Clinical physicists' perceptions of weekly chart checks and the potential role for automated image review assessed by structured interviews.

BACKGROUND: This study utilizes interviews of clinical medical physicists to investigate self-reported shortcomings of the current weekly chart check workflow and opportunities for improvement. METHODS: Nineteen medical physicists were recruited for a 30-minute semi-structured interview, with a particular focus placed on image review and the use of automated tools for image review in weekly checks. Survey-type questions were used to gather quantitative information about chart check practices and importance placed on reducing chart check workloads versus increasing chart check effectiveness. Open-ended questions were used to probe respondents about their current weekly chart check workflow, opinions of the value of weekly chart checks and perceived shortcomings, and barriers and facilitators to the implementation of automated chart check tools. Thematic analysis was used to develop common themes across the interviews. RESULTS: Physicists ranked highly the value of reducing the time spent on weekly chart checks (average 6.3 on a scale from 1 to 10), but placed more value on increasing the effectiveness of checks with an average of 9.2 on a 1-10 scale. Four major themes were identified: (1) weekly chart checks need to adapt to an electronic record-and-verify chart environment, (2) physicists could add value to patient care by analyzing images without duplicating the work done by physicians, (3) greater support for trending analysis is needed in weekly checks, and (4) automation has the potential to increase the value of physics checks. CONCLUSION: This study identified several key shortcomings of the current weekly chart check process from the perspective of the clinical medical physicist. Our results show strong support for automating components of the weekly check workflow in order to allow for more effective checks that emphasize follow-up, trending, failure modes and effects analysis, and allow time to be spent on other higher value tasks that improve patient safety.

Results of an Artificial Intelligence-Based Image Review System to Detect Patient Misalignment Errors in a Multi-institutional Database of Cone Beam Computed Tomography-Guided Radiation Therapy.

PURPOSE: Present knowledge of patient setup and alignment errors in image guided radiation therapy (IGRT) relies on voluntary reporting, which is thought to underestimate error frequencies. A manual retrospective patient-setup misalignment error search is infeasible owing to the bulk of cases to be reviewed. We applied a deep learning-based misalignment error detection algorithm (EDA) to perform a fully automated retrospective error search of clinical IGRT databases and determine an absolute gross patient misalignment error rate. METHODS AND MATERIALS: The EDA was developed to analyze the registration between planning scans and pretreatment cone beam computed tomography scans, outputting a misalignment score ranging from 0 (most unlikely) to 1 (most likely). The algorithm was trained using simulated translational errors on a data set obtained from 680 patients treated at 2 radiation therapy clinics between 2017 and 2022. A receiver operating characteristic analysis was performed to obtain target thresholds. DICOM Query and Retrieval software was integrated with the EDA to interact with the clinical database and fully automate data retrieval and analysis during a retrospective error search from 2016 to 2017 and from 2021 to 2022 for the 2 institutions, respectively. Registrations were flagged for human review using both a hard-thresholding method and a prediction trending analysis over each individual patient's treatment course. Flagged registrations were manually reviewed and categorized as errors (>1 cm misalignment at the target) or nonerrors. RESULTS: A total of 17,612 registrations were analyzed by the EDA, resulting in 7.7% flagged events. Three previously reported errors were successfully flagged by the EDA, and 4 previously unreported vertebral body misalignment errors were discovered during case reviews. False positive cases often displayed substantial image artifacts, patient rotation, and soft tissue anatomy changes. CONCLUSIONS: Our results validated the clinical utility of the EDA for bulk image reviews and highlighted the reliability and safety of IGRT, with an absolute gross patient misalignment error rate of 0.04% ± 0.02% per delivered fraction.

Automated detection of vertebral body misalignments in orthogonal kV and MV guided radiotherapy: application to a comprehensive retrospective dataset.

Objective. In image-guided radiotherapy (IGRT), off-by-one vertebral body misalignments are rare but potentially catastrophic. In this study, a novel detection method for such misalignments in IGRT was investigated using densely-connected convolutional networks (DenseNets) for applications towards real-time error prevention and retrospective error auditing.Approach. A total of 4213 images acquired from 527 radiotherapy patients aligned with planar kV or MV radiographs were used to develop and test error-detection software modules. Digitally reconstructed radiographs (DRRs) and setup images were retrieved and co-registered according to the clinically applied alignment contained in the DICOM REG files. A semi-automated algorithm was developed to simulate patient positioning errors on the anterior-posterior (AP) and lateral (LAT) images shifted by one vertebral body. A DenseNet architecture was designed to classify either AP images individually or AP and LAT image pairs. Receiver-operator characteristic curves (ROC) and areas under the curves (AUC) were computed to evaluate the classifiers on test subsets. Subsequently, the algorithm was applied to the entire dataset in order to retrospectively determine the absolute off-by-one vertebral body error rate for planar radiograph guided RT at our institution from 2011-2021.Main results. The AUCs for the kV models were 0.98 for unpaired AP and 0.99 for paired AP-LAT. The AUC for the MV AP model was 0.92. For a specificity of 95%, the paired kV model achieved a sensitivity of 99%. Application of the model to the entire dataset yielded a per-fraction off-by-one vertebral body error rate of 0.044% [0.0022%, 0.21%] for paired kV IGRT including one previously unreported error.Significance. Our error detection algorithm was successful in classifying vertebral body positioning errors with sufficient accuracy for retrospective quality control and real-time error prevention. The reported positioning error rate for planar radiograph IGRT is unique in being determined independently of an error reporting system.

