A deep learning approach to remove contrast from contrast-enhanced CT for proton dose calculation.

PURPOSE: Non-Contrast Enhanced CT (NCECT) is normally required for proton dose calculation while Contrast Enhanced CT (CECT) is often scanned for tumor and organ delineation. Possible tissue motion between these two CTs raises dosimetry uncertainties, especially for moving tumors in the thorax and abdomen. Here we report a deep-learning approach to generate NCECT directly from CECT. This method could be useful to avoid the NCECT scan, reduce CT simulation time and imaging dose, and decrease the uncertainties caused by tissue motion between otherwise two different CT scans. METHODS: A deep network was developed to convert CECT to NCECT. The network receives a 3D image from CECT images as input and generates a corresponding contrast-removed NCECT image patch. Abdominal CECT and NCECT image pairs of 20 patients were deformably registered and 8000 image patch pairs extracted from the registered image pairs were utilized to train and test the model. CTs of clinical proton patients and their treatment plans were employed to evaluate the dosimetric impact of using the generated NCECT for proton dose calculation. RESULTS: Our approach achieved a Cosine Similarity score of 0.988 and an MSE value of 0.002. A quantitative comparison of clinical proton dose plans computed on the CECT and the generated NCECT for five proton patients revealed significant dose differences at the distal of beam paths. V100% of PTV and GTV changed by 3.5% and 5.5%, respectively. The mean HU difference for all five patients between the generated and the scanned NCECTs was ∼4.72, whereas the difference between CECT and the scanned NCECT was ∼64.52, indicating a ∼93% reduction in mean HU difference. CONCLUSIONS: A deep learning approach was developed to generate NCECTs from CECTs. This approach could be useful for the proton dose calculation to reduce uncertainties caused by tissue motion between CECT and NCECT.

Technical note: Minimizing CIED artifacts on a 0.35 T MRI-Linac using deep learning.

BACKGROUND: Artifacts from implantable cardioverter defibrillators (ICDs) are a challenge to magnetic resonance imaging (MRI)-guided radiotherapy (MRgRT). PURPOSE: This study tested an unsupervised generative adversarial network to mitigate ICD artifacts in balanced steady-state free precession (bSSFP) cine MRIs and improve image quality and tracking performance for MRgRT. METHODS: Fourteen healthy volunteers (Group A) were scanned on a 0.35 T MRI-Linac with and without an MR conditional ICD taped to their left pectoral to simulate an implanted ICD. bSSFP MRI data from 12 of the volunteers were used to train a CycleGAN model to reduce ICD artifacts. The data from the remaining two volunteers were used for testing. In addition, the dataset was reorganized three times using a Leave-One-Out scheme. Tracking metrics [Dice similarity coefficient (DSC), target registration error (TRE), and 95 percentile Hausdorff distance (95% HD)] were evaluated for whole-heart contours. Image quality metrics [normalized root mean square error (nRMSE), peak signal-to-noise ratio (PSNR), and multiscale structural similarity (MS-SSIM) scores] were evaluated. The technique was also tested qualitatively on three additional ICD datasets (Group B) including a patient with an implanted ICD. RESULTS: For the whole-heart contour with CycleGAN reconstruction: 1) Mean DSC rose from 0.910 to 0.935; 2) Mean TRE dropped from 4.488 to 2.877 mm; and 3) Mean 95% HD dropped from 10.236 to 7.700 mm. For the whole-body slice with CycleGAN reconstruction: 1) Mean nRMSE dropped from 0.644 to 0.420; 2) Mean MS-SSIM rose from 0.779 to 0.819; and 3) Mean PSNR rose from 18.744 to 22.368. The three Group B datasets evaluated qualitatively displayed a reduction in ICD artifacts in the heart. CONCLUSION: CycleGAN-generated reconstructions significantly improved both tracking and image quality metrics when used to mitigate artifacts from ICDs.

Factorization Theorem Connecting the Light-Cone Distribution Amplitudes of Heavy-Flavor Mesons in QCD and Heavy-Quark Effective Theory.

The light-cone distribution amplitude (LCDA) of a heavy-light meson defined in heavy quark effective theory (HQET) is a fundamental nonperturbative input to account for innumerable B meson exclusive decay and production processes. On the other hand, the conventional heavy-flavored meson LCDA defined in QCD also ubiquitously enters the factorization formula for hard exclusive B production processes. Inspired by the observation that these two LCDAs exhibit the identical infrared behaviors, yet differ in the ultraviolet scale of order m_{b} or greater, we propose a novel factorization theorem for the heavy-light mesons, that the LCDA defined in QCD can be further expressed as a convolution between the LCDA in HQET and a perturbatively calculable coefficient function thanks to asymptotic freedom. This refactorization program can be invoked to fully disentangle the effects from three disparate scales Q, m_{b}, and Λ_{QCD} for a hard exclusive B production process, particularly to facilitate the resummation of logarithms of type lnQ/m_{b} and lnm_{b}/Λ_{QCD} in a systematic fashion.

