the planning CT position computed. The formula 1.3×Σ+0.5xσ was used to generate a PRV of each OAR in the dorsoventral, mediolateral, and craniocaudal axis. A total of 30 dogs were sampled, with 450 OARs contoured, and 2145 shifts assessed. The PRV expansion was qualitatively different for each organ (1‐4 mm for the dorsoventral and 1‐2 mm for the mediolateral and craniocaudal axes). Maximal PRV expansion was ≤4 mm and directional for the majority; most pronounced for corneas and retinas. Findings from the current study may help improve awareness of and minimization of radiation dose in peri‐ocular OARs for future canine patients. Because some OARs were difficult to visualize on CBCTs and/ or to delineate on the planning CT, authors recommend that PRV estimates be institution‐specific and applied with caution.

The spleen as an organ at risk in paediatric radiotherapy: A SIOP-Europe Radiation Oncology Working Group report

BACKGROUND

Radiation may cause long-term splenic dysfunction, risking potentially fatal late sepsis. We aimed to review this complication's magnitude in paediatric radiotherapy and gauge the level of awareness of the spleen as an organ at risk.

METHODS

Clinical trial protocols and radiotherapy guidelines, patient/parent information sheets, and professional guidance documents were reviewed to assess the perceived risk of radiotherapy-related splenic dysfunction. Paediatric oncologists and paediatric radiation oncologists across Europe were surveyed to estimate the level of understanding of this risk and to ascertain current practice. Spleen doses received in practice were examined. A systematic review of relevant publications was undertaken.

RESULTS

The risk is not mentioned in most clinical trials, patient information leaflets, or professional guidance documents. When mentioned, a threshold dose of 40 Gy is cited. The survey showed only limited awareness. More than half of patients assessed received spleen doses in excess of 10 Gy. The systematic review identified one paper reporting a relative mortality risk of 5.5 with spleen doses in the 10-20 Gy range.

CONCLUSIONS

The risk of mortality from overwhelming infection is poorly recognised. We therefore recommend routine delineation of the spleen. Protocols and guidelines should give a spleen dose objective as low as reasonably achievable, ideally mean <10 Gy without compromise to target volumes. Revised evidence-based guidelines and continuing professional development activities should inform oncologists. Patient/parent information should mention the risk and the dose received be communicated to colleagues. Antibiotic prophylaxis and/or (re)vaccination should be considered if the mean spleen dose is ≥10 Gy.

An Evaluation of Health Numeracy among Radiation Therapists and Dosimetrists

Purpose

Medical errors in radiation oncology sometimes involve tasks reliant on practitioners’ grasp of numeracy. Numeracy has been shown to be suboptimal across various health care professionals. Herein, we assess health numeracy among American Society of Radiologic Technologists (ASRT) members.

Methods and materials

The Numeracy Understanding for Medicine instrument (NUMi), an instrument to measure numeracy in the general population, was adapted to oncology for this study and distributed to ASRT members (n = 14,228) in 2017. Per NUMi scoring, health numeracy scores were categorized as low (0-7), low average (8-12), high average (13-17), or high (18-20). The impact of cGy versus Gy on numeracy performance was investigated. Spearman’s rho and a Wilcox-Mann-Whitney test were used for comparisons between the different groups.

Results

A total of 662 eligible participants completed the instrument and identified as radiation oncology professionals. In the cGy and Gy NUMi scores, approximately 2% of respondents scored low-average, approximately 40% scored high-average, and approximately 58% scored high, with a median score of 18.0. Although the optimum NUMi score for ASRT members is unknown, one might expect our cohort to have numeracy skills at least as high as college freshmen. Roughly one-sixth of our study group scored at or below the average score of college freshmen (NUMi = 15). In the subset analysis of NUMi questions pertaining to radiation dose unit (cGy vs Gy), respondents performed better with cGy (mean score: 2.94; range, 2-3) versus Gy (mean: 2.91; range, 0-3; P = .011).

Conclusions

In this study of limited sample size, overall numeracy is quite good compared with the general population. However, the range of scores is wide, and some respondents have lower scores that may be concerning, suggesting that numeracy may be an issue that requires improvement for a subset of the studied cohort. Performance was superior with the unit cGy; thus, the adoption of cGy as the standard unit is reasonable.

