Search

Background: Image-guided radiation-therapy (IGRT)-based robotic radiosurgery using magnetic resonance imaging (MRI)-only simulation could allow for improved target definition with highly conformal radiotherapy treatments. Fiducial marker (FM)-based alignment is used with robotic radiosurgery treatments of sites such as the prostate because it aids in accurate target localization. Synthetic CT (sCT) images are generated in the MRI-only workflow but FMs used for IGRT appear as signal voids in MRIs and do not appear in MR-generated sCTs, hindering the ability to use sCTs for fiducial-based IGRT., Purpose: In this study we evaluate the fiducial tracking accuracy for a novel artificial fiducial insertion method in sCT images that allows for fiducial marker tracking in robotic radiosurgery, using MRI-only simulation imaging (MRI-only workflow)., Methods: Artificial fiducial markers were inserted into sCT images at the site of the real marker implantation as visible in MRI. Two phantoms were used in this study. A custom anthropomorphic pelvis phantom was designed to validate the tracking accuracy for a variety of artificial fiducials in an MRI-only workflow. A head phantom containing a hidden target and orthogonal film pair inserts was used to perform end-to-end tests of artificial fiducial configurations inserted in sCT images. The setup and end-to-end targeting accuracy of the MRI-only workflow were compared to the computed tomography (CT)-based standard. Each phantom had six FMs implanted with a minimum spacing of 2 cm. For each phantom a bulk-density sCT was generated, and artificial FMs were inserted at the implantation location. Several methods of FM insertion were tested including: (1) replacing HU with a fixed value (10000HU) (voxel-burned); (2) using a representative fiducial image derived from a linear combination of fiducial templates (composite-fiducial); (3) computationally simulating FM signal voids using a digital phantom containing FMs and inserting the corresponding signal void into sCT images (simulated-fiducial). All tests were performed on a CyberKnife system (Accuray, Sunnyvale, CA). Treatment plans and digital-reconstructed-radiographs were generated from the original CT and sCTs with embedded fiducials and used to align the phantom on the treatment couch. Differences in the initial phantom alignment (3D translations/rotations) and tracking parameters between CT-based plans and sCT-based plans were analyzed. End-to-end plans for both scenarios were generated and analyzed following our clinical protocol., Results: For all plans, the fiducial tracking algorithm was able to identify the fiducial locations. The mean FM-extraction uncertainty for the composite and simulated FMs was below 48% for fiducials in both the anthropomorphic pelvis and end-to-end phantoms, which is below the 70% treatment uncertainty threshold. The total targeting error was within tolerance (<0.95 mm) for end-to-end tests of sCT images with the composite and head-on simulated FMs (0.26, 0.44, and 0.35 mm for the composite fiducial in sCT, head-on simulated fiducial in sCT, and fiducials in original CT, respectively., Conclusions: MRI-only simulation for robotic radiosurgery could potentially improve treatment accuracy and reduce planning margins. Our study has shown that using a composite-derived or simulated FM in conjunction with sCT images, MRI-only workflow can provide clinically acceptable setup accuracy in line with CT-based standards for FM-based robotic radiosurgery., (© 2023 American Association of Physicists in Medicine.)