Development and evaluation of machine learning models for voxel dose predictions in online adaptive magnetic resonance guided radiation therapy.

PURPOSE: Daily online adaptive plan quality in magnetic resonance imaging guided radiation therapy (MRgRT) is difficult to assess in relation to the fully optimized, high quality plans traditionally established offline. Machine learning prediction models developed in this work are capable of predicting 3D dose distributions, enabling the evaluation of online adaptive plan quality to better inform adaptive decision-making in MRgRT. METHODS: Artificial neural networks predicted 3D dose distributions from input variables related to patient anatomy, geometry, and target/organ-at-risk relationships in over 300 treatment plans from 53 patients receiving adaptive, linac-based MRgRT for abdominal cancers. The models do not include any beam related variables such as beam angles or fluence and were optimized to balance errors related to raw dose and specific plan quality metrics used to guide daily online adaptive decisions. RESULTS: Averaged over all plans, the dose prediction error and the absolute error were 0.1 ± 3.4 Gy (0.1 ± 6.2%) and 3.5 ± 2.4 Gy (6.4 ± 4.3%) respectively. Plan metric prediction errors were -0.1 ± 1.5%, -0.5 ± 2.1%, -0.9 ± 2.2 Gy, and 0.1 ± 2.7 Gy for V95, V100, D95, and Dmean respectively. Plan metric prediction absolute errors were 1.1 ± 1.1%, 1.5 ± 1.5%, 1.9 ± 1.4 Gy, and 2.2 ± 1.6 Gy. Approximately 10% (25) of the plans studied were clearly identified by the prediction models as inferior quality plans needing further optimization and refinement. CONCLUSION: Machine learning prediction models for treatment plan 3D dose distributions in online adaptive MRgRT were developed and tested. Clinical integration of the models requires minimal effort, producing 3D dose predictions for a new patient's plan using only target and OAR structures as inputs. These models can enable improved workflows for MRgRT through more informed plan optimization and plan quality assessment in real time.

Automatic x-ray image contrast enhancement based on parameter auto-optimization.

PURPOSE: Insufficient image contrast associated with radiation therapy daily setup x-ray images could negatively affect accurate patient treatment setup. We developed a method to perform automatic and user-independent contrast enhancement on 2D kilo voltage (kV) and megavoltage (MV) x-ray images. The goal was to provide tissue contrast optimized for each treatment site in order to support accurate patient daily treatment setup and the subsequent offline review. METHODS: The proposed method processes the 2D x-ray images with an optimized image processing filter chain, which consists of a noise reduction filter and a high-pass filter followed by a contrast limited adaptive histogram equalization (CLAHE) filter. The most important innovation is to optimize the image processing parameters automatically to determine the required image contrast settings per disease site and imaging modality. Three major parameters controlling the image processing chain, i.e., the Gaussian smoothing weighting factor for the high-pass filter, the block size, and the clip limiting parameter for the CLAHE filter, were determined automatically using an interior-point constrained optimization algorithm. RESULTS: Fifty-two kV and MV x-ray images were included in this study. The results were manually evaluated and ranked with scores from 1 (worst, unacceptable) to 5 (significantly better than adequate and visually praise worthy) by physicians and physicists. The average scores for the images processed by the proposed method, the CLAHE, and the best window-level adjustment were 3.92, 2.83, and 2.27, respectively. The percentage of the processed images received a score of 5 were 48, 29, and 18%, respectively. CONCLUSION: The proposed method is able to outperform the standard image contrast adjustment procedures that are currently used in the commercial clinical systems. When the proposed method is implemented in the clinical systems as an automatic image processing filter, it could be useful for allowing quicker and potentially more accurate treatment setup and facilitating the subsequent offline review and verification.

A method to reconstruct and apply 3D primary fluence for treatment delivery verification.