Impact of Interfractional Bladder and Trigone Displacement and Deformation on Radiation Exposure and Subsequent Acute Genitourinary Toxicity: A Post Hoc Analysis of Patients Treated with Magnetic Resonance Imaging-Guided Prostate Stereotactic Body Radiation Therapy in a Phase 3 Randomized Trial.

PURPOSE: Emerging data suggest that trigone dosimetry may be more associated with poststereotactic body radiation therapy (SBRT) urinary toxicity than whole bladder dosimetry. We quantify the dosimetric effect of interfractional displacement and deformation of the whole bladder and trigone during prostate SBRT using on-board, pretreatment 0.35T magnetic resonance images (MRI). METHODS AND MATERIALS: Seventy-seven patients treated with MRI-guided prostate SBRT (40 Gy/5 fractions) on the MRI arm of a phase 3 single-center randomized trial were included. Bladder and trigone structures were contoured on images obtained from a 0.35T simulation MRI and 5 on-board pretreatment MRIs. Dice similarity coefficient (DSC) scores and changes in volume between simulation and daily treatments were calculated. Dosimetric parameters including Dmax, D0.03 cc, Dmean, V40 Gy, V39 Gy, V38 Gy, and V20 Gy for the bladder and trigone for the simulation and daily treatments were collected. Both physician-scored (Common Terminology Criteria for Adverse Events, version 4.03 scale) as well as patient-reported (International Prostate Symptom Scores and the Expanded Prostate Cancer Index Composite-26 scores) acute genitourinary (GU) toxicity outcomes were collected and analyzed. RESULTS: The average treatment bladder volume was about 30% smaller than the simulation bladder volume; however, the trigone volume remained fairly consistent despite being positively correlated with total bladder volume. Overall, the trigone accounted for <2% of the bladder volume. Median DSC for the bladder was 0.79, whereas the median DSC of the trigone was only 0.33. No statistically significant associations between our selected bladder and trigonal dosimetric parameters and grade ≥2 GU toxicity were identified, although numerically, patients with GU toxicity (grade ≥2) had higher intermediate doses to the bladder (V20 Gy and Dmean) and larger volumes exposed to higher doses in the trigone (V40 Gy, V39 Gy, and V38 Gy). CONCLUSIONS: The trigone exhibits little volume change, but considerable interfractional displacement/deformation. As a result, the relative volume of the trigone receiving high doses during prostate SBRT varies substantially between fractions, which could influence GU toxicity and may not be predicted by radiation planning dosimetry.

Quantifying Intrafraction Motion and the Impact of Gating for Magnetic Resonance Imaging-Guided Stereotactic Radiation therapy for Prostate Cancer: Analysis of the Magnetic Resonance Imaging Arm From the MIRAGE Phase 3 Randomized Trial.

PURPOSE: Real-time intrafraction tracking/gating is an integral component of magnetic resonance imaging-guided radiation therapy (MRgRT) and may have contributed to the acute toxicity reduction during prostate stereotactic body radiation therapy observed on the MRgRT-arm of the MIRAGE (MAGNETIC RESONANCE IMAGING-GUIDED Stereotactic Body Radiotherapy for Prostate Cancer) randomized trial (NCT04384770). Herein we characterized intrafraction prostate motion and assessed gating effectiveness. METHODS AND MATERIALS: Seventy-nine patients were treated on an MR-LINAC. Real-time cine imaging was acquired at 4Hz in a sagittal plane. If >10% of the prostate area moved outside of a 3-mm gating boundary, an automatic beam hold was initiated. An in-house tool was developed to retrospectively extract gating signal for all patients and identify the tracked prostate in each cine frame for a subgroup of 40 patients. The fraction of time the prostate was within the gating window was defined as the gating duty cycle (GDC). RESULTS: A total of 391 treatments from 79 patients were analyzed. Median GDC was 0.974 (IQR, 0.916-0.983). Fifty (63.2%) and 24 (30.4%) patients had at least 1 fraction with GDC ≤0.9 and GDC ≤0.8, respectively. Incidence of low GDC fractions among patients appeared stochastic. Patients with minimum GDC <0.8 trended toward more frequent grade 2 genitourinary toxicity compared with those with minimum GDC >0.8 (38% vs 18%, P = .065). Prostate intrafraction motion was mostly along the bladder-rectum axis and predominantly in the superior-anterior direction. Motion in the inferior-posterior direction was associated with significantly higher rate of acute grade 2 genitourinary toxicity (66.7% vs 13.9%, P = .001). Gating limited mean prostate motion during treatment delivery in fractions with a GDC <0.9 (<0.8) to 2.9 mm (2.9 mm) versus 4.1 mm (4.7 mm) for ungated motion. CONCLUSIONS: Fractions with large intrafraction motion were associated with increased toxicity and their occurrence among patients appears stochastic. Real-time tracking/gating effectively mitigated this motion and is likely a major contributing factor of acute toxicity reduction associated with MRgRT.

MRI-Guided Radiation Therapy for Prostate Cancer: The Next Frontier in Ultrahypofractionation.