Purpose: Convolutional neural networks have achieved excellent results in automatic medical image segmentation. In this study, we proposed a novel three-dimensional (3D) multipath DenseNet for generating the accurate glioblastoma (GBM) tumor contour from four multimodal pre-operative MR images. We hypothesized that the multipath architecture could achieve more accurate segmentation than a singlepath architecture., Methods: Two hundred and fifty-eight GBM patients were included in this study. Each patient had four MR images (T1-weighted, contrast-enhanced T1-weighted, T2-weighted, and FLAIR) and the manually segmented tumor contour. We built a 3D multipath DenseNet that could be trained to achieve an end-to-end mapping from four MR images to the corresponding GBM tumor contour. A 3D singlepath DenseNet was also built for comparison. Both DenseNets were based on the encoder-decoder architecture. All four images were concatenated and fed into a single encoder path in the singlepath DenseNet, while each input image had its own encoder path in the multipath DenseNet. The patient cohort was randomly split into a training set of 180 patients, a validation set of 39 patients, and a testing set of 39 patients. Model performance was evaluated using the Dice similarity coefficient (DSC), average surface distance (ASD), and 95% Hausdorff distance (HD 95% ). Wilcoxon signed-rank tests were conducted to assess statistical significances., Results: The singlepath DenseNet achieved the DSC of 0.911 ± 0.060, ASD of 1.3 ± 0.7 mm, and HD 95% of 5.2 ± 7.1 mm, while the multipath DenseNet achieved the DSC of 0.922 ± 0.041, ASD of 1.1 ± 0.5 mm, and HD 95% of 3.9 ± 3.3 mm. The P-values of all Wilcoxon signed-rank tests were less than 0.05., Conclusions: Both DenseNets generated GBM tumor contours in good agreement with the manually segmented contours from multimodal MR images. The multipath DenseNet achieved more accurate tumor segmentation than the singlepath DenseNet. Here presented the 3D multipath DenseNet that demonstrated an improved accuracy over comparable algorithms in the clinical task of GBM tumor segmentation., (© 2021 American Association of Physicists in Medicine.)

Purpose: Clinical sites utilizing magnetic resonance imaging (MRI)-only simulation for prostate radiotherapy planning typically use fiducial markers for pretreatment patient positioning and alignment. Fiducial markers appear as small signal voids in MRI images and are often difficult to discern. Existing clinical methods for fiducial marker localization require multiple MRI sequences and/or manual interaction and specialized expertise. In this study, we develop a robust method for automatic fiducial marker detection in prostate MRI simulation images and quantify the pretreatment alignment accuracy using automatically detected fiducial markers in MRI., Methods and Materials: In this study, a deep learning-based algorithm was used to convert MRI images into labeled fiducial marker volumes. Seventy-seven prostate cancer patients who received marker implantation prior to MRI and CT simulation imaging were selected for this study. Multiple-Echo T 1 -VIBE MRI images were acquired, and images were stratified (at the patient level) based on the presence of intraprostatic calcifications. Ground truth (GT) contours were defined by an expert on MRI using CT images. Training was done using the pix2pix generative adversarial network (GAN) image-to-image translation package and model testing was done using fivefold cross validation. For performance comparison, an experienced medical dosimetrist and a medical physicist each manually contoured fiducial markers in MRI images. The percent of correct detections and F 1 classification scores are reported for markers detected using the automatic detection algorithm and human observers. The patient positioning errors were quantified by calculating the target registration errors (TREs) from fiducial marker driven rigid registration between MRI and CBCT images. Target registration errors were quantified for fiducial marker contours defined on MRI by the automatic detection algorithm and the two expert human observers., Results: Ninety-six percent of implanted fiducial markers were correctly identified using the automatic detection algorithm. Two expert raters correctly identified 97% and 96% of fiducial markers, respectively. The F 1 classification score was 0.68, 0.75, and 0.72 for the automatic detection algorithm and two human raters, respectively. The main source of false discoveries was intraprostatic calcifications. The mean TRE differences between alignments from automatic detection algorithm and human detected markers and GT were <1 mm., Conclusions: We have developed a deep learning-based approach to automatically detect fiducial markers in MRI-only simulation images in a clinically representative patient cohort. The automatic detection algorithm-predicted markers can allow for patient setup with similar accuracy to independent human observers., (© 2020 American Association of Physicists in Medicine.)