MOTIVATION: In this study, a method is reported to perform IMRT and VMAT treatment delivery verification using 3D volumetric primary beam fluences reconstructed directly from planned beam parameters and treatment delivery records. The goals of this paper are to demonstrate that 1) 3D beam fluences can be reconstructed efficiently, 2) quality assurance (QA) based on the reconstructed 3D fluences is capable of detecting additional treatment delivery errors, particularly for VMAT plans, beyond those identifiable by other existing treatment delivery verification methods, and 3) QA results based on 3D fluence calculation (3DFC) are correlated with QA results based on physical phantom measurements and radiation dose recalculations. METHODS: Using beam parameters extracted from DICOM plan files and treatment delivery log files, 3D volumetric primary fluences are reconstructed by forward-projecting the beam apertures, defined by the MLC leaf positions and modulated by beam MU values, at all gantry angles using first-order ray tracing. Treatment delivery verifications are performed by comparing 3D fluences reconstructed using beam parameters in delivery log files against those reconstructed from treatment plans. Passing rates are then determined using both voxel intensity differences and a 3D gamma analysis. QA sensitivity to various sources of errors is defined as the observed differences in passing rates. Correlations between passing rates obtained from QA derived from both 3D fluence calculations and physical measurements are investigated prospectively using 20 clinical treatment plans with artificially introduced machine delivery errors. RESULTS: Studies with artificially introduced errors show that common treatment delivery problems including gantry angle errors, MU errors, jaw position errors, collimator rotation errors, and MLC leaf position errors were detectable at less than normal machine tolerances. The reported 3DFC QA method has greater sensitivity than measurement-based QA methods. Statistical analysis-based Spearman's correlations shows that the 3DFC QA passing rates are significantly correlated with passing rates of physical phantom measurement-based QA methods. CONCLUSION: Among measurement-less treatment delivery verification methods, the reported 3DFC method is less demanding than those based on full dose re-calculations, and more comprehensive than those that solely checks beam parameters in treatment log files. With QA passing rates correlating to measurement-based passing rates, the 3DFC QA results could be useful for complementing the physical phantom measurements, or verifying treatment deliveries when physical measurements are not available. For the past 4+ years, the reported method has been implemented at authors' institution 1) as a complementary metric to physical phantom measurements for pretreatment, patient-specific QA of IMRT and VMAT plans, and 2) as an important part of the log file-based automated verification of daily patient treatment deliveries. It has been demonstrated to be useful in catching both treatment plan data transfer errors and treatment delivery problems.

A Method to Recognize Anatomical Site and Image Acquisition View in X-ray Images.

A method was developed to recognize anatomical site and image acquisition view automatically in 2D X-ray images that are used in image-guided radiation therapy. The purpose is to enable site and view dependent automation and optimization in the image processing tasks including 2D-2D image registration, 2D image contrast enhancement, and independent treatment site confirmation. The X-ray images for 180 patients of six disease sites (the brain, head-neck, breast, lung, abdomen, and pelvis) were included in this study with 30 patients each site and two images of orthogonal views each patient. A hierarchical multiclass recognition model was developed to recognize general site first and then specific site. Each node of the hierarchical model recognized the images using a feature extraction step based on principal component analysis followed by a binary classification step based on support vector machine. Given two images in known orthogonal views, the site recognition model achieved a 99% average F1 score across the six sites. If the views were unknown in the images, the average F1 score was 97%. If only one image was taken either with or without view information, the average F1 score was 94%. The accuracy of the site-specific view recognition models was 100%.

Methods to model and predict the ViewRay treatment deliveries to aid patient scheduling and treatment planning.

A software tool is developed, given a new treatment plan, to predict treatment delivery time for radiation therapy (RT) treatments of patients on ViewRay magnetic resonance image-guided radiation therapy (MR-IGRT) delivery system. This tool is necessary for managing patient treatment scheduling in our clinic. The predicted treatment delivery time and the assessment of plan complexities could also be useful to aid treatment planning. A patient's total treatment delivery time, not including time required for localization, is modeled as the sum of four components: 1) the treatment initialization time; 2) the total beam-on time; 3) the gantry rotation time; and 4) the multileaf collimator (MLC) motion time. Each of the four components is predicted separately. The total beam-on time can be calculated using both the planned beam-on time and the decay-corrected dose rate. To predict the remain-ing components, we retrospectively analyzed the patient treatment delivery record files. The initialization time is demonstrated to be random since it depends on the final gantry angle of the previous treatment. Based on modeling the relationships between the gantry rotation angles and the corresponding rotation time, linear regression is applied to predict the gantry rotation time. The MLC motion time is calculated using the leaves delay modeling method and the leaf motion speed. A quantitative analysis was performed to understand the correlation between the total treatment time and the plan complexity. The proposed algorithm is able to predict the ViewRay treatment delivery time with the average prediction error 0.22min or 1.82%, and the maximal prediction error 0.89 min or 7.88%. The analysis has shown the correlation between the plan modulation (PM) factor and the total treatment delivery time, as well as the treatment delivery duty cycle. A possibility has been identified to significantly reduce MLC motion time by optimizing the positions of closed MLC pairs. The accuracy of the proposed prediction algorithm is sufficient to support patient treatment appointment scheduling. This developed software tool is currently applied in use on a daily basis in our clinic, and could also be used as an important indicator for treatment plan complexity.

A software tool to automatically assure and report daily treatment deliveries by a cobalt-60 radiation therapy device.