Technological advances in MRI-guided radiation therapy (MRIgRT) have improved real-time visualization of the prostate and its surrounding structures over CT-guided radiation therapy. Seminal studies have demonstrated safe dose escalation achieved through ultrahypofractionation with MRIgRT due to planning target volume (PTV) margin reduction and treatment gating. On-table adaptation with MRI-based technologies can also incorporate real-time changes in target shape and volume and can reduce high doses of radiation to sensitive surrounding structures that may move into the treatment field. Ongoing clinical trials seek to refine ultrahypofractionated radiotherapy treatments for prostate cancer using MRIgRT. Though these studies have the potential to demonstrate improved biochemical control and reduced side effects, limitations concerning patient treatment times and operational workflows may preclude wide adoption of this technology outside of centers of excellence. In this review, we discuss the advantages and limitations of MRIgRT for prostate cancer, as well as clinical trials testing the efficacy and toxicity of ultrafractionation in patients with localized or post-prostatectomy recurrent prostate cancer.

Human factors in the clinical implementation of deep learning-based automated contouring of pelvic organs at risk for MRI-guided radiotherapy.

PURPOSE: Deep neural nets have revolutionized the science of auto-segmentation and present great promise for treatment planning automation. However, little data exists regarding clinical implementation and human factors. We evaluated the performance and clinical implementation of a novel deep learning-based auto-contouring workflow for 0.35T magnetic resonance imaging (MRI)-guided pelvic radiotherapy, focusing on automation bias and objective measures of workflow savings. METHODS: An auto-contouring model was developed using a UNet-derived architecture for the femoral heads, bladder, and rectum in 0.35T MR images. Training data was taken from 75 patients treated with MRI-guided radiotherapy at our institution. The model was tested against 20 retrospective cases outside the training set, and subsequently was clinically implemented. Usability was evaluated on the first 30 clinical cases by computing Dice coefficient (DSC), Hausdorff distance (HD), and the fraction of slices that were used un-modified by planners. Final contours were retrospectively reviewed by an experienced planner and clinical significance of deviations was graded as negligible, low, moderate, and high probability of leading to actionable dosimetric variations. In order to assess whether the use of auto-contouring led to final contours more or less in agreement with an objective standard, 10 pre-treatment and 10 post-treatment blinded cases were re-contoured from scratch by three expert planners to get expert consensus contours (EC). EC was compared to clinically used (CU) contours using DSC. Student's t-test and Levene's statistic were used to test statistical significance of differences in mean and standard deviation, respectively. Finally, the dosimetric significance of the contour differences were assessed by comparing the difference in bladder and rectum maximum point doses between EC and CU before and after the introduction of automation. RESULTS: Median (interquartile range) DSC for the retrospective test data were 0.92(0.02), 0.92(0.06), 0.93(0.06), 0.87(0.04) for the post-processed contours for the right and left femoral heads, bladder, and rectum, respectively. Post-implementation median DSC were 1.0(0.0), 1.0(0.0), 0.98(0.04), and 0.98(0.06), respectively. For each organ, 96.2, 95.4, 59.5, and 68.21 percent of slices were used unmodified by the planner. DSC between EC and pre-implementation CU contours were 0.91(0.05*), 0.91*(0.05*), 0.95(0.04), and 0.88(0.04) for right and left femoral heads, bladder, and rectum, respectively. The corresponding DSC for post-implementation CU contours were 0.93(0.02*), 0.93*(0.01*), 0.96(0.01), and 0.85(0.02) (asterisks indicate statistically significant difference). In a retrospective review of contours used for planning, a total of four deviating slices in two patients were graded as low potential clinical significance. No deviations were graded as moderate or high. Mean differences between EC and CU rectum max-doses were 0.1 ± 2.6 Gy and -0.9 ± 2.5 Gy for pre- and post-implementation, respectively. Mean differences between EC and CU bladder/bladder wall max-doses were -0.9 ± 4.1 Gy and 0.0 ± 0.6 Gy for pre- and post-implementation, respectively. These differences were not statistically significant according to Student's t-test. CONCLUSION: We have presented an analysis of the clinical implementation of a novel auto-contouring workflow. Substantial workflow savings were obtained. The introduction of auto-contouring into the clinical workflow changed the contouring behavior of planners. Automation bias was observed, but it had little deleterious effect on treatment planning.

Proof-of-concept study of artificial intelligence-assisted review of CBCT image guidance.

PURPOSE: Automation and computer assistance can support quality assurance tasks in radiotherapy. Retrospective image review requires significant human resources, and automation of image review remains a noteworthy missing element in previous work. Here, we present initial findings from a proof-of-concept clinical implementation of an AI-assisted review of CBCT registrations used for patient setup. METHODS: An automated pipeline was developed and executed nightly, utilizing python scripts to interact with the clinical database through DICOM networking protocol and automate data retrieval and analysis. A previously developed artificial intelligence (AI) algorithm scored CBCT setup registrations based on misalignment likelihood, using a scale from 0 (most unlikely) through 1 (most likely). Over a 45-day period, 1357 pre-treatment CBCT registrations from 197 patients were retrieved and analyzed by the pipeline. Daily summary reports of the previous day's registrations were produced. Initial action levels targeted 10% of cases to highlight for in-depth physics review. A validation subset of 100 cases was scored by three independent observers to characterize AI-model performance. RESULTS: Following an ROC analysis, a global threshold for model predictions of 0.87 was determined, with a sensitivity of 100% and specificity of 82%. Inspecting the observer scores for the stratified validation dataset showed a statistically significant correlation between observer scores and model predictions. CONCLUSION: In this work, we describe the implementation of an automated AI-analysis pipeline for daily quantitative analysis of CBCT-guided patient setup registrations. The AI-model was validated against independent expert observers, and appropriate action levels were determined to minimize false positives without sacrificing sensitivity. Case studies demonstrate the potential benefits of such a pipeline to bolster quality and safety programs in radiotherapy. To the authors' knowledge, there are no previous works performing AI-assisted assessment of pre-treatment CBCT-based patient alignment.

