Clinical Acceptability of Automated Radiation Treatment Planning for Head and Neck Cancer Using the Radiation Planning Assistant.

PURPOSE: Radiation treatment planning for head and neck cancer is a complex process with much variability; automated treatment planning is a promising option to improve plan quality and efficiency. This study compared radiation plans generated from a fully automated radiation treatment planning system to plans generated manually that had been clinically approved and delivered. METHODS AND MATERIALS: The study cohort consisted of 50 patients treated by a specialized head and neck cancer team at a tertiary care center. An automated radiation treatment planning system, the Radiation Planning Assistant, was used to create autoplans for all patients using their original, approved contours. Common dose-volume histogram (DVH) criteria were used to compare the quality of autoplans to the clinical plans. Fourteen radiation oncologists, each from a different institution, then reviewed and compared the autoplans and clinical plans in a blinded fashion. RESULTS: Autoplans and clinical plans were very similar with regard to DVH metrics for coverage and critical structure constraints. Physician reviewers found both the clinical plans and autoplans acceptable for use; overall, 78% of the clinical plans and 88% of the autoplans were found to be usable as is (without any edits). When asked to choose which plan would be preferred for approval, 27% of physician reviewers selected the clinical plan, 47% selected the autoplan, 25% said both were equivalent, and 0% said neither. Hence, overall, 72% of physician reviewers believed the autoplan or either the clinical or autoplan was preferable. CONCLUSIONS: Automated radiation treatment planning creates consistent, clinically acceptable treatment plans that meet DVH criteria and are found to be appropriate on physician review.

Generating High-Quality Lymph Node Clinical Target Volumes for Head and Neck Cancer Radiation Therapy Using a Fully Automated Deep Learning-Based Approach.

PURPOSE: To develop a deep learning model that generates consistent, high-quality lymph node clinical target volumes (CTV) contours for head and neck cancer (HNC) patients, as an integral part of a fully automated radiation treatment planning workflow. METHODS AND MATERIALS: Computed tomography (CT) scans from 71 HNC patients were retrospectively collected and split into training (n = 51), cross-validation (n = 10), and test (n = 10) data sets. All had target volume delineations covering lymph node levels Ia through V (Ia-V), Ib through V (Ib-V), II through IV (II-IV), and retropharyngeal (RP) nodes, which were previously approved by a radiation oncologist specializing in HNC. Volumes of interest (VOIs) about nodal levels were automatically identified using computer vision techniques. The VOI (cropped CT image) and approved contours were used to train a U-Net autosegmentation model. Each lymph node level was trained independently, with model parameters optimized by assessing performance on the cross-validation data set. Once optimal model parameters were identified, overlap and distance metrics were calculated between ground truth and autosegmentations on the test set. Lastly, this final model was used on 32 additional patient scans (not included in original 71 cases) and autosegmentations visually rated by 3 radiation oncologists as being "clinically acceptable without requiring edits," "requiring minor edits," or "requiring major edits." RESULTS: When comparing ground truths to autosegmentations on the test data set, median Dice Similarity Coefficients were 0.90, 0.90, 0.89, and 0.81, and median mean surface distance values were 1.0 mm, 1.0 mm, 1.1 mm, and 1.3 mm for node levels Ia-V, Ib-V, II-IV, and RP nodes, respectively. Qualitative scoring varied among physicians. Overall, 99% of autosegmented target volumes were either scored as being clinically acceptable or requiring minor edits (ie, stylistic recommendations, <2 minutes). CONCLUSIONS: We developed a fully automated artificial intelligence approach to autodelineate nodal CTVs for patients with intact HNC. Most autosegmentations were found to be clinically acceptable after qualitative review when considering recommended stylistic edits. This promising work automatically delineates nodal CTVs in a robust and consistent manner; this approach can be implemented in ongoing efforts for fully automated radiation treatment planning.

Assessing Outcomes of Patients Treated With Re-Irradiation Utilizing Proton Pencil-Beam Scanning for Primary or Recurrent Malignancies of the Esophagus and Gastroesophageal Junction.