The aims of this study were to develop a method for automatic and immediate verification of treatment delivery after each treatment fraction in order to detect and correct errors, and to develop a comprehensive daily report which includes delivery verification results, daily image-guided radiation therapy (IGRT) review, and information for weekly physics reviews. After systematically analyzing the requirements for treatment delivery verification and understanding the available information from a commercial MRI-guided radiotherapy treatment machine, we designed a procedure to use 1) treatment plan files, 2) delivery log files, and 3) beam output information to verify the accuracy and completeness of each daily treatment delivery. The procedure verifies the correctness of delivered treatment plan parameters including beams, beam segments and, for each segment, the beam-on time and MLC leaf positions. For each beam, composite primary fluence maps are calculated from the MLC leaf positions and segment beam-on time. Error statistics are calculated on the fluence difference maps between the plan and the delivery. A daily treatment delivery report is designed to include all required information for IGRT and weekly physics reviews including the plan and treatment fraction information, daily beam output information, and the treatment delivery verification results. A computer program was developed to implement the proposed procedure of the automatic delivery verification and daily report generation for an MRI guided radiation therapy system. The program was clinically commissioned. Sensitivity was measured with simulated errors. The final version has been integrated into the com-mercial version of the treatment delivery system. The method automatically verifies the EBRT treatment deliveries and generates the daily treatment reports. Already in clinical use for over one year, it is useful to facilitate delivery error detection, and to expedite physician daily IGRT review and physicist weekly chart review.

A comprehensive lung CT landmark pair dataset for evaluating deformable image registration algorithms.

PURPOSE: Deformable image registration (DIR) is a key enabling technology in many diagnostic and therapeutic tasks, but often does not meet the required robustness and accuracy for supporting clinical tasks. This is in large part due to a lack of high-quality benchmark datasets by which new DIR algorithms can be evaluated. Our team was supported by the National Institute of Biomedical Imaging and Bioengineering to develop DIR benchmark dataset libraries for multiple anatomical sites, comprising of large numbers of highly accurate landmark pairs on matching blood vessel bifurcations. Here we introduce our lung CT DIR benchmark dataset library, which was developed to improve upon the number and distribution of landmark pairs in current public lung CT benchmark datasets. ACQUISITION AND VALIDATION METHODS: Thirty CT image pairs were acquired from several publicly available repositories as well as authors' institution with IRB approval. The data processing workflow included multiple steps: (1) The images were denoised. (2) Lungs, airways, and blood vessels were automatically segmented. (3) Bifurcations were directly detected on the skeleton of the segmented vessel tree. (4) Falsely identified bifurcations were filtered out using manually defined rules. (5) A DIR was used to project landmarks detected on the first image onto the second image of the image pair to form landmark pairs. (6) Landmark pairs were manually verified. This workflow resulted in an average of 1262 landmark pairs per image pair. Estimates of the landmark pair target registration error (TRE) using digital phantoms were 0.4 mm ± 0.3 mm. DATA FORMAT AND USAGE NOTES: The data is published in Zenodo at https://doi.org/10.5281/zenodo.8200423. Instructions for use can be found at https://github.com/deshanyang/Lung-DIR-QA. POTENTIAL APPLICATIONS: The dataset library generated in this work is the largest of its kind to date and will provide researchers with a new and improved set of ground truth benchmarks for quantitatively validating DIR algorithms within the lung.

Deep learning-based motion compensation for four-dimensional cone-beam computed tomography (4D-CBCT) reconstruction.

BACKGROUND: Motion-compensated (MoCo) reconstruction shows great promise in improving four-dimensional cone-beam computed tomography (4D-CBCT) image quality. MoCo reconstruction for a 4D-CBCT could be more accurate using motion information at the CBCT imaging time than that obtained from previous 4D-CT scans. However, such data-driven approaches are hampered by the quality of initial 4D-CBCT images used for motion modeling. PURPOSE: This study aims to develop a deep-learning method to generate high-quality motion models for MoCo reconstruction to improve the quality of final 4D-CBCT images. METHODS: A 3D artifact-reduction convolutional neural network (CNN) was proposed to improve conventional phase-correlated Feldkamp-Davis-Kress (PCF) reconstructions by reducing undersampling-induced streaking artifacts while maintaining motion information. The CNN-generated artifact-mitigated 4D-CBCT images (CNN enhanced) were then used to build a motion model which was used by MoCo reconstruction (CNN+MoCo). The proposed procedure was evaluated using in-vivo patient datasets, an extended cardiac-torso (XCAT) phantom, and the public SPARE challenge datasets. The quality of reconstructed images for XCAT phantom and SPARE datasets was quantitatively assessed using root-mean-square-error (RMSE) and normalized cross-correlation (NCC). RESULTS: The trained CNN effectively reduced the streaking artifacts of PCF CBCT images for all datasets. More detailed structures can be recovered using the proposed CNN+MoCo reconstruction procedure. XCAT phantom experiments showed that the accuracy of estimated motion model using CNN enhanced images was greatly improved over PCF. CNN+MoCo showed lower RMSE and higher NCC compared to PCF, CNN enhanced and conventional MoCo. For the SPARE datasets, the average (± standard deviation) RMSE in mm-1 for body region of PCF, CNN enhanced, conventional MoCo and CNN+MoCo were 0.0040 ± 0.0009, 0.0029 ± 0.0002, 0.0024 ± 0.0003 and 0.0021 ± 0.0003. Corresponding NCC were 0.84 ± 0.05, 0.91 ± 0.05, 0.91 ± 0.05 and 0.93 ± 0.04. CONCLUSIONS: CNN-based artifact reduction can substantially reduce the artifacts in the initial 4D-CBCT images. The improved images could be used to enhance the motion modeling and ultimately improve the quality of the final 4D-CBCT images reconstructed using MoCo.