Development and multi-institutional validation of a convolutional neural network to detect vertebral body mis-alignments in 2D x-ray setup images.

BACKGROUND: Misalignment to the incorrect vertebral body remains a rare but serious patient safety risk in image-guided radiotherapy (IGRT). PURPOSE: Our group has proposed that an automated image-review algorithm be inserted into the IGRT process as an interlock to detect off-by-one vertebral body errors. This study presents the development and multi-institutional validation of a convolutional neural network (CNN)-based approach for such an algorithm using patient image data from a planar stereoscopic x-ray IGRT system. METHODS: X-rays and digitally reconstructed radiographs (DRRs) were collected from 429 spine radiotherapy patients (1592 treatment fractions) treated at six institutions using a stereoscopic x-ray image guidance system. Clinically-applied, physician approved, alignments were used for true-negative, "no-error" cases. "Off-by-one vertebral body" errors were simulated by translating DRRs along the spinal column using a semi-automated method. A leave-one-institution-out approach was used to estimate model accuracy on data from unseen institutions as follows: All of the images from five of the institutions were used to train a CNN model from scratch using a fixed network architecture and hyper-parameters. The size of this training set ranged from 5700 to 9372 images, depending on exactly which five institutions were contributing data. The training set was randomized and split using a 75/25 split into the final training/ validation sets. X-ray/ DRR image pairs and the associated binary labels of "no-error" or "shift" were used as the model input. Model accuracy was evaluated using images from the sixth institution, which were left out of the training phase entirely. This test set ranged from 180 to 3852 images, again depending on which institution had been left out of the training phase. The trained model was used to classify the images from the test set as either "no-error" or "shifted", and the model predictions were compared to the ground truth labels to assess the model accuracy. This process was repeated until each institution's images had been used as the testing dataset. RESULTS: When the six models were used to classify unseen image pairs from the institution left out during training, the resulting receiver operating characteristic area under the curve values ranged from 0.976 to 0.998. With the specificity fixed at 99%, the corresponding sensitivities ranged from 61.9% to 99.2% (mean: 77.6%). With the specificity fixed at 95%, sensitivities ranged from 85.5% to 99.8% (mean: 92.9%). CONCLUSION: This study demonstrated the CNN-based vertebral body misalignment model is robust when applied to previously unseen test data from an outside institution, indicating that this proposed additional safeguard against misalignment is feasible.

Feasibility of a deep-learning based anatomical region labeling tool for Cone-Beam Computed Tomography scans in radiotherapy.

Background and purpose: Currently, there is no robust indicator within the Cone-Beam Computed Tomography (CBCT) DICOM headers as to which anatomical region is present on the scan. This can be a predicament to CBCT-based algorithms trained on specific body regions, such as auto-segmentation and radiomics tools used in the radiotherapy workflow. We propose an anatomical region labeling (ARL) algorithm to classify CBCT scans into four distinct regions: head & neck, thoracic-abdominal, pelvis, and extremity. Materials and methods: Algorithm training and testing was performed on 3,802 CBCT scans from 596 patients treated at our radiotherapy center. The ARL model, which consists of a convolutional neural network, makes use of a single CBCT coronal slice to output a probability of occurrence for each of the four classes. ARL was evaluated on the test dataset composed of 1,090 scans and compared to a support vector machine (SVM) model. ARL was also used to label CBCT treatment scans for 22 consecutive days as part of a proof-of-concept implementation. A validation study was performed on the first 100 unique patient scans to evaluate the functionality of the tool in the clinical setting. Results: ARL achieved an overall accuracy of 99.2% on the test dataset, outperforming the SVM (91.5% accuracy). Our validation study has shown strong agreement between the human annotations and ARL predictions, with accuracies of 99.0% for all four regions. Conclusion: The high classification accuracy demonstrated by ARL suggests that it may be employed as a pre-processing step for site-specific, CBCT-based radiotherapy tools.

Magnetic Resonance Imaging-Guided vs Computed Tomography-Guided Stereotactic Body Radiotherapy for Prostate Cancer: The MIRAGE Randomized Clinical Trial.

