Search

Recent advancements in machine learning have led to novel imaging systems and algorithms that address ill-posed problems. Assessing their trustworthiness and understanding how to deploy them safely at test time remains an important and open problem. We propose a method that leverages conformal prediction to retrieve upper/lower bounds and statistical inliers/outliers of reconstructions based on the prediction intervals of downstream metrics. We apply our method to sparse-view CT for downstream radiotherapy planning and show 1) that metric-guided bounds have valid coverage for downstream metrics while conventional pixel-wise bounds do not and 2) anatomical differences of upper/lower bounds between metric-guided and pixel-wise methods. Our work paves the way for more meaningful reconstruction bounds. Code available at https://github.com/matthewyccheung/conformal-metric

PURPOSE: The Ocean Road Cancer Institute (ORCI) in Tanzania began offering 3D conformal radiation therapy (3DCRT) in 2018. Steep learning curves, high patient volume, and a limited workforce resulted in long radiation therapy (RT) planning workflows. We aimed to establish the feasibility of implementing an automation-assisted cervical cancer 3DCRT planning system. MATERIALS AND METHODS: We performed chart abstractions on 30 patients with cervical cancer treated with 3DCRT at ORCI. The Radiation Planning Assistant (RPA) generated a new automated set of contours and plans on the basis of anonymized computed tomography images. Each were assessed for edit time requirements, dose-volume safety metrics, and clinical acceptability by two ORCI physician investigators. Dice similarity coefficient (DSC) agreement analysis was conducted between original and new contour sets. RESULTS: The average time to manually develop treatment plans was 7 days. Applying RPA, automated same-day contours and plans were developed for 29 of 30 patients (97%). Of the 29 evaluable contours, all were approved with <2 minutes of edit time. Agreement between clinical and RPA contours was highest for the rectum (median DSC, 0.72) and bladder (DSC, 0.90). Agreement was lower with the primary tumor clinical target volume (CTVp; DSC, 0.69) and elective nodal clinical target volume (CTVn; DSC, 0.63). All RPA plans were approved with <4 minutes of edit time. RPA target coverage was excellent, covering the CTVp with median V45 Gy 100% and CTVn with median V45 Gy 99.9%. CONCLUSION: Automation-assisted 3DCRT contouring yielded high levels of agreement for normal structures. The RPA met all planning safety metrics and sustained high levels of clinical acceptability with minimal edit times. This tool offers the potential to significantly decrease RT planning timelines while maintaining high-quality RT delivery in resource-constrained settings.

CT scans are the standard-of-care for many clinical ailments, and are needed for treatments like external beam radiotherapy. Unfortunately, CT scanners are rare in low and mid-resource settings due to their costs. Planar X-ray radiography units, in comparison, are far more prevalent, but can only provide limited 2D observations of the 3D anatomy. In this work, we propose a method to generate CT volumes from few (<5) planar X-ray observations using a prior data distribution, and perform the first evaluation of such a reconstruction algorithm for a clinical application: radiotherapy planning. We propose a deep generative model, building on advances in neural implicit representations to synthesize volumetric CT scans from few input planar X-ray images at different angles. To focus the generation task on clinically-relevant features, our model can also leverage anatomical guidance during training (via segmentation masks). We generated 2-field opposed, palliative radiotherapy plans on thoracic CTs reconstructed by our method, and found that isocenter radiation dose on reconstructed scans have <1% error with respect to the dose calculated on clinically acquired CTs using <=4 X-ray views. In addition, our method is better than recent sparse CT reconstruction baselines in terms of standard pixel and structure-level metrics (PSNR, SSIM, Dice score) on the public LIDC lung CT dataset. Code is available at: https://github.com/wanderinrain/Xray2CT., Comment: 10 pages, 5 figures

Manually delineating upper abdominal organs at risk (OARs) is a time-consuming task. To develop a deep-learning-based tool for accurate and robust auto-segmentation of these OARs, forty pancreatic cancer patients with contrast-enhanced breath-hold computed tomographic (CT) images were selected. We trained a three-dimensional (3D) U-Net ensemble that automatically segments all organ contours concurrently with the self-configuring nnU-Net framework. Our tool's performance was assessed on a held-out test set of 30 patients quantitatively. Five radiation oncologists from three different institutions assessed the performance of the tool using a 5-point Likert scale on an additional 75 randomly selected test patients. The mean (± std. dev.) Dice similarity coefficient values between the automatic segmentation and the ground truth on contrast-enhanced CT images were 0.80 ± 0.08, 0.89 ± 0.05, 0.90 ± 0.06, 0.92 ± 0.03, 0.96 ± 0.01, 0.97 ± 0.01, 0.96 ± 0.01, and 0.96 ± 0.01 for the duodenum, small bowel, large bowel, stomach, liver, spleen, right kidney, and left kidney, respectively. 89.3% (contrast-enhanced) and 85.3% (non-contrast-enhanced) of duodenum contours were scored as a 3 or above, which required only minor edits. More than 90% of the other organs' contours were scored as a 3 or above. Our tool achieved a high level of clinical acceptability with a small training dataset and provides accurate contours for treatment planning.