Implementation of a knowledge-based decision support system for treatment plan auditing through automation.

BACKGROUND: Independent auditing is a necessary component of a comprehensive quality assurance (QA) program and can also be utilized for continuous quality improvement (QI) in various radiotherapy processes. Two senior physicists at our institution have been performing a time intensive manual audit of cross-campus treatment plans annually, with the aim of further standardizing our planning procedures, updating policies and guidelines, and providing training opportunities of all staff members. PURPOSE: A knowledge-based automated anomaly-detection algorithm to provide decision support and strengthen our manual retrospective plan auditing process was developed. This standardized and improved the efficiency of the assessment of our external beam radiotherapy (EBRT) treatment planning across all eight campuses of our institution. METHODS: A total of 843 external beam radiotherapy plans for 721 lung patients from January 2020 to March 2021 were automatically acquired from our clinical treatment planning and management systems. From each plan, 44 parameters were automatically extracted and pre-processed. A knowledge-based anomaly detection algorithm, namely, "isolation forest" (iForest), was then applied to the plan dataset. An anomaly score was determined for each plan using recursive partitioning mechanism. Top 20 plans ranked with the highest anomaly scores for each treatment technique (2D/3D/IMRT/VMAT/SBRT) including auto-populated parameters were used to guide the manual auditing process and validated by two plan auditors. RESULTS: The two auditors verified that 75.6% plans with the highest iForest anomaly scores have similar concerning qualities that may lead to actionable recommendations for our planning procedures and staff training materials. The time to audit a chart was approximately 20.8 min on average when done manually and 14.0 min when done with the iForest guidance. Approximately 6.8 min were saved per chart with the iForest method. For our typical internal audit review of 250 charts annually, the total time savings are approximately 30 hr per year. CONCLUSION: iForest effectively detects anomalous plans and strengthens our cross-campus manual plan auditing procedure by adding decision support and further improve standardization. Due to the use of automation, this method was efficient and will be used to establish a standard plan auditing procedure, which could occur more frequently.

Respiratory motion management using a single rapid MRI scan for a 0.35 T MRI-Linac system.

BACKGROUND: MRI has a rapidly growing role in radiation therapy (RT) for treatment planning, real-time image guidance, and beam gating (e.g., MRI-Linac). Free-breathing 4D-MRI is desirable in respiratory motion management for therapy. Moreover, high-quality 3D-MRIs without motion artifacts are needed to delineate lesions. Existing MRI methods require multiple scans with lengthy acquisition times or are limited by low spatial resolution, contrast, and signal-to-noise ratio. PURPOSE: We developed a novel method to obtain motion-resolved 4D-MRIs and motion-integrated 3D-MRI reconstruction using a single rapid (35-45 s scan on a 0.35 T MRI-Linac. METHODS: Golden-angle radial stack-of-stars MRI scans were acquired from a respiratory motion phantom and 12 healthy volunteers (n = 12) on a 0.35 T MRI-Linac. A self-navigated method was employed to detect respiratory motion using 2000 (acquisition time = 5-7 min) and the first 200 spokes (acquisition time = 35-45 s). Multi-coil non-uniform fast Fourier transform (MCNUFFT), compressed sensing (CS), and deep-learning Phase2Phase (P2P) methods were employed to reconstruct motion-resolved 4D-MRI using 2000 spokes (MCNUFFT2000) and 200 spokes (CS200 and P2P200). Deformable motion vector fields (MVFs) were computed from the 4D-MRIs and used to reconstruct motion-corrected 3D-MRIs with the MOtion Transformation Integrated forward-Fourier (MOTIF) method. Image quality was evaluated quantitatively using the structural similarity index measure (SSIM) and the root mean square error (RMSE), and qualitatively in a blinded radiological review. RESULTS: Evaluation using the respiratory motion phantom experiment showed that the proposed method reversed the effects of motion blurring and restored edge sharpness. In the human study, P2P200 had smaller inaccuracy in MVFs estimation than CS200. P2P200 had significantly greater SSIMs (p < 0.0001) and smaller RMSEs (p < 0.001) than CS200 in motion-resolved 4D-MRI and motion-corrected 3D-MRI. The radiological review found that MOTIF 3D-MRIs using MCNUFFT2000 exhibited the highest image quality (scoring > 8 out of 10), followed by P2P200 (scoring > 5 out of 10), and then motion-uncorrected (scoring < 3 out of 10) in sharpness, contrast, and artifact-freeness. CONCLUSIONS: We have successfully demonstrated a method for respiratory motion management for MRI-guided RT. The method integrated self-navigated respiratory motion detection, deep-learning P2P 4D-MRI reconstruction, and a motion integrated reconstruction (MOTIF) for 3D-MRI using a single rapid MRI scan (35-45 s) on a 0.35 T MRI-Linac system.