Physician review of image registration and normal structure delineation

Introduction

Methods

Results

Conclusion

Using deep learning to model the biological dose prediction on bulky lung cancer patients of partial stereotactic ablation radiotherapy

PURPOSE

To develop a biological dose prediction model considering tissue bio-reactions in addition to patient anatomy for achieving a more comprehensive evaluation of tumor control and promoting the automatic planning of bulky lung cancer.

METHODS

A database containing images and partial stereotactic ablation boost radiotherapy (P-SABR) plans of 94 bulky lung cancer patients was studied. Patient-specific parameters of gross tumor boost volume (GTVb), planning gross target volume (PGTV), and identified organs at risk (OARs) were extracted via Numpy and simple ITK. The original dose and structure maps for P-SABR patients were resampled to have a voxel resolution of 3.9 × 3.9 × 3 mm³ . Biological equivalent dose (BED) distributions were reprogrammed based on physical dose volumes. A developed deep learning architecture, Nestnet, was adopted as the training framework. We utilized two approaches for data organization to correlate the structures and BED: (a) BED programming before training model (B-Nestnet); (b) BED programming after the training process (D-B Nestnet). The early-stop mechanism was adopted on the validation set to avoid overfitting. The evaluation criteria of predictive accuracy contain the minimum BED of GTVb and PGTV, the maximum and the mean BED of all targets, BED-volume metrics. For comparison, we also used the original Unet for BED prediction. The absolute differences were statistically analyzed with the paired-samples t test.

RESULTS

The statistical outcomes demonstrate that D-B Nestnet model predicts biological dose distributions accurately. The average absolute biases of [max, mean] BED for GTVb, PGTV are [2.1%, 3.3%] and [2.1%, 4.7%], respectively. Averaging across most of OARs, the D-B Nestnet model is capable of predicting the errors of the max and mean BED within 6.3% and 6.1%, respectively. While the compared models performed worse with averaged max and mean BED prediction errors surpassing 10% on some specific OARs.

CONCLUSIONS

The study developed a D-B Nestnet model capable of predicting BED distribution accurately for bulky lung cancer patients in P-SABR. The predicted BED map enables a quick intuitive evaluation of tumor ablation, modification of the ablation range to improve BED of tumor targets, and quality assessment. It represents a major step forward toward automated P-SABR planning on bulky lung cancer in real clinical practice.

Artificial intelligence in radiation oncology

Artificial intelligence (AI) has the potential to fundamentally alter the way medicine is practised. AI platforms excel in recognizing complex patterns in medical data and provide a quantitative, rather than purely qualitative, assessment of clinical conditions. Accordingly, AI could have particularly transformative applications in radiation oncology given the multifaceted and highly technical nature of this field of medicine with a heavy reliance on digital data processing and computer software. Indeed, AI has the potential to improve the accuracy, precision, efficiency and overall quality of radiation therapy for patients with cancer. In this Perspective, we first provide a general description of AI methods, followed by a high-level overview of the radiation therapy workflow with discussion of the implications that AI is likely to have on each step of this process. Finally, we describe the challenges associated with the clinical development and implementation of AI platforms in radiation oncology and provide our perspective on how these platforms might change the roles of radiotherapy medical professionals.

Geometric and Dosimetric Evaluation of a Commercially Available Auto-segmentation Tool for Gross Tumour Volume Delineation in Locally Advanced Non-small Cell Lung Cancer: a Feasibility Study

AIMS

To quantify the reliability of a commercially available auto-segmentation tool in locally advanced non-small cell lung cancer using serial four-dimensional computed tomography (4DCT) scans during conventionally fractionated radiotherapy.

MATERIALS AND METHODS

Eight patients with serial 4DCT scans (n = 44) acquired over the course of radiotherapy were assessed. Each 4DCT had a physician-defined primary tumour manual contour (MC). An auto-contour (AC) and a user-adjusted auto-contour (UA-AC) were created for each scan. Geometric agreement of the AC and the UA-AC to the MC was assessed using the dice similarity coefficient (DSC), the centre of mass (COM) shift from the MC and the structure volume difference from the MC. Bland Altman analysis was carried out to assess agreement between contouring methods. Dosimetric reliability was assessed by comparison of planning target volume dose coverage on the MC and UA-AC. The time trend analysis of the geometric accuracy measures from the initial planning scan through to the final scan for each patient was evaluated using a Wilcoxon signed ranks test to assess the reliability of the UA-AC over the duration of radiotherapy.