Importance: Magnetic resonance imaging (MRI) guidance offers multiple theoretical advantages in the context of stereotactic body radiotherapy (SBRT) for prostate cancer. However, to our knowledge, these advantages have yet to be demonstrated in a randomized clinical trial. Objective: To determine whether aggressive margin reduction with MRI guidance significantly reduces acute grade 2 or greater genitourinary (GU) toxic effects after prostate SBRT compared with computed tomography (CT) guidance. Design, Setting, and Participants: This phase 3 randomized clinical trial (MRI-Guided Stereotactic Body Radiotherapy for Prostate Cancer [MIRAGE]) enrolled men aged 18 years or older who were receiving SBRT for clinically localized prostate adenocarcinoma at a single center between May 5, 2020, and October 1, 2021. Data were analyzed from January 15, 2021, through May 15, 2022. All patients had 3 months or more of follow-up. Interventions: Patients were randomized 1:1 to SBRT with CT guidance (control arm) or MRI guidance. Planning margins of 4 mm (CT arm) and 2 mm (MRI arm) were used to deliver 40 Gy in 5 fractions. Main Outcomes and Measures: The primary end point was the incidence of acute (≤90 days after SBRT) grade 2 or greater GU toxic effects (using Common Terminology Criteria for Adverse Events, version 4.03 [CTCAE v4.03]). Secondary outcomes included CTCAE v4.03-based gastrointestinal toxic effects and International Prostate Symptom Score (IPSS)-based and Expanded Prostate Cancer Index Composite-26 (EPIC-26)-based outcomes. Results: Between May 2020 and October 2021, 156 patients were randomized: 77 to CT (median age, 71 years [IQR, 67-77 years]) and 79 to MRI (median age, 71 years [IQR, 68-75 years]). A prespecified interim futility analysis conducted after 100 patients reached 90 or more days after SBRT was performed October 1, 2021, with the sample size reestimated to 154 patients. Thus, the trial was closed to accrual early. The incidence of acute grade 2 or greater GU toxic effects was significantly lower with MRI vs CT guidance (24.4% [95% CI, 15.4%-35.4%] vs 43.4% [95% CI, 32.1%-55.3%]; P = .01), as was the incidence of acute grade 2 or greater gastrointestinal toxic effects (0.0% [95% CI, 0.0%-4.6%] vs 10.5% [95% CI, 4.7%-19.7%]; P = .003). Magnetic resonance imaging guidance was associated with a significantly smaller percentage of patients with a 15-point or greater increase in IPSS at 1 month (6.8% [5 of 72] vs 19.4% [14 of 74]; P = .01) and a significantly reduced percentage of patients with a clinically significant (≥12-point) decrease in EPIC-26 bowel scores (25.0% [17 of 68] vs 50.0% [34 of 68]; P = .001) at 1 month. Conclusions and Relevance: In this randomized clinical trial, compared with CT-guidance, MRI-guided SBRT significantly reduced both moderate acute physician-scored toxic effects and decrements in patient-reported quality of life. Longer-term follow-up will confirm whether these notable benefits persist. Trial Registration: ClinicalTrials.gov Identifier: NCT04384770.

Dosimetric evaluation of respiratory gating on a 0.35-T magnetic resonance-guided radiotherapy linac.

PURPOSE: The commercial 0.35-T magnetic resonance imaging (MRI)-guided radiotherapy vendor ViewRay recently introduced upgraded real-time imaging frame rates based on compressed sensing techniques. Furthermore, additional motion tracking algorithms were made available. Compressed sensing allows for increased image frame rates but may compromise image quality. To assess the impact of this upgrade on respiratory gating accuracy, we evaluated gated dose distributions pre- and post-upgrade using a motion phantom and radiochromic film. METHODS: Seven motion waveforms (four artificial, two patient-derived free-breathing, and one breath-holding) were used to drive an MRI-compatible motion phantom. A treatment plan was developed to deliver a 3-cm diameter spherical dose distribution typical of a stereotactic body radiotherapy plan. Gating was performed using 4-frames per second (fps) imaging pre-upgrade on the "default" tracking algorithm and 8-fps post-upgrade using the "small mobile targets" (SMT) and "large deforming targets" (LDT) tracking algorithms. Radiochromic film was placed in a moving insert within the phantom to measure dose. The planned and delivered dose distributions were compared using the gamma index with 3%/3-mm criteria. Dose-area histograms were produced to calculate the dose to 95% (D95) of the sphere planning target volume (PTV) and two simulated gross tumor volumes formed by contracting the PTV by 3 and 5 mm, respectively. RESULTS: Gamma pass rates ranged from 18% to 93% over the 21 combinations of breathing trace and gating conditions examined. D95 ranged from 206 to 514 cGy. On average, the LDT algorithm yielded lower gamma and D95 values than the default and SMT algorithms. CONCLUSION: Respiratory gating at 8 fps with the new tracking algorithms provides similar gating performance to the original algorithm with 4 fps, although the LDT algorithm had lower accuracy for our non-deformable target. This indicates that the choice of deformable image registration algorithm should be chosen deliberately based on whether the target is rigid or deforming.

Development and interinstitutional validation of an automatic vertebral-body misalignment error detector for cone-beam CT-guided radiotherapy.