Automated radiotherapy treatment plan integrity verification.

PURPOSE: In our clinic, physicists spend from 15 to 60 min to verify the physical and dosimetric integrity of radiotherapy plans before presentation to radiation oncology physicians for approval. The purpose of this study was to design and implement a framework to automate as many elements of this quality control (QC) step as possible. METHODS: A comprehensive computer application was developed to carry out a majority of these verification tasks in the Philips PINNACLE treatment planning system (TPS). This QC tool functions based on both PINNACLE scripting elements and PERL sub-routines. The core of this technique is the method of dynamic scripting, which involves a PERL programming module that is flexible and powerful for treatment plan data handling. Run-time plan data are collected, saved into temporary files, and analyzed against standard values and predefined logical rules. The results were summarized in a hypertext markup language (HTML) report that is displayed to the user. RESULTS: This tool has been in clinical use for over a year. The occurrence frequency of technical problems, which would cause delays and suboptimal plans, has been reduced since clinical implementation. CONCLUSIONS: In addition to drastically reducing the set of human-driven logical comparisons, this QC tool also accomplished some tasks that are otherwise either quite laborious or impractical for humans to verify, e.g., identifying conflicts amongst IMRT optimization objectives.

Physical phantom studies of helical cone-beam CT with exact reconstruction.

PURPOSE: Onboard cone-beam computed tomography (CBCT) connected to radiotherapy linear accelerators suffers CT number consistency and uniformity problems in addition to limited longitudinal coverage. Such problems have prevented CBCT from being fully utilized in many quantitative applications including tumor response evaluation and daily radiation dose computation. This paper presents a feasibility study on the helical CBCT scan with exact reconstruction that could be a potential solution. METHODS: A Varian TrueBeam treatment machine was programmed in the research mode to accomplish helical scans that required synchronized gantry circular rotation and couch table linear motion. Two physical phantoms were scanned in both 360° and 720° helical trajectories. A Katsevich exact reconstruction algorithm was implemented and tested with digital phantom simulations. It was further optimized to account for mechanical instabilities of both gantry rotation and couch table motion from the physical phantom measurements. Preprocessing was employed to correct photon scattering, beam hardening, and bowtie filtration. The reconstructed images were compared to those reconstructed from the FDK approximate reconstruction algorithm using the same phantom projections. Comparisons have also been made with the clinical circular CBCT images and the diagnostic helical CT images of the same physical phantoms. RESULTS: Satisfactory reconstruction results were obtained for the Katsevich algorithm in digital phantom study. Physical phantom results demonstrated that a 360° helical scan could provide up to 19 cm longitudinal coverage, which could be increased to 54 cm with a 720° helical scan. Image spatial resolution and soft tissue contrast were sufficient. The Q-value, which combined the spatial frequency response (modulation transfer function) and the image noise, was calculated, and suggested that the Katsevich algorithm was superior to the FDK algorithm. CONCLUSIONS: A helical CBCT scan is useful to extend the longitudinal coverage. The Katsevich exact reconstruction algorithm could provide additional advantages in image qualities over the traditional FDK approximate algorithm. The combination of helical CBCT scan with exact reconstruction was proved feasible and would render CBCT more useful in image-guided radiation therapy.

Technical note: electronic chart checks in a paperless radiation therapy clinic.

PURPOSE: EcCk, which stands for Electronic Chart ChecK, is a computer software and database system. It was developed to improve quality and efficiency of patient chart checking in radiation oncology departments. The core concept is to automatically collect and analyze patient treatment data, and to report discrepancies and potential concerns. METHODS: EcCk consists of several different computer technologies, including relational database, DICOM, dynamic HTML, and image processing. Implemented in MATLAB and C#, EcCk processes patient data in DICOM, PDF, Microsoft Word, database, and Pinnacle native formats. Generated reports are stored on the storage server and indexed in the database. A standalone report-browser program is implemented to allow users to view reports on any computer in the department. Checks are performed according to predefined logical rules, and results are presented through color-coded reports in which discrepancies are summarized and highlighted. Users examine the reports and take appropriate actions. The core design is intended to automate human task and to improve the reliability of the performed tasks. The software is not intended to replace human audits but rather to aid as a decision support tool. RESULTS: The software was successfully implemented in the clinical environment and has demonstrated the feasibility of automation of this common task with modern clinical tools. The software integrates multiple disconnected systems and successfully supports analysis of data in diverse formats. CONCLUSIONS: While the human is the ultimate expert, EcCk has a significant potential to improve quality and efficiency of patient treatment record audits, and to allow verification of tasks that are not easily performed by humans. EcCk can potentially relieve human experts from simple and repetitive tasks, and allow them to work on other important tasks, and in the end to improve the quality and safety of radiation therapy treatments.