INTRODUCTION: Re-irradiation (re-RT) for locoregionally recurrent esophageal and gastroesophageal junction (GEJ) cancer and de novo esophageal + GEJ cancer arising in-field after a course of prior radiation poses considerable treatment challenges given the sensitivity of surrounding organs at risk (OARs). Guidelines for treatment of this presentation are not well established. Pencil-beam scanning (PBS) proton therapy has the ability to decrease radiation dose to OARs relative to photon plans. We present the first published series to date of re-RT with PBS for esophageal + GEJ malignancies and hypothesize that re-RT with proton PBS will be feasible and improve the safety profile of re-RT for this cohort of patients. METHODS: Consecutive esophageal + GEJ cancers treated with PBS re-RT within a single institution were analyzed. Comparative volumetric-modulated arc therapy photon plans were generated. A total of 17 patients were included for analysis. RESULTS: At a median follow-up of 11.6 months, 1-year local control was 75.3% and overall survival was 68.9%. There were five (27.8%) grade 3 or higher late toxicities. When matched for clinical target volume coverage, proton PBS plans delivered significantly lower doses to the spinal cord, lungs, liver, and heart (all p < 0.05); five volumetric-modulated arc therapy plans would have been undeliverable on the basis of physician-specified OAR constraints. CONCLUSIONS: Re-RT for de novo or recurrent malignancies of the esophagus + GEJ, when delivered with PBS proton therapy, yields high rates of local control with acceptable acute and late toxicities in a high-risk population and decreased radiation dose to OARs relative to comparative photon plans. This is the largest series of proton re-RT for esophageal malignancies and the first that exclusively used PBS.

Automatic detection of contouring errors using convolutional neural networks.

PURPOSE: To develop a head and neck normal structures autocontouring tool that could be used to automatically detect the errors in autocontours from a clinically validated autocontouring tool. METHODS: An autocontouring tool based on convolutional neural networks (CNN) was developed for 16 normal structures of the head and neck and tested to identify the contour errors from a clinically validated multiatlas-based autocontouring system (MACS). The computed tomography (CT) scans and clinical contours from 3495 patients were semiautomatically curated and used to train and validate the CNN-based autocontouring tool. The final accuracy of the tool was evaluated by calculating the Sørensen-Dice similarity coefficients (DSC) and Hausdorff distances between the automatically generated contours and physician-drawn contours on 174 internal and 24 external CT scans. Lastly, the CNN-based tool was evaluated on 60 patients' CT scans to investigate the possibility to detect contouring failures. The contouring failures on these patients were classified as either minor or major errors. The criteria to detect contouring errors were determined by analyzing the DSC between the CNN- and MACS-based contours under two independent scenarios: (a) contours with minor errors are clinically acceptable and (b) contours with minor errors are clinically unacceptable. RESULTS: The average DSC and Hausdorff distance of our CNN-based tool was 98.4%/1.23 cm for brain, 89.1%/0.42 cm for eyes, 86.8%/1.28 cm for mandible, 86.4%/0.88 cm for brainstem, 83.4%/0.71 cm for spinal cord, 82.7%/1.37 cm for parotids, 80.7%/1.08 cm for esophagus, 71.7%/0.39 cm for lenses, 68.6%/0.72 for optic nerves, 66.4%/0.46 cm for cochleas, and 40.7%/0.96 cm for optic chiasm. With the error detection tool, the proportions of the clinically unacceptable MACS contours that were correctly detected were 0.99/0.80 on average except for the optic chiasm, when contours with minor errors are clinically acceptable/unacceptable, respectively. The proportions of the clinically acceptable MACS contours that were correctly detected were 0.81/0.60 on average except for the optic chiasm, when contours with minor errors are clinically acceptable/unacceptable, respectively. CONCLUSION: Our CNN-based autocontouring tool performed well on both the publically available and the internal datasets. Furthermore, our results show that CNN-based algorithms are able to identify ill-defined contours from a clinically validated and used multiatlas-based autocontouring tool. Therefore, our CNN-based tool can effectively perform automatic verification of MACS contours.

Fully Automatic Treatment Planning for External-Beam Radiation Therapy of Locally Advanced Cervical Cancer: A Tool for Low-Resource Clinics.