RESULTS

User adjustment significantly improved all geometric comparison metrics over the AC alone. Improved agreement was observed in smaller tumours not abutting normal soft tissue and median values for geometric comparisons to the MC for DSC, tumour volume difference and COM offset were 0.80 (range 0.49-0.89), 0.8 cm³ (range 0.0-5.9 cm³) and 0.16 cm (range 0.09-0.69 cm), respectively. There were no significant differences in dose metrics measured from the MC and the UA-AC after Bonferroni correction. Variation in geometric agreement between the MC and the UA-AC were observed over the course of radiotherapy with both DSC (P = 0.035) and COM shift from the MC (ns) worsening. The median tumour volume difference from the MC improved at the later time point.

CONCLUSIONS

These findings suggest that the UA-AC can produce geometrically and dosimetrically acceptable contours for appropriately selected patients with non-small cell lung cancer. Larger studies are required to confirm the findings.

A Machine Learning method for relabeling arbitrary DICOM structure sets to TG-263 defined labels

PURPOSE

To present a Machine Learning pipeline for automatically relabeling anatomical structure sets in the Digital Imaging and Communications in Medicine (DICOM) format to a standard nomenclature that will enable data abstraction for research and quality improvement.

METHODS

DICOM structure sets from approximately 1200 lung and prostate cancer patients across 40 treatment centers were used to build predictive models to automate the relabeling of clinically specified structure labels to standardized labels as defined by the American Association of Physics in Medicine's (AAPM) Task Group 263 (TG-263). Volumetric bitmaps were created based on the delineated volumes and were combined with associated bony anatomy data to build feature vectors. Feature reduction was performed with singular value decomposition and the resulting vectors were used for predicting the label of each structure using five different classifier algorithms on the Apache Spark platform with 5-fold cross-validation. Undersampling methods were used to deal with underlying class imbalance that hindered the performance of classifiers. Experiments were performed on both a curated version of the data, which included only annotated structures, and the non-curated data that included all structures from the original treatment plans.

RESULTS

Random Forest provided the highest accuracies with F₁ scores of 98.77 for lung and 95.06 for prostate on the curated data sets. Scores were lower with 95.67 for lung and 90.22 for prostate on the non-curated data sets, highlighting some of the challenges of classifying real clinical data. Including bony anatomy data and pooling information from all structures for the same patient both increased accuracies. In some cases, undersampling with k-Means clustering for class balancing improved classifier accuracy but in all experiments it significantly reduced run time compared to random undersampling.

CONCLUSION

This work shows that structure sets can be relabeled using our approach with accuracies over 95% for many structure types when presented with curated data. Although accuracies dropped when using the full non-curated data sets, some structure types were still correctly labeled over 90% of the time. With similar results obtained on an external test data set, we can infer that the proposed models are likely to work on other clinical data sets.

A Systematic Review of Contouring Guidelines in Radiation Oncology: Analysis of Frequency, Methodology, and Delivery of Consensus Recommendations

PURPOSE

Clinical trials have described variation in radiation therapy plan quality, of which contour delineation is a key component, and linked this to inferior patient outcomes. In response, consensus guidelines have been developed to standardize contour delineation. This investigation assesses trends in contouring guidelines and examines the methodologies used to generate and deliver recommendations.

METHODS AND MATERIALS

We conducted a literature search for contouring guidelines published after 1995. Of 11,124 citations, 332 were identified for full-text review to determine inclusion. We abstracted articles for the intent of the consensus process, key elements of the methodology, and mode of information delivery. A Fisher exact test was used to identify elements that differed among the guidelines generated for clinical trials and routine care.

RESULTS

Overall, 142 guidelines were included, of which 16 (11%) were developed for a clinical trial. There was an increase in guideline publication over time (0 from 1995-1999 vs 65 from 2015- 2019; P = .03), particularly among recommendations for stereotactic radiation and brachytherapy. The most common disease sites were head and neck (24%), gastrointestinal (12%), and gynecologic (12%). Methods used to develop recommendations included literature review (50%) and image-based methods (45%). Panels included a median of 10 physicians (interquartile range, 7-16); 70% of panels represented multidisciplinary expertise. Guidelines developed for a clinical trial were more likely to include an image-based approach, with quantitative analysis of contours submitted by the panel members and to publish a full set of image-based recommendations (P < .005).