BACKGROUND: In cone-beam computed tomography (CBCT)-guided radiotherapy, off-by-one vertebral-body misalignments are rare but serious errors that lead to wrong-site treatments. PURPOSE: An automatic error detection algorithm was developed that uses a three-branch convolutional neural network error detection model (EDM) to detect off-by-one vertebral-body misalignments using planning computed tomography (CT) images and setup CBCT images. METHODS: Algorithm training and test data consisted of planning CTs and CBCTs from 480 patients undergoing radiotherapy treatment in the thoracic and abdominal regions at two radiotherapy clinics. The clinically applied registration was used to derive true-negative (no error) data. The setup and planning images were then misaligned by one vertebral-body in both the superior and inferior directions, simulating the most likely misalignment scenarios. For each of the aligned and misaligned 3D image pairs, 2D slice pairs were automatically extracted in each anatomical plane about a point within the vertebral column. The three slice pairs obtained were then inputted to the EDM that returned a probability of vertebral misalignment. One model (EDM1 ) was trained solely on data from institution 1. EDM1 was further trained using a lower learning rate on a dataset from institution 2 to produce a fine-tuned model, EDM2 . Another model, EDM3 , was trained from scratch using a training dataset composed of data from both institutions. These three models were validated on a randomly selected and unseen dataset composed of images from both institutions, for a total of 303 image pairs. The model performances were quantified using a receiver operating characteristic analysis. Due to the rarity of vertebral-body misalignments in the clinic, a minimum threshold value yielding a specificity of at least 99% was selected. Using this threshold, the sensitivity was calculated for each model, on each institution's test set separately. RESULTS: When applied to the combined test set, EDM1 , EDM2 , and EDM3 resulted in an area under curve of 99.5%, 99.4%, and 99.5%, respectively. EDM1 achieved a sensitivity of 96% and 88% on Institution 1 and Institution 2 test set, respectively. EDM2 obtained a sensitivity of 95% on each institution's test set. EDM3 achieved a sensitivity of 95% and 88% on Institution 1 and Institution 2 test set, respectively. CONCLUSION: The proposed algorithm demonstrated accuracy in identifying off-by-one vertebral-body misalignments in CBCT-guided radiotherapy that was sufficiently high to allow for practical implementation. It was found that fine-tuning the model on a multi-facility dataset can further enhance the generalizability of the algorithm.

Barriers and facilitators to clinical implementation of radiotherapy treatment planning automation: A survey study of medical dosimetrists.

PURPOSE: Little is known about the scale of clinical implementation of automated treatment planning techniques in the United States. In this work, we examine the barriers and facilitators to adoption of commercially available automated planning tools into the clinical workflow using a survey of medical dosimetrists. METHODS/MATERIALS: Survey questions were developed based on a literature review of automation research and cognitive interviews of medical dosimetrists at our institution. Treatment planning automation was defined to include auto-contouring and automated treatment planning. Survey questions probed frequency of use, positive and negative perceptions, potential implementation changes, and demographic and institutional descriptive statistics. The survey sample was identified using both a LinkedIn search and referral requests sent to physics directors and senior physicists at 34 radiotherapy clinics in our state. The survey was active from August 2020 to April 2021. RESULTS: Thirty-four responses were collected out of 59 surveys sent. Three categories of barriers to use of automation were identified. The first related to perceptions of limited accuracy and usability of the algorithms. Eighty-eight percent of respondents reported that auto-contouring inaccuracy limited its use, and 62% thought it was difficult to modify an automated plan, thus limiting its usefulness. The second barrier relates to the perception that automation increases the probability of an error reaching the patient. Third, respondents were concerned that automation will make their jobs less satisfying and less secure. Large majorities reported that they enjoyed plan optimization, would not want to lose that part of their job, and expressed explicit job security fears. CONCLUSION: To our knowledge this is the first systematic investigation into the views of automation by medical dosimetrists. Potential barriers and facilitators to use were explicitly identified. This investigation highlights several concrete approaches that could potentially increase the translation of automation into the clinic, along with areas of needed research.

Offline generator for digitally reconstructed radiographs of a commercial stereoscopic radiotherapy image-guidance system.

PURPOSE: Image-guided radiotherapy (IGRT) research sometimes involves simulated changes to patient positioning using retrospectively collected clinical data. For example, researchers may simulate patient misalignments to develop error detection algorithms or positioning optimization algorithms. The Brainlab ExacTrac system can be used to retrospectively "replay" simulated alignment scenarios but does not allow export of digitally reconstructed radiographs (DRRs) with simulated positioning variations for further analysis. Here we describe methods to overcome this limitation and replicate ExacTrac system DRRs by using projective geometry parameters contained in the ExacTrac configuration files saved for every imaged subject. METHODS: Two ExacTrac DRR generators were implemented, one with custom MATLAB software based on first principles, and the other using libraries from the Insight Segmentation and Registration Toolkit (ITK). A description of perspective projections for DRR rendering applications is included, with emphasis on linear operators in real projective space P 3 ${\mathbb{P}^3}$ . We provide a general methodology for the extraction of relevant geometric values needed to replicate ExacTrac DRRs. Our generators were tested on phantom and patient images, both acquired in a known treatment position. We demonstrate the validity of our methods by comparing our generated DRRs to reference DRRs produced by the ExacTrac system during a treatment workflow using a manual landmark analysis as well as rigid registration with the elastix software package. RESULTS: Manual landmarks selected between the corresponding DRR generators across patient and phantom images have an average displacement of 1.15 mm. For elastix image registrations, we found that absolute value vertical and horizontal translations were 0.18 and 0.35 mm on average, respectively. Rigid rotations were within 0.002 degrees. CONCLUSION: Custom and ITK-based algorithms successfully reproduce ExacTrac DRRs and have the distinctive advantage of incorporating any desired 6D couch position. An open-source repository is provided separately for users to implement in IGRT patient positioning research.

Ablative radiotherapy for liver tumors using stereotactic MRI-guidance: A prospective phase I trial.