PURPOSE: The purpose of this study was to validate a fully automatic treatment planning system for conventional radiotherapy of cervical cancer. This system was developed to mitigate staff shortages in low-resource clinics. METHODS: In collaboration with hospitals in South Africa and the United States, we have developed the Radiation Planning Assistant (RPA), which includes algorithms for automating every step of planning: delineating the body contour, detecting the marked isocenter, designing the treatment-beam apertures, and optimizing the beam weights to minimize dose heterogeneity. First, we validated the RPA retrospectively on 150 planning computed tomography (CT) scans. We then tested it remotely on 14 planning CT scans at two South African hospitals. Finally, automatically planned treatment beams were clinically deployed at our institution. RESULTS: The automatically and manually delineated body contours agreed well (median mean surface distance, 0.6 mm; range, 0.4 to 1.9 mm). The automatically and manually detected marked isocenters agreed well (mean difference, 1.1 mm; range, 0.1 to 2.9 mm). In validating the automatically designed beam apertures, two physicians, one from our institution and one from a South African partner institution, rated 91% and 88% of plans acceptable for treatment, respectively. The use of automatically optimized beam weights reduced the maximum dose significantly (median, -1.9%; P < .001). Of the 14 plans from South Africa, 100% were rated clinically acceptable. Automatically planned treatment beams have been used for 24 patients with cervical cancer by physicians at our institution, with edits as needed, and its use is ongoing. CONCLUSION: We found that fully automatic treatment planning is effective for cervical cancer radiotherapy and may provide a reliable option for low-resource clinics. Prospective studies are ongoing in the United States and are planned with partner clinics.

Auto-delineation of oropharyngeal clinical target volumes using 3D convolutional neural networks.

Accurate clinical target volume (CTV) delineation is essential to ensure proper tumor coverage in radiation therapy. This is a particularly difficult task for head-and-neck cancer patients where detailed knowledge of the pathways of microscopic tumor spread is necessary. This paper proposes a solution to auto-segment these volumes in oropharyngeal cancer patients using a two-channel 3D U-Net architecture. The first channel feeds the network with the patient's CT image providing anatomical context, whereas the second channel provides the network with tumor location and morphological information. Radiation therapy simulation computer tomography scans and their corresponding manually delineated CTV and gross tumor volume (GTV) delineations from 285 oropharyngeal patients previously treated at MD Anderson Cancer Center were used in this study. CTV and GTV delineations underwent rigorous group peer-review prior to the start of treatment delivery. The convolutional network's parameters were fine-tuned using a training set of 210 patients using 3-fold cross-validation. During hyper-parameter selection, we use a score based on the overlap (dice similarity coefficient (DSC)) and missed volumes (false negative dice (FND)) to minimize any possible under-treatment. Three auto-delineated models were created to estimate tight, moderate, and wide CTV margin delineations. Predictions on our test set (75 patients) resulted in auto-delineations with high overlap and close surface distance agreement (DSC > 0.75 on 96% of cases for tight and moderate auto-delineation models and 97% of cases having mean surface distance ⩽ 5.0 mm) to the ground-truth. We found that applying a 5 mm uniform margin expansion to the auto-delineated CTVs would cover at least 90% of the physician CTV volumes for a large majority of patients; however, determination of appropriate margin expansions for auto-delineated CTVs merits further investigation.

Retrospective Validation and Clinical Implementation of Automated Contouring of Organs at Risk in the Head and Neck: A Step Toward Automated Radiation Treatment Planning for Low- and Middle-Income Countries.

Purpose We assessed automated contouring of normal structures for patients with head-and-neck cancer (HNC) using a multiatlas deformable-image-registration algorithm to better provide a fully automated radiation treatment planning solution for low- and middle-income countries, provide quantitative analysis, and determine acceptability worldwide. Methods Autocontours of eight normal structures (brain, brainstem, cochleae, eyes, lungs, mandible, parotid glands, and spinal cord) from 128 patients with HNC were retrospectively scored by a dedicated HNC radiation oncologist. Contours from a 10-patient subset were evaluated by five additional radiation oncologists from international partner institutions, and interphysician variability was assessed. Quantitative agreement of autocontours with independently physician-drawn structures was assessed using the Dice similarity coefficient and mean surface and Hausdorff distances. Automated contouring was then implemented clinically and has been used for 166 patients, and contours were quantitatively compared with the physician-edited autocontours using the same metrics. Results Retrospectively, 87% of normal structure contours were rated as acceptable for use in dose-volume-histogram-based planning without edit. Upon clinical implementation, 50% of contours were not edited for use in treatment planning. The mean (± standard deviation) Dice similarity coefficient of autocontours compared with physician-edited autocontours for parotid glands (0.92 ± 0.10), brainstem (0.95 ± 0.09), and spinal cord (0.92 ± 0.12) indicate that only minor edits were performed. The average mean surface and Hausdorff distances for all structures were less than 0.15 mm and 1.8 mm, respectively. Conclusion Automated contouring of normal structures generates reliable contours that require only minimal editing, as judged by retrospective ratings from multiple international centers and clinical integration. Autocontours are acceptable for treatment planning with no or, at most, minor edits, suggesting that automated contouring is feasible for clinical use and in the ongoing development of automated radiation treatment planning algorithms.