To develop an automated workflow for rectal cancer three-dimensional conformal radiotherapy treatment planning that combines deep-learning(DL) aperture predictions and forward-planning algorithms. We designed an algorithm to automate the clinical workflow for planning with field-in-field. DL models were trained, validated, and tested on 555 patients to automatically generate aperture shapes for primary and boost fields. Network inputs were digitally reconstructed radiography, gross tumor volume(GTV), and nodal GTV. A physician scored each aperture for 20 patients on a 5-point scale(>3 acceptable). A planning algorithm was then developed to create a homogeneous dose using a combination of wedges and subfields. The algorithm iteratively identifies a hotspot volume, creates a subfield, and optimizes beam weight all without user intervention. The algorithm was tested on 20 patients using clinical apertures with different settings, and the resulting plans(4 plans/patient) were scored by a physician. The end-to-end workflow was tested and scored by a physician on 39 patients using DL-generated apertures and planning algorithms. The predicted apertures had Dice scores of 0.95, 0.94, and 0.90 for posterior-anterior, laterals, and boost fields, respectively. 100%, 95%, and 87.5% of the posterior-anterior, laterals, and boost apertures were scored as clinically acceptable, respectively. Wedged and non-wedged plans were clinically acceptable for 85% and 50% of patients, respectively. The final plans hotspot dose percentage was reduced from 121%($\pm$ 14%) to 109%($\pm$ 5%) of prescription dose. The integrated end-to-end workflow of automatically generated apertures and optimized field-in-field planning gave clinically acceptable plans for 38/39(97%) of patients. We have successfully automated the clinical workflow for generating radiotherapy plans for rectal cancer for our institution.

PurposeThe purpose of this study was to develop and test a set of illustrated instructions for effective training for mechanical quality assurance (QA) of medical linear accelerators (linac).MethodsIllustrated instructions were created for mechanical QA and underwent several steps of review, testing, and refinement. Eleven testers with no recent QA experience were then recruited from our radiotherapy department (one student, two computational scientists, and eight dosimetrists). This group was selected because they have experience of radiation therapy but no preconceived ideas about how to do QA. The following parameters were progressively decalibrated on a Varian C-series linac: Group A = gantry angle, ceiling laser position, X1 jaw position, couch longitudinal position, physical graticule position (five testers); Group B = Group A + wall laser position, couch lateral and vertical position, collimator angle (three testers); Group C = Group B + couch angle, wall laser angle, and optical distance indicator (three testers). Testers were taught how to use the linac and then used the instructions to try to identify these errors. An experienced physicist observed each session, giving support on machine operation as necessary.ResultsTesters were able to follow the instructions. They determined gantry, collimator, and couch angle errors within 0.4°, 0.3°, and 0.9° of the actual changed values, respectively. Laser positions were determined within 1 mm and jaw positions within 2 mm. Couch position errors were determined within 2 mm and 3 mm for lateral/longitudinal and vertical errors, respectively. Accessory-positioning errors were determined within 1 mm. Optical distance indicator errors were determined within 2 mm when comparing with distance sticks and 6 mm when using blocks, indicating that distance sticks should be the preferred approach for inexperienced staff.ConclusionsInexperienced

Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision-support systems for diagnosis, surgery planning, and population-based analysis on spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms towards labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel-level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the the results of this evaluation and further investigate the performance-variation at vertebra-level, scan-level, and at different fields-of-view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The content and code concerning VerSe can be accessed at: https://github.com/anjany/verse., Comment: Challenge report for the VerSe 2019 and 2020. Published in Medical Image Analysis (DOI: https://doi.org/10.1016/j.media.2021.102166)