BACKGROUND AND PURPOSE: To prospectively determine the feasibility, safety, and efficacy of stereotactic body radiation therapy (SBRT) to primary and secondary liver tumors with MR-guided radiation therapy (MRgRT). MATERIALS AND METHODS: Treatment plans with a conventional CT-guided linear accelerator and a MRI-guided tri-60Co teletherapy unit (MR-Co) were generated and compared for patients undergoing liver-directed SBRT from 2015 to 2017. If dosimetric parameters were met on MR-Co, patients were treated with MRgRT. The highest priority constraint was >1000 cc or >800 cc of normal liver receiving <15 Gy for single- or multiple-lesion treatments, respectively. Treatment was delivered every other day. RESULTS: Of 23 patients screened, 20 patients (8 primary, 12 secondary) and 25 liver tumors underwent MR-guided SBRT to a median dose of 54 Gy (range 11.5-60) in a median of 3 fractions (range 1-5). With a median follow up of 18.9 months, the 1- and 2-year estimate of local control were 94.7% and 79.6%, respectively. A difference in local control between single and multiple lesions or BED ≥ 100 Gy10 and BED < 100 Gy10, respectively, was observed. The 2-year estimate of overall survival (OS) was 50.7% with a median OS of 29 months. There were no acute grade ≥ 3 toxicities and one late grade 3/4 toxicity from a single patient whose plan exceeded an unrecognized dose constraint at the time. CONCLUSION: MR-guided SBRT is a viable and safe option in the delivery of ultrahypofractionated ablative radiation treatment to primary and secondary liver tumors resulting in high rates of local control and very favorable toxicity profiles.

Machine-assisted interpolation algorithm for semi-automated segmentation of highly deformable organs.

PURPOSE: Accurate and robust auto-segmentation of highly deformable organs (HDOs), for example, stomach or bowel, remains an outstanding problem due to these organs' frequent and large anatomical variations. Yet, time-consuming manual segmentation of these organs presents a particular challenge to time-limited modern radiotherapy techniques such as on-line adaptive radiotherapy and high-dose-rate brachytherapy. We propose a machine-assisted interpolation (MAI) that uses prior information in the form of sparse manual delineations to facilitate rapid, accurate segmentation of the stomach from low field magnetic resonance images (MRI) and the bowel from computed tomography (CT) images. METHODS: Stomach MR images from 116 patients undergoing 0.35T MRI-guided abdominal radiotherapy and bowel CT images from 120 patients undergoing high dose rate pelvic brachytherapy treatment were collected. For each patient volume, the manual delineation of the HDO was extracted from every 8th slice. These manually drawn contours were first interpolated to obtain an initial estimate of the HDO contour. A two-channel 64 × 64 pixel patch-based convolutional neural network (CNN) was trained to localize the position of the organ's boundary on each slice within a five-pixel wide road using the image and interpolated contour estimate. This boundary prediction was then input, in conjunction with the image, to an organ closing CNN which output the final organ segmentation. A Dense-UNet architecture was used for both networks. The MAI algorithm was separately trained for the stomach segmentation and the bowel segmentation. Algorithm performance was compared against linear interpolation (LI) alone and against fully automated segmentation (FAS) using a Dense-UNet trained on the same datasets. The Dice Similarity Coefficient (DSC) and mean surface distance (MSD) metrics were used to compare the predictions from the three methods. Statistically significance was tested using Student's t test. RESULTS: For the stomach segmentation, the mean DSC from MAI (0.91 ± 0.02) was 5.0% and 10.0% higher as compared to LI and FAS, respectively. The average MSD from MAI (0.77 ± 0.25 mm) was 0.54 and 3.19 mm lower compared to the two other methods. Only 7% of MAI stomach predictions resulted in a DSC < 0.8, as compared to 30% and 28% for LI and FAS, respectively. For the bowel segmentation, the mean DSC of MAI (0.90 ± 0.04) was 6% and 18% higher, and the average MSD of MAI (0.93 ± 0.48 mm) was 0.42 and 4.9 mm lower as compared to LI and FAS. Sixteen percent of the predicted contour from MAI resulted in a DSC < 0.8, as compared to 46% and 60% for FAS and LI, respectively. All comparisons between MAI and the baseline methods were found to be statistically significant (p-value < 0.001). CONCLUSIONS: The proposed MAI algorithm significantly outperformed LI in terms of accuracy and robustness for both stomach segmentation from low-field MRIs and bowel segmentation from CT images. At this time, FAS methods for HDOs still require significant manual editing. Therefore, we believe that the MAI algorithm has the potential to expedite the process of HDO delineation within the radiation therapy workflow.

Clinical assessment of geometric distortion for a 0.35T MR-guided radiotherapy system.

PURPOSE: To estimate the overall spatial distortion on clinical patient images for a 0.35 T MR-guided radiotherapy system. METHODS: Ten patients with head-and-neck cancer underwent CT and MR simulations with identical immobilization. The MR images underwent the standard systematic distortion correction post-processing. The images were rigidly registered and landmark-based analysis was performed by an anatomical expert. Distortion was quantified using Euclidean distance between each landmark pair and tagged by tissue interface: bone-tissue, soft tissue, or air-tissue. For baseline comparisons, an anthropomorphic phantom was imaged and analyzed. RESULTS: The average spatial discrepancy between CT and MR landmarks was 1.15 ± 1.14 mm for the phantom and 1.46 ± 1.78 mm for patients. The error histogram peaked at 0-1 mm. 66% of the discrepancies were <2 mm and 51% <1 mm. In the patient data, statistically significant differences (p-values < 0.0001) were found between the different tissue interfaces with averages of 0.88 ± 1.24 mm, 2.01 ± 2.20 mm, and 1.41 ± 1.56 mm for the air/tissue, bone/tissue, and soft tissue, respectively. The distortion generally correlated with the in-plane radial distance from the image center along the longitudinal axis of the MR. CONCLUSION: Spatial distortion remains in the MR images after systematic distortion corrections. Although the average errors were relatively small, large distortions observed at bone/tissue interfaces emphasize the need for quantitative methods for assessing and correcting patient-specific spatial distortions.