Radiation Planning Assistant - A Streamlined, Fully Automated Radiotherapy Treatment Planning System.

The Radiation Planning Assistant (RPA) is a system developed for the fully automated creation of radiotherapy treatment plans, including volume-modulated arc therapy (VMAT) plans for patients with head/neck cancer and 4-field box plans for patients with cervical cancer. It is a combination of specially developed in-house software that uses an application programming interface to communicate with a commercial radiotherapy treatment planning system. It also interfaces with a commercial secondary dose verification software. The necessary inputs to the system are a Treatment Plan Order, approved by the radiation oncologist, and a simulation computed tomography (CT) image, approved by the radiographer. The RPA then generates a complete radiotherapy treatment plan. For the cervical cancer treatment plans, no additional user intervention is necessary until the plan is complete. For head/neck treatment plans, after the normal tissue and some of the target structures are automatically delineated on the CT image, the radiation oncologist must review the contours, making edits if necessary. They also delineate the gross tumor volume. The RPA then completes the treatment planning process, creating a VMAT plan. Finally, the completed plan must be reviewed by qualified clinical staff.

Deep Learning Algorithm for Auto-Delineation of High-Risk Oropharyngeal Clinical Target Volumes With Built-In Dice Similarity Coefficient Parameter Optimization Function.

PURPOSE: Automating and standardizing the contouring of clinical target volumes (CTVs) can reduce interphysician variability, which is one of the largest sources of uncertainty in head and neck radiation therapy. In addition to using uniform margin expansions to auto-delineate high-risk CTVs, very little work has been performed to provide patient- and disease-specific high-risk CTVs. The aim of the present study was to develop a deep neural network for the auto-delineation of high-risk CTVs. METHODS AND MATERIALS: Fifty-two oropharyngeal cancer patients were selected for the present study. All patients were treated at The University of Texas MD Anderson Cancer Center from January 2006 to August 2010 and had previously contoured gross tumor volumes and CTVs. We developed a deep learning algorithm using deep auto-encoders to identify physician contouring patterns at our institution. These models use distance map information from surrounding anatomic structures and the gross tumor volume as input parameters and conduct voxel-based classification to identify voxels that are part of the high-risk CTV. In addition, we developed a novel probability threshold selection function, based on the Dice similarity coefficient (DSC), to improve the generalization of the predicted volumes. The DSC-based function is implemented during an inner cross-validation loop, and probability thresholds are selected a priori during model parameter optimization. We performed a volumetric comparison between the predicted and manually contoured volumes to assess our model. RESULTS: The predicted volumes had a median DSC value of 0.81 (range 0.62-0.90), median mean surface distance of 2.8 mm (range 1.6-5.5), and median 95th Hausdorff distance of 7.5 mm (range 4.7-17.9) when comparing our predicted high-risk CTVs with the physician manual contours. CONCLUSIONS: These predicted high-risk CTVs provided close agreement to the ground-truth compared with current interobserver variability. The predicted contours could be implemented clinically, with only minor or no changes.

Model for Estimating Power and Downtime Effects on Teletherapy Units in Low-Resource Settings.

PURPOSE: More than 6,500 megavoltage teletherapy units are needed worldwide, many in low-resource settings. Cobalt-60 units or linear accelerators (linacs) can fill this need. We have evaluated machine performance on the basis of patient throughput to provide insight into machine viability under various conditions in such a way that conclusions can be generalized to a vast array of clinical scenarios. MATERIALS AND METHODS: Data from patient treatment plans, peer-reviewed studies, and international organizations were combined to assess the relative patient throughput of linacs and cobalt-60 units that deliver radiotherapy with standard techniques under various power and maintenance support conditions. Data concerning the frequency and duration of power outages and downtime characteristics of the machines were used to model teletherapy operation in low-resource settings. RESULTS: Modeled average daily throughput was decreased for linacs because of lack of power infrastructure and for cobalt-60 units because of limited and decaying source strength. For conformal radiotherapy delivered with multileaf collimators, average daily patient throughput over 8 years of operation was equal for cobalt-60 units and linacs when an average of 1.83 hours of power outage occurred per 10-hour working day. Relative to conformal treatments delivered with multileaf collimators on the respective machines, the use of advanced techniques on linacs decreased throughput between 20% and 32% and, for cobalt machines, the need to manually place blocks reduced throughput up to 37%. CONCLUSION: Our patient throughput data indicate that cobalt-60 units are generally best suited for implementation when machine operation might be 70% or less of total operable time because of power outages or mechanical repair. However, each implementation scenario is unique and requires consideration of all variables affecting implementation.