CONCLUSIONS

This review highlights an increase in consensus contouring recommendations over time. Guidelines focus on disease sites, such as head and neck, with evidence supporting a correlation between treatment planning and patient outcomes, although variation exists in the approach to the consensus process. Elements that may improve guideline acceptance (ie, image-based consensus contour analysis) and usability (ie, inclusion of a full image set) are more common in guidelines developed for clinical trials.

Clinical Evaluation of Deep Learning and Atlas-Based Auto-Contouring of Bladder and Rectum for Prostate Radiation Therapy

PURPOSE

Auto-contouring may reduce workload, interobserver variation, and time associated with manual contouring of organs at risk. Manual contouring remains the standard due in part to uncertainty around the time and workload savings after accounting for the review and editing of auto-contours. This preliminary study compares a standard manual contouring workflow with 2 auto-contouring workflows (atlas and deep learning) for contouring the bladder and rectum in patients with prostate cancer.

METHODS AND MATERIALS

Three contouring workflows were defined based on the initial contour-generation method including manual (MAN), atlas-based auto-contour (ATLAS), and deep-learning auto-contour (DEEP). For each workflow, initial contour generation was retrospectively performed on 15 patients with prostate cancer. Then, radiation oncologists (ROs) edited each contour while blinded to the manner in which the initial contour was generated. Workflows were compared by time (both in initial contour generation and in RO editing), contour similarity, and dosimetric evaluation.

RESULTS

Mean durations for initial contour generation were 10.9 min, 1.4 min, and 1.2 min for MAN, DEEP, and ATLAS, respectively. Initial DEEP contours were more geometrically similar to initial MAN contours. Mean durations of the RO editing steps for MAN, DEEP, and ATLAS contours were 4.1 min, 4.7 min, and 10.2 min, respectively. The geometric extent of RO edits was consistently larger for ATLAS contours compared with MAN and DEEP. No differences in clinically relevant dose-volume metrics were observed between workflows.

CONCLUSION

Auto-contouring software affords time savings for initial contour generation; however, it is important to also quantify workload changes at the RO editing step. Using deep-learning auto-contouring for bladder and rectum contour generation reduced contouring time without negatively affecting RO editing times, contour geometry, or clinically relevant dose-volume metrics. This work contributes to growing evidence that deep-learning methods are a clinically viable solution for organ-at-risk contouring in radiation therapy.

Safety First: Developing and Deploying a System to Promote Safety and Quality in Your Clinic

The terms "safety and quality" (SAQ) have become inextricably linked, highly used terms that together encompass a wide range of parameters within medical departments. Safety has always been a priority in radiation oncology; quality assurance has been foundational to our practice. Despite this increased focus and attention on SAQ, the "what" of SAQ remains ill-defined, largely because of the vast number of indicators that fall under this umbrella. Similarly, the "how" of developing and maintaining the highest standards of SAQ is not formulaic and varies based on the unique setting of individual practices. There are several excellent resources available to inform SAQ in radiation oncology, including the American Society for Radiation Oncology's "Safety Is No Accident," which provides an overview of safety and quality standards and resources. This review is intended as a brief summary of key considerations, with the goal of providing a practical framework and context for improving or developing a SAQ program in radiation oncology practices. We believe that the following 10 key elements, drawn from numerous reports that have appeared over the last decade examining this topic, should be considered when conceptualizing a practice-based approach to SAQ: establishing a strong safety culture; establishing a structured program for safety and quality; establishing up-to-date, relevant, and accessible policies and procedures; a system for peer review; systems to assess and reduce risk; an educational program focused on safety and quality; development and review of meaningful quality metrics; utilization of a physics quality control system; well-defined models for staffing, training, and professional development; and finally, validation from external bodies via accreditations and audits. These 10 items are addressed herein.