Aluminum oxide based optically stimulated luminescent dosimeters (OSLD) have been recognized as a useful dosimeter for measuring CT dose, particularly for patient dose measurements. Despite the increasing use of this dosimeter, appropriate dosimeter calibration techniques have not been established in the literature; while the manufacturer offers a calibration procedure, it is known to have relatively large uncertainties. The purpose of this work was to evaluate two clinical approaches for calibrating these dosimeters for CT applications, and to determine the uncertainty associated with measurements using these techniques. Three unique calibration procedures were used to calculate dose for a range of CT conditions using a commercially available OSLD and reader. The three calibration procedures included calibration (a) using the vendor-provided method, (b) relative to a 120 kVp CT spectrum in air, and (c) relative to a megavoltage beam (implemented with 60 Co). The dose measured using each of these approaches was compared to dose measured using a calibrated farmer-type ion chamber. Finally, the uncertainty in the dose measured using each approach was determined. For the CT and megavoltage calibration methods, the dose measured using the OSLD nanoDot was within 5% of the dose measured using an ion chamber for a wide range of different CT scan parameters (80-140 kVp, and with measurements at a range of positions). When calibrated using the vendor-recommended protocol, the OSLD measured doses were on average 15.5% lower than ion chamber doses. Two clinical calibration techniques have been evaluated and are presented in this work as alternatives to the vendor-provided calibration approach. These techniques provide high precision for OSLD-based measurements in a CT environment.

Aluminum oxide based optically stimulated luminescent dosimeters (OSLD) have been recognized as a useful dosimeter for measuring CT dose, particularly for patient dose measurements. Despite the increasing use of this dosimeter, appropriate dosimeter calibration techniques have not been established in the literature; while the manufacturer offers a calibration procedure, it is known to have relatively large uncertainties. The purpose of this work was to evaluate two clinical approaches for calibrating these dosimeters for CT applications, and to determine the uncertainty associated with measurements using these techniques. Three unique calibration procedures were used to calculate dose for a range of CT conditions using a commercially available OSLD and reader. The three calibration procedures included calibration (a) using the vendor-provided method, (b) relative to a 120 kVp CT spectrum in air, and (c) relative to a megavoltage beam (implemented with 60 Co). The dose measured using each of these approaches was compared to dose measured using a calibrated farmer-type ion chamber. Finally, the uncertainty in the dose measured using each approach was determined. For the CT and megavoltage calibration methods, the dose measured using the OSLD nanoDot was within 5% of the dose measured using an ion chamber for a wide range of different CT scan parameters (80-140 kVp, and with measurements at a range of positions). When calibrated using the vendor-recommended protocol, the OSLD measured doses were on average 15.5% lower than ion chamber doses. Two clinical calibration techniques have been evaluated and are presented in this work as alternatives to the vendor-provided calibration approach. These techniques provide high precision for OSLD-based measurements in a CT environment.

PURPOSE:Magnetic fields are known to alter radiation dose deposition. Before patients receive treatment using an MRI-linear accelerator (MRI-Linac), preclinical studies are needed to understand the biological consequences of magnetic-field-induced dose effects. In the present study, the authors sought to identify a beam energy and magnetic field strength combination suitable for preclinical murine experiments. METHODS:Magnetic field dose effects were simulated in a mouse lung phantom using various beam energies (225 kVp, 350 kVp, 662 keV [Cs-137], 2 MV, and 1.25 MeV [Co-60]) and magnetic field strengths (0.75, 1.5, and 3 T). The resulting dose distributions were compared with those in a simulated human lung phantom irradiated with a 6 or 8 MV beam and orthogonal 1.5 T magnetic field. RESULTS:In the human lung phantom, the authors observed a dose increase of 45% and 54% at the soft-tissue-to-lung interface and a dose decrease of 41% and 48% at the lung-to-soft-tissue interface for the 6 and 8 MV beams, respectively. In the mouse simulations, the magnetic fields had no measurable effect on the 225 or 350 kVp dose distribution. The dose increases with the Cs-137 beam for the 0.75, 1.5, and 3 T magnetic fields were 9%, 29%, and 42%, respectively. The dose decreases were 9%, 21%, and 37%. For the 2 MV beam, the dose increases were 16%, 33%, and 31% and the dose decreases were 9%, 19%, and 30%. For the Co-60 beam, the dose increases were 19%, 54%, and 44%, and the dose decreases were 19%, 42%, and 40%. CONCLUSIONS:The magnetic field dose effects in the mouse phantom using a Cs-137, 3 T combination or a Co-60, 1.5 or 3 T combination most closely resemble those in simulated human treatments with a 6 MV, 1.5 T MRI-Linac. The effects with a Co-60, 1.5 T combination most closely resemble those in simulated human treatments with an 8 MV, 1.5 T MRI-Linac.