Evaluation of the efficiency and effectiveness of independent dose calculation followed by machine log file analysis against conventional measurement based IMRT QA.

Experimental methods are commonly used for patient-specific IMRT delivery verification. There are a variety of IMRT QA techniques which have been proposed and clinically used with a common understanding that not one single method can detect all possible errors. The aim of this work was to compare the efficiency and effectiveness of independent dose calculation followed by machine log file analysis to conventional measurement-based methods in detecting errors in IMRT delivery. Sixteen IMRT treatment plans (5 head-and-neck, 3 rectum, 3 breast, and 5 prostate plans) created with a commercial treatment planning system (TPS) were recalculated on a QA phantom. All treatment plans underwent ion chamber (IC) and 2D diode array measurements. The same set of plans was also recomputed with another commercial treatment planning system and the two sets of calculations were compared. The deviations between dosimetric measurements and independent dose calculation were evaluated. The comparisons included evaluations of DVHs and point doses calculated by the two TPS systems. Machine log files were captured during pretreatment composite point dose measurements and analyzed to verify data transfer and performance of the delivery machine. Average deviation between IC measurements and point dose calculations with the two TPSs for head-and-neck plans were 1.2 ± 1.3% and 1.4 ± 1.6%, respectively. For 2D diode array measurements, the mean gamma value with 3% dose difference and 3 mm distance-to-agreement was within 1.5% for 13 of 16 plans. The mean 3D dose differences calculated from two TPSs were within 3% for head-and-neck cases and within 2% for other plans. The machine log file analysis showed that the gantry angle, jaw position, collimator angle, and MUs were consistent as planned, and maximal MLC position error was less than 0.5 mm. The independent dose calculation followed by the machine log analysis takes an average 47 ± 6 minutes, while the experimental approach (using IC and 2D diode array measurements) takes an average about 2 hours in our clinic. Independent dose calculation followed by machine log file analysis can be a reliable tool to verify IMRT treatments. Additionally, independent dose calculations have the potential to identify several problems (heterogeneity calculations, data corruptions, system failures) with the primary TPS, which generally are not identifiable with a measurement-based approach. Additionally, machine log file analysis can identify many problems (gantry, collimator, jaw setting) which also may not be detected with a measurement-based approach. Machine log file analysis could also detect performance problems for individual MLC leaves which could be masked in the analysis of a measured fluence.

Contour interpolation by deep learning approach.

Purpose: Contour interpolation is an important tool for expediting manual segmentation of anatomical structures. The process allows users to manually contour on discontinuous slices and then automatically fill in the gaps, therefore saving time and efforts. The most used conventional shape-based interpolation (SBI) algorithm, which operates on shape information, often performs suboptimally near the superior and inferior borders of organs and for the gastrointestinal structures. In this study, we present a generic deep learning solution to improve the robustness and accuracy for contour interpolation, especially for these historically difficult cases. Approach: A generic deep contour interpolation model was developed and trained using 16,796 publicly available cases from 5 different data libraries, covering 15 organs. The network inputs were a 128 × 128 × 5 image patch and the two-dimensional contour masks for the top and bottom slices of the patch. The outputs were the organ masks for the three middle slices. The performance was evaluated on both dice scores and distance-to-agreement (DTA) values. Results: The deep contour interpolation model achieved a dice score of 0.95 ± 0.05 and a mean DTA value of 1.09 ± 2.30 mm , averaged on 3167 testing cases of all 15 organs. In a comparison, the results by the conventional SBI method were 0.94 ± 0.08 and 1.50 ± 3.63 mm , respectively. For the difficult cases, the dice score and DTA value were 0.91 ± 0.09 and 1.68 ± 2.28 mm by the deep interpolator, compared with 0.86 ± 0.13 and 3.43 ± 5.89 mm by SBI. The t-test results confirmed that the performance improvements were statistically significant ( p < 0.05 ) for all cases in dice scores and for small organs and difficult cases in DTA values. Ablation studies were also performed. Conclusions: A deep learning method was developed to enhance the process of contour interpolation. It could be useful for expediting the tasks of manual segmentation of organs and structures in the medical images.

Real-time B0 compensation during gantry rotation in a 0.35-T MRI-Linac.