Cost-effective immobilization for whole brain radiation therapy.

To investigate the inter- and intra-fraction motion associated with the use of a low-cost tape immobilization technique as an alternative to thermoplastic immobilization masks for whole-brain treatments. The results of this study may be of interest to clinical staff with severely limited resources (e.g., in low-income countries) and also when treating patients who cannot tolerate standard immobilization masks. Setup reproducibility of eight healthy volunteers was assessed for two different immobilization techniques. (a) One strip of tape was placed across the volunteer's forehead and attached to the sides of the treatment table. (b) A second strip was added to the first, under the chin, and secured to the table above the volunteer's head. After initial positioning, anterior and lateral photographs were acquired. Volunteers were positioned five times with each technique to allow calculation of inter-fraction reproducibility measurements. To estimate intra-fraction reproducibility, 5-minute anterior and lateral videos were taken for each technique per volunteer. An in-house software was used to analyze the photos and videos to assess setup reproducibility. The maximum intra-fraction displacement for all volunteers was 2.8 mm. Intra-fraction motion increased with time on table. The maximum inter-fraction range of positions for all volunteers was 5.4 mm. The magnitude of inter-fraction and intra-fraction motion found using the "1-strip" and "2-strip" tape immobilization techniques was comparable to motion restrictions provided by a thermoplastic mask for whole-brain radiotherapy. The results suggest that tape-based immobilization techniques represent an economical and useful alternative to the thermoplastic mask.

Reproducibility of patient setup in the seated treatment position: A novel treatment chair design.

Radiotherapy in a seated position may be indicated for patients who are unable to lie on the treatment couch for the duration of treatment, in scenarios where a seated treatment position provides superior anatomical positioning and dose distributions, or for a low-cost system designed using a fixed treatment beam and rotating seated patient. In this study, we report a novel treatment chair that was constructed to allow for three-dimensional imaging and treatment delivery while ensuring robust immobilization, providing reproducibility equivalent to that in the traditional supine position. Five patients undergoing radiation treatment for head-and-neck cancers were enrolled and were setup in the chair, with immobilization devices created, and then imaged with orthogonal X-rays in a scenario that mimicked radiation treatments (without treatment delivery). Six subregions of the acquired images were rigidly registered to evaluate intra- and interfraction displacement and chair construction. Displacements under conditions of simulated image guidance were acquired by first registering one subregion; the residual displacement of other subregions was then measured. Additionally, we administered a patient questionnaire to gain patient feedback and assess comparison to the supine position. Average inter- and intrafraction displacements of all subregions in the seated position were less than 2 and 3 mm, respectively. When image guidance was simulated, L-R and A-P interfraction displacements were reduced by an average of 1 mm, providing setup of comparable quality to supine setups. The enrolled patients, who had no indication for a seated treatment position, reported no preference in the seated or the supine position. The novel chair design provides acceptable inter- and intrafraction displacement, with reproducibility equivalent to that reported for patients in the supine position. Patient feedback will be incorporated in the refinement of the chair, facilitating treatment of head-and-neck cancer in patients who are unable to lie for the duration of treatment or for use in an economical fixed-beam setup.

3D-Printed Small-Animal Immobilizer for Use in Preclinical Radiotherapy.

We have designed a method for immobilizing the subjects of small-animal studies using a study group-specific 3D-printed immobilizer that significantly reduces interfraction rotational variation. A cone-beam CT scan acquired from a single specimen in a study group was used to create a 3D-printed immobilizer that can be used for all specimens in the same study group. 3D printing allows for the incorporation of study-specific features into the immobilizer design, including geometries suitable for use in MR and CT scanners, holders for fiducial markers, and anesthesia nose cones of various sizes. Using metrics of rotational setup variations, we compared the current setup in our small-animal irradiation system, a half-pipe bed, with the 3D-printed device. We also assessed translational displacement within the immobilizer. The printed design significantly reduced setup variation, with average reductions in rotational displacement of 76% ± 3% (1.57 to 0.37°) in pitch, 78% ± 3% (1.85 to 0.41°) in yaw, and 87% ± 3% (5.39 to 0.70°) in roll. Translational displacement within the printed immobilizer was less than 1.5 ± 0.3 mm. This method of immobilization allows for repeatable setup when using MR or CT scans for the purpose of radiotherapy, streamlines the workflow, and places little burden on the study subjects.