Purpose: Increased utilization of magnetic resonance imaging (MRI) in radiotherapy has caused a growing need for phantoms that provide tissue-like contrast in both computed tomography (CT) and MRI images. Such phantoms can be used to compare MRI-based processes with CT-based clinical standards. Here, we develop and demonstrate the clinical utility of a three-dimensional (3D)-printed anthropomorphic pelvis phantom containing materials capable of T 1 , T 2 , and electron density matching for a clinically relevant set of soft tissues and bone., Methods: The phantom design was based on a male pelvic anatomy template with thin boundaries separating tissue types. Slots were included to allow insertion of various dosimeters. The phantom structure was created using a 3D printer. The tissue compartments were filled with carrageenan-based materials designed to match the T 1 and T 2 relaxation times and electron densities of the corresponding tissues. CT and MRI images of the phantom were acquired and used to compare phantom T 1 and T 2 relaxation times and electron densities to literature-reported values for human tissue. To demonstrate clinical utility, the phantom was used for end-to-end testing of an MRI-only treatment simulation and planning workflow. Based on a T 2 -weighted MRI image, synthetic CT (sCT) images were created using a statistical decomposition algorithm (MRIPlanner, Spectronic Research AB, Sweden) and used for dose calculation of volumetric-modulated arc therapy (VMAT) and seven-field intensity-modulated radiation therapy (IMRT) prostate plans. The plans were delivered on a Truebeam STX (Varian Medical Systems, Palo Alto, CA), with film and a 0.3 cc ion chamber used to measure the delivered dose. Doses calculated on the CT and sCTs were compared using common dose volume histogram metrics., Results: T 1 and T 2 relaxation time and electron density measurements for the muscle, prostate, and bone agreed well with literature-reported in vivo measurements. Film analysis resulted in a 99.7% gamma pass rate (3.0%, 3.0 mm) for both plans. The ion chamber-measured dose discrepancies at the isocenter were 0.36% and 1.67% for the IMRT and VMAT plans, respectively. The differences in PTV D98% and D95% between plans calculated on the CT and 1.5T/3.0 T-derived sCT images were under 3%., Conclusion: The developed phantom provides tissue-like contrast on MRI and CT and can be used to validate MRI-based processes through comparison with standard CT-based processes., (© 2020 American Association of Physicists in Medicine.)

Purpose: The improved soft tissue contrast of magnetic resonance imaging (MRI) compared to computed tomography (CT) makes it a useful imaging modality for radiotherapy treatment planning. Even when MR images are acquired for treatment planning, the standard clinical practice currently also requires a CT for dose calculation and x-ray-based patient positioning. This increases workloads, introduces uncertainty due to the required inter-modality image registrations, and involves unnecessary irradiation. While it would be beneficial to use exclusively MR images, a method needs to be employed to estimate a synthetic CT (sCT) for generating electron density maps and patient positioning reference images. We investigated 2D and 3D convolutional neural networks (CNNs) to generate a male pelvic sCT using a T1-weighted MR image and compare their performance., Methods: A retrospective study was performed using CTs and T1-weighted MR images of 20 prostate cancer patients. CTs were deformably registered to MR images to create CT-MR pairs for training networks. The proposed 2D CNN, which contained 27 convolutional layers, was modified from the state-of-the-art 2D CNN to save computational memory and prepare for building the 3D CNN. The proposed 2D and 3D models were trained from scratch to map intensities of T1-weighted MR images to CT Hounsfield Unit (HU) values. Each sCT was generated in a fivefold cross-validation framework and compared with the corresponding deformed CT (dCT) using voxel-wise mean absolute error (MAE). The sCT geometric accuracy was evaluated by comparing bone regions, defined by thresholding at 150 HU in the dCTs and the sCTs, using dice similarity coefficient (DSC), recall, and precision. To evaluate sCT patient positioning accuracy, bone regions in dCTs and sCTs were rigidly registered to the corresponding cone-beam CTs. The resulting paired Euler transformation vectors were compared by calculating translation vector distances and absolute differences of Euler angles. Statistical tests were performed to evaluate the differences among the proposed models and Han's model., Results: Generating a pelvic sCT required approximately 5.5 s using the proposed models. The average MAEs within the body contour were 40.5 ± 5.4 HU (mean ± SD) and 37.6 ± 5.1 HU for the 2D and 3D CNNs, respectively. The average DSC, recall, and precision for the bone region (thresholding the CT at 150 HU) were 0.81 ± 0.04, 0.85 ± 0.04, and 0.77 ± 0.09 for the 2D CNN, and 0.82 ± 0.04, 0.84 ± 0.04, and 0.80 ± 0.08 for the 3D CNN, respectively. For both models, mean translation vector distances are less than 0.6 mm with mean absolute differences of Euler angles less than 0.5°., Conclusions: The 2D and 3D CNNs generated accurate pelvic sCTs for the 20 patients using T1-weighted MR images. Statistical tests indicated that the proposed 3D model was able to generate sCTs with smaller MAE and higher bone region precision compared to 2D models. Results of patient alignment tests suggested that sCTs generated by the proposed CNNs can provide accurate patient positioning. The accuracy of the dose calculation using generated sCTs will be tested and compared for the proposed models in the future., (© 2019 American Association of Physicists in Medicine.)