PurposeThe extensive use of computed tomography (CT) in diagnostic procedures is accompanied by a growing need for more accurate and patient-specific dosimetry techniques. Optically stimulated luminescent dosimeters (OSLDs) offer a potential solution for patient-specific CT point-based surface dosimetry by measuring air kerma. The purpose of this work was to characterize the OSLD nanoDot for CT dosimetry, quantifying necessary correction factors, and evaluating the uncertainty of these factors.MethodsA characterization of the Landauer OSL nanoDot (Landauer, Inc., Greenwood, IL) was conducted using both measurements and theoretical approaches in a CT environment. The effects of signal depletion, signal fading, dose linearity, and angular dependence were characterized through direct measurement for CT energies (80-140 kV) and delivered doses ranging from ∼5 to >1000 mGy. Energy dependence as a function of scan parameters was evaluated using two independent approaches: direct measurement and a theoretical approach based on Burlin cavity theory and Monte Carlo simulated spectra. This beam-quality dependence was evaluated for a range of CT scanning parameters.ResultsCorrection factors for the dosimeter response in terms of signal fading, dose linearity, and angular dependence were found to be small for most measurement conditions (<3%). The relative uncertainty was determined for each factor and reported at the two-sigma level. Differences in irradiation geometry (rotational versus static) resulted in a difference in dosimeter signal of 3% on average. Beam quality varied with scan parameters and necessitated the largest correction factor, ranging from 0.80 to 1.15 relative to a calibration performed in air using a 120 kV beam. Good agreement was found between the theoretical and measurement approaches.ConclusionsCorrection factors for the measurement of air kerma were generally small for CT dosimetry, although angular effects, and particularly effects due to change

PurposeThe extensive use of computed tomography (CT) in diagnostic procedures is accompanied by a growing need for more accurate and patient-specific dosimetry techniques. Optically stimulated luminescent dosimeters (OSLDs) offer a potential solution for patient-specific CT point-based surface dosimetry by measuring air kerma. The purpose of this work was to characterize the OSLD nanoDot for CT dosimetry, quantifying necessary correction factors, and evaluating the uncertainty of these factors.MethodsA characterization of the Landauer OSL nanoDot (Landauer, Inc., Greenwood, IL) was conducted using both measurements and theoretical approaches in a CT environment. The effects of signal depletion, signal fading, dose linearity, and angular dependence were characterized through direct measurement for CT energies (80-140 kV) and delivered doses ranging from ∼5 to >1000 mGy. Energy dependence as a function of scan parameters was evaluated using two independent approaches: direct measurement and a theoretical approach based on Burlin cavity theory and Monte Carlo simulated spectra. This beam-quality dependence was evaluated for a range of CT scanning parameters.ResultsCorrection factors for the dosimeter response in terms of signal fading, dose linearity, and angular dependence were found to be small for most measurement conditions (<3%). The relative uncertainty was determined for each factor and reported at the two-sigma level. Differences in irradiation geometry (rotational versus static) resulted in a difference in dosimeter signal of 3% on average. Beam quality varied with scan parameters and necessitated the largest correction factor, ranging from 0.80 to 1.15 relative to a calibration performed in air using a 120 kV beam. Good agreement was found between the theoretical and measurement approaches.ConclusionsCorrection factors for the measurement of air kerma were generally small for CT dosimetry, although angular effects, and particularly effects due to change