Magnetic resonance imaging-guided stereotactic body radiotherapy for prostate cancer (mirage): a phase iii randomized trial.

BACKGROUND: Stereotactic body radiotherapy (SBRT) is becoming increasingly used in treating localized prostate cancer (PCa), with evidence showing similar toxicity and efficacy profiles when compared with longer courses of definitive radiation. Magnetic resonance imaging (MRI)-guided radiotherapy has multiple potential advantages over standard computed tomography (CT)-guided radiotherapy, including enhanced prostate visualization (abrogating the need for fiducials and MRI fusion), enhanced identification of the urethra, the ability to track the prostate in real-time, and the capacity to perform online adaptive planning. However, it is unknown whether these potential advantages translate into improved outcomes. This phase III randomized superiority trial is designed to prospectively evaluate whether toxicity is lower after MRI-guided versus CT-guided SBRT. METHODS: Three hundred men with localized PCa will be randomized in a 1:1 ratio to SBRT using CT or MRI guidance. Randomization will be stratified by baseline International Prostate Symptom Score (IPSS) (≤15 or > 15) and prostate gland volume (≤50 cc or > 50 cc). Five fractions of 8 Gy will be delivered to the prostate over the course of fourteen days, with or without hormonal therapy and elective nodal radiotherapy (to a dose of 5 Gy per fraction) as per the investigator's discretion. The primary endpoint is the incidence of physician-reported acute grade ≥ 2 genitourinary (GU) toxicity (during the first 90 days after SBRT), as assessed by the CTCAE version 4.03 scale. Secondary clinical endpoints include incidence of acute grade ≥ 2 gastrointestinal (GI) toxicity, 5-year cumulative incidences of physician-reported late grade ≥ 2 GU and GI toxicity, temporal changes in patient-reported quality of life (QOL) outcomes, 5-year biochemical recurrence-free survival and the proportion of fractions of MRI-guided SBRT in which online adaptive radiotherapy is used. DISCUSSION: The MIRAGE trial is the first randomized trial comparing MRI-guided with standard CT-guided SBRT for localized PCa. The primary hypothesis is that MRI-guided SBRT will lead to an improvement in the cumulative incidence of acute grade ≥ 2 GU toxicity when compared to CT-guided SBRT. The pragmatic superiority design focused on an acute toxicity endpoint will allow an early comparison of the two technologies. TRIAL REGISTRATION: Clinicaltrials.gov identifier: NCT04384770. Date of registration: May 12, 2020. https://clinicaltrials.gov/ct2/show/NCT04384770 PROTOCOL VERSION: Version 2.1, Aug 28, 2020.

Dosimetric Quality of Online Adapted Pancreatic Cancer Treatment Plans on an MRI-Guided Radiation Therapy System.

PURPOSE: Stereotactic magnetic resonance image-guided adaptive radiation therapy (SMART) is an emerging technique that shows promise in the treatment of pancreatic cancer and other abdominopelvic malignancies. However, it is unknown whether the time-limited nature of on-table adaptive planning may result in dosimetrically suboptimal plans. The purpose of this study was to quantitatively address that question through systemic retrospective replanning of treated on-table adaptive pancreatic cancer cases. METHODS AND MATERIALS: Of 74 consecutive adapted fractions, 30 were retrospectively replanned based on deficiencies in planning target volume (PTV) and gross tumor volume (GTV) coverage or doses to organs-at-risk (OARs) that exceeded ideal constraints. Retrospective plans were created by adjusting dose-volume objectives in an iterative fashion until deemed optimized. The goal of replanning was to improve PTV/GTV coverage while keeping the dose to gastrointestinal OARs the same or lower or to reduce OAR doses while keeping PTV coverage the same or higher. The global maximum dose was required to be maintained within 2% of that of the treated adaptive plan to eliminate it as a confounding factor. A threshold of 5% improvement in PTV coverage or 5% decrease in OAR dose was used to define a clinically significant improvement. RESULTS: Of the 30 replans, 7 obtained at least 5% PTV coverage improvement. The average increase in PTV coverage for these plans was 11%. No plans were clinically significantly improved in terms of OAR sparing. Changes in beam-on time did not show any correlation. Statistical analysis via a linear mixed-effects model with a nested random effect suggested that both GTV and PTV coverage were improved over SMART process plans by 0.91 cc (P = .02) and 2.03 cc (P < .001), respectively. CONCLUSIONS: Dosimetric plan quality of at least 10% of SMART fractions may be improved through more extensive replanning than is currently performed on-table. Further work is needed to develop an automated replanning workflow to streamline the in-depth replanning process to better fit into an on-table adaptive workflow.