BACKGROUND: Rotation of the ferromagnetic gantry of a low magnetic field MRI-Linac was previously demonstrated to cause large center frequency offsets of ±400 Hz. The B0 off-resonances cause image artifacts and imaging isocenter shifts that would preclude MRI-guided arc therapy. PURPOSE: The purpose of this study was to measure and compensate for center frequency offsets in real time during gantry rotation on a 0.35-T MRI-Linac using a free induction decay (FID) navigator. METHODS: A nonselective FID navigator was added before each 2D balanced steady-state free precession cine image acquisition on a 0.35-T MRI-Linac. Images were acquired at 7.3 frames per second. Phase data from the initial FID navigator (while the gantry was stationary) was used as a reference. The phase data from each subsequent FID navigator was used to calculate the real-time B0 off-resonance. The transmitter/receiver phase and the phase accrual over the adjacent image acquisition were adjusted to correct for the center frequency offset. Measurements were performed using an MRI-Linac dynamic phantom prior to and while the gantry rotated clockwise and counterclockwise. Image quality and signal-to-noise ratio (SNR) were compared between uncorrected and B0 -corrected MRIs using a reference image acquired while the gantry was stationary. Four targets in the phantom were manually contoured on the first image frame, and an active contouring algorithm was used retrospectively on each subsequent frame to assess image variations and calculate Dice coefficients. Additionally, three healthy volunteers were imaged using the same pulse sequences with and without real-time B0 compensation during gantry rotation. Normalized root mean square errors (nRMSEs) were calculated for the phantom and in vivo to assess the efficacy of the B0 compensation on image quality. The measured center frequency offsets from the volunteer and MRI dynamic phantom navigator data were also compared. The sinusoidal behavior of the center frequency offsets was modeled based on the gantry layout and long-time constant eddy currents resulting from gantry rotation. RESULTS: The duration of the FID navigator and processing was 4.5 ms. The FID navigator resulted in a ≤11% drop in SNR in the phantom and in vivo (liver). Dice coefficients from the MRI-guided radiation therapy (MR-IGRT) phantom contour measurements remained above 0.8 with B0 compensation. Without B0 compensation, the Dice coefficients dropped below 0.8 for up to 21% of the time depending on the contour. Real-time B0 compensation resulted in mean reductions in nRMSE of 51% and 16% for the MR-IGRT phantom and in vivo, respectively. Peak-to-peak center frequency offsets ranged from 757 to 773 Hz in the phantom and 760 to 871 Hz in vivo. CONCLUSION: Dynamic real-time B0 compensation significantly improved image quality and reduced artifacts during gantry rotation in the phantom and in vivo. However, the FID navigator resulted in a small drop in the imaging duty cycle and SNR.

A reconstruction approach for proton computed tomography by modeling the integral depth dose of the scanning proton pencil beam.

PURPOSE: To present a proton computed tomography (pCT) reconstruction approach that models the integral depth dose (IDD) of the clinical scanning proton beam into beamlets. Using a multilayer ionization chamber (MLIC) as the imager, the proposed pCT system and the reconstruction approach can minimize extra ambient neutron dose and simplify the beamline design by eliminating an additional collimator to confine the proton beam. METHODS: Monte Carlo simulation was applied to digitally simulate the IDDs of the exiting proton beams detected by the MLIC. A forward model was developed to model each IDD into a weighted sum of percentage depth doses of the constituent beamlets separated laterally by 1 mm. The water equivalent path lengths (WEPLs) of the beamlets were determined by iteratively minimizing the squared L2-norm between the forward projected and simulated IDDs. The final WEPL values were reconstructed to pCT images, that is, proton stopping power ratio (SPR) maps, through simultaneous algebraic reconstruction technique with total variation regularization. The reconstruction process was tested with a digital cylindrical water-based phantom and an ICRP adult reference computational phantom. The mean of SPR within regions of interest (ROIs) and the WEPL along a 4 mm-wide beam ( WEP L 4 mm ${\rm{WEP}}{{\rm{L}}_{4{\rm{mm}}}}$ ) were compared with the reference values. The spatial resolution was analyzed at the edge of a cortical insert of the cylindrical phantom. RESULTS: The percentage deviations from reference SPR were within ±1% in all selected ROIs. The mean absolute error of the reconstructed SPR was 0.33%, 0.19%, and 0.27% for the cylindrical phantom, the adult phantom at the head and lung region, respectively. The corresponding percentage deviations from reference WEP L 4 mm ${\rm{WEP}}{{\rm{L}}_{4{\rm{mm}}}}$ were 0.48 ± 0.64%, 0.28 ± 0.48%, and 0.22 ± 0.49%. The full width at half maximum of the line spread function (LSF) derived from the radial edge spread function (ESF) of a cortical insert was 0.13 cm. The frequency at 10% of the modulation transfer function (MTF) was 6.38 cm-1 . The mean signal-to-noise ratio (SNR) of all the inserts was 2.45. The mean imaging dose was 0.29 and 0.25 cGy at the head and lung region of the adult phantom, respectively. CONCLUSION: A new pCT reconstruction approach was developed by modeling the IDDs of the uncollimated scanning proton beams in the pencil beam geometry. SPR accuracy within ±1%, spatial resolution of better than 2 mm at 10% MTF, and imaging dose at the magnitude of mGy were achieved. Potential side effects caused by neutron dose were eliminated by removing the extra beam collimator.