Integrated Natural Language Processing and Machine Learning Models for Standardizing Radiotherapy Structure Names

The lack of standardized structure names in radiotherapy (RT) data limits interoperability, data sharing, and the ability to perform big data analysis. To standardize radiotherapy structure names, we developed an integrated natural language processing (NLP) and machine learning (ML) based system that can map the physician-given structure names to American Association of Physicists in Medicine (AAPM) Task Group 263 (TG-263) standard names. The dataset consist of 794 prostate and 754 lung cancer patients across the 40 different radiation therapy centers managed by the Veterans Health Administration (VA). Additionally, data from the Radiation Oncology department at Virginia Commonwealth University (VCU) was collected to serve as a test set. Domain experts identified as anatomically significant nine prostate and ten lung organs-at-risk (OAR) structures and manually labeled them according to the TG-263 standards, and remaining structures were labeled as Non_OAR. We experimented with six different classification algorithms and three feature vector methods, and the final model was built with fastText algorithm. Multiple validation techniques are used to assess the robustness of the proposed methodology. The macro-averaged F 1 score was used as the main evaluation metric. The model achieved an F 1 score of 0.97 on prostate structures and 0.99 for lung structures from the VA dataset. The model also performed well on the test (VCU) dataset, achieving an F 1 score of 0.93 for prostate structures and 0.95 on lung structures. In this work, we demonstrate that NLP and ML based approaches can used to standardize the physician-given RT structure names with high fidelity. This standardization can help with big data analytics in the radiation therapy domain using population-derived datasets, including standardization of the treatment planning process, clinical decision support systems, treatment quality improvement programs, and hypothesis-driven clinical research.

Provision of Organ at Risk Contouring Guidance in UK Radiotherapy Clinical Trials

AIMS

Accurate delineation of organs at risk (OAR) is vital to the radiotherapy planning process. Inaccuracies in OAR delineation arising from imprecise anatomical definitions may affect plan optimisation and risk inappropriate dose delivery to normal tissues. The aim of this study was to review the provision of OAR contouring guidance in National Institute of Health Research Clinical Research Network (NIHR CRN) portfolio clinical trials.

MATERIALS AND METHODS

The National Radiotherapy Quality Trials Assurance (RTTQA) Group carried out a two-round Delphi assessment to determine which OAR descriptions provided optimal guidance.

RESULTS

Eighty-four clinical trials involving radiotherapy quality assurance were identified as either in recruitment or in setup within the NIHR CRN portfolio. Fifty-nine trials mandated OAR contouring. In total there were 412 OAR; 171 were uniquely named; 159 OAR had more than one name associated with a single structure, with the greatest nomenclature variation seen for the femoral head ± neck, the parotid gland, and bowel. The two-round Delphi assessment determined 42 OAR descriptions as providing optimal contouring guidance.

CONCLUSIONS

This study identified the need for OAR nomenclature and contouring guidance consistency across clinical trials. In response to this study and in conjunction with the Global Quality Assurance of Radiation Therapy Clinical Trials Harmonisation Group, the RTTQA Group is in collaboration with international partners to provide consensus recommendations for OAR delineation in clinical trials.

Initial experience with introducing national guidelines for CT- and MRI-based delineation of organs at risk in radiotherapy

A fundamental problem in radiotherapy is the variation of organ at risk (OAR) volumes. Here we present our initial experience in engaging a large Radiation Oncology (RO) community to agree on national guidelines for OAR delineations. Our project builds on associated standardization initiatives and invites professionals from all radiotherapy departments nationwide. Presently, one guideline (rectum) has successfully been agreed on by a majority vote. Reaching out to all relevant parties in a timely manner and motivating funding agencies to support the work represented early challenges. Population-based data and a scalable methodological approach are major strengths of the proposed strategy.

Why Smart Oncology Clinicians do Dumb Things: A Review of Cognitive Bias in Radiation Oncology

This review will discuss the (perhaps biased) way in which smart oncologists think, biases they can identify, and potential strategies to minimize the impact of bias. It is critical to understand cognitive bias as a significant risk (recognized by the Joint Commission) associated with patient safety, and cognitive bias has been implicated in major radiotherapy incidents. The way in which we think are reviewed, covering both System 1 and system 2 processes of thinking, as well as behavioral economics concepts (prospect theory, expected utility theory). Predisposing factors to cognitive error are explained, with exploration of the groupings of person factors, patient factors, and system factors which can influence the quality of our decision-making. Other factors found to influence decision making are also discussed (rudeness, repeated decision making, hunger, personal attitudes). The review goes on to discuss cognitive bias in the clinic and in workplace interactions (including recruitment), with practical examples provided of each bias. Finally, the review covers strategies to combat cognitive bias, including summarize aloud, crowd wisdom, prospective hindsight, and joint evaluation. More definitive ways to mitigate bias are desirable.