PURPOSE:Magnetic fields are known to alter radiation dose deposition. Before patients receive treatment using an MRI-linear accelerator (MRI-Linac), preclinical studies are needed to understand the biological consequences of magnetic-field-induced dose effects. In the present study, the authors sought to identify a beam energy and magnetic field strength combination suitable for preclinical murine experiments. METHODS:Magnetic field dose effects were simulated in a mouse lung phantom using various beam energies (225 kVp, 350 kVp, 662 keV [Cs-137], 2 MV, and 1.25 MeV [Co-60]) and magnetic field strengths (0.75, 1.5, and 3 T). The resulting dose distributions were compared with those in a simulated human lung phantom irradiated with a 6 or 8 MV beam and orthogonal 1.5 T magnetic field. RESULTS:In the human lung phantom, the authors observed a dose increase of 45% and 54% at the soft-tissue-to-lung interface and a dose decrease of 41% and 48% at the lung-to-soft-tissue interface for the 6 and 8 MV beams, respectively. In the mouse simulations, the magnetic fields had no measurable effect on the 225 or 350 kVp dose distribution. The dose increases with the Cs-137 beam for the 0.75, 1.5, and 3 T magnetic fields were 9%, 29%, and 42%, respectively. The dose decreases were 9%, 21%, and 37%. For the 2 MV beam, the dose increases were 16%, 33%, and 31% and the dose decreases were 9%, 19%, and 30%. For the Co-60 beam, the dose increases were 19%, 54%, and 44%, and the dose decreases were 19%, 42%, and 40%. CONCLUSIONS:The magnetic field dose effects in the mouse phantom using a Cs-137, 3 T combination or a Co-60, 1.5 or 3 T combination most closely resemble those in simulated human treatments with a 6 MV, 1.5 T MRI-Linac. The effects with a Co-60, 1.5 T combination most closely resemble those in simulated human treatments with an 8 MV, 1.5 T MRI-Linac.

Larynx may alternatively serve as a target or organs at risk (OAR) in head and neck cancer (HNC) image-guided radiotherapy (IGRT). The objective of this study was to estimate IGRT parameters required for larynx positional error independent of isocentric alignment and suggest population-based compensatory margins. Ten HNC patients receiving radiotherapy (RT) with daily CT on-rails imaging were assessed. Seven landmark points were placed on each daily scan. Taking the most superior-anterior point of the C5 vertebra as a reference isocenter for each scan, residual displacement vectors to the other six points were calculated postisocentric alignment. Subsequently, using the first scan as a reference, the magnitude of vector differences for all six points for all scans over the course of treatment was calculated. Residual systematic and random error and the necessary compensatory CTV-to-PTV and OAR-to-PRV margins were calculated, using both observational cohort data and a bootstrap-resampled population estimator. The grand mean displacements for all anatomical points was 5.07 mm, with mean systematic error of 1.1 mm and mean random setup error of 2.63 mm, while bootstrapped POIs grand mean displacement was 5.09 mm, with mean systematic error of 1.23 mm and mean random setup error of 2.61 mm. Required margin for CTV-PTV expansion was 4.6 mm for all cohort points, while the bootstrap estimator of the equivalent margin was 4.9 mm. The calculated OAR-to-PRV expansion for the observed residual setup error was 2.7 mm and bootstrap estimated expansion of 2.9 mm. We conclude that the interfractional larynx setup error is a significant source of RT setup/delivery error in HNC, both when the larynx is considered as a CTV or OAR. We estimate the need for a uniform expansion of 5 mm to compensate for setup error if the larynx is a target, or 3 mm if the larynx is an OAR, when using a nonlaryngeal bony isocenter.

Larynx may alternatively serve as a target or organs at risk (OAR) in head and neck cancer (HNC) image-guided radiotherapy (IGRT). The objective of this study was to estimate IGRT parameters required for larynx positional error independent of isocentric alignment and suggest population-based compensatory margins. Ten HNC patients receiving radiotherapy (RT) with daily CT on-rails imaging were assessed. Seven landmark points were placed on each daily scan. Taking the most superior-anterior point of the C5 vertebra as a reference isocenter for each scan, residual displacement vectors to the other six points were calculated postisocentric alignment. Subsequently, using the first scan as a reference, the magnitude of vector differences for all six points for all scans over the course of treatment was calculated. Residual systematic and random error and the necessary compensatory CTV-to-PTV and OAR-to-PRV margins were calculated, using both observational cohort data and a bootstrap-resampled population estimator. The grand mean displacements for all anatomical points was 5.07 mm, with mean systematic error of 1.1 mm and mean random setup error of 2.63 mm, while bootstrapped POIs grand mean displacement was 5.09 mm, with mean systematic error of 1.23 mm and mean random setup error of 2.61 mm. Required margin for CTV-PTV expansion was 4.6 mm for all cohort points, while the bootstrap estimator of the equivalent margin was 4.9 mm. The calculated OAR-to-PRV expansion for the observed residual setup error was 2.7 mm and bootstrap estimated expansion of 2.9 mm. We conclude that the interfractional larynx setup error is a significant source of RT setup/delivery error in HNC, both when the larynx is considered as a CTV or OAR. We estimate the need for a uniform expansion of 5 mm to compensate for setup error if the larynx is a target, or 3 mm if the larynx is an OAR, when using a nonlaryngeal bony isocenter.