Purpose: To develop and evaluate a method of reconstructing a patient- and treatment day- specific volumetric image and motion model from free-breathing cone-beam projections and respiratory surrogate measurements. This Motion-Compensated Simultaneous Algebraic Reconstruction Technique (MC-SART) generates and uses a motion model derived directly from the cone-beam projections, without requiring prior motion measurements from 4DCT, and can compensate for both inter- and intrabin deformations. The motion model can be used to generate images at arbitrary breathing points, which can be used for estimating volumetric images during treatment delivery., Methods: The MC-SART was formulated using simultaneous image reconstruction and motion model estimation. For image reconstruction, projections were first binned according to external surrogate measurements. Projections in each bin were used to reconstruct a set of volumetric images using MC-SART. The motion model was estimated based on deformable image registration between the reconstructed bins, and least squares fitting to model parameters. The model was used to compensate for motion in both projection and backprojection operations in the subsequent image reconstruction iterations. These updated images were then used to update the motion model, and the two steps were alternated between. The final output is a volumetric reference image and a motion model that can be used to generate images at any other time point from surrogate measurements., Results: A retrospective patient dataset consisting of eight lung cancer patients was used to evaluate the method. The absolute intensity differences in the lung regions compared to ground truth were 50.8 ± 43.9 HU in peak exhale phases (reference) and 80.8 ± 74.0 in peak inhale phases (generated). The 50th percentile of voxel registration error of all voxels in the lung regions with >5 mm amplitude was 1.3 mm. The MC-SART was also applied to measured patient cone-beam projections acquired with a linac-mounted CBCT system. Results from this patient data demonstrate the feasibility of MC-SART and showed qualitative image quality improvements compared to other state-of-the-art algorithms., Conclusion: We have developed a simultaneous image reconstruction and motion model estimation method that uses Cone-beam computed tomography (CBCT) projections and respiratory surrogate measurements to reconstruct a high-quality reference image and motion model of a patient in treatment position. The method provided superior performance in both HU accuracy and positional accuracy compared to other existing methods. The resultant reference image and motion model can be combined with respiratory surrogate measurements to generate volumetric images representing patient anatomy at arbitrary time points., (© 2019 American Association of Physicists in Medicine.)

Purpose: To develop a three-dimensional (3D) deformable head-and-neck (H&N) phantom with realistic tissue contrast for both kilovoltage (kV) and megavoltage (MV) imaging modalities and use it to objectively evaluate deformable image registration (DIR) algorithms., Methods: The phantom represents H&N patient anatomy. It is constructed from thermoplastic, which becomes pliable in boiling water, and hardened epoxy resin. Using a system of additives, the Hounsfield unit (HU) values of these materials were tuned to mimic anatomy for both kV and MV imaging. The phantom opens along a sagittal midsection to reveal radiotransparent markers, which were used to characterize the phantom deformation. The deformed and undeformed phantoms were scanned with kV and MV imaging modalities. Additionally, a calibration curve was created to change the HUs of the MV scans to be similar to kV HUs, (MC). The extracted ground-truth deformation was then compared to the results of two commercially available DIR algorithms, from Velocity Medical Solutions and mim software., Results: The phantom produced a 3D deformation, representing neck flexion, with a magnitude of up to 8 mm and was able to represent tissue HUs for both kV and MV imaging modalities. The two tested deformation algorithms yielded vastly different results. For kV-kV registration, mim produced mean and maximum errors of 1.8 and 11.5 mm, respectively. These same numbers for Velocity were 2.4 and 7.1 mm, respectively. For MV-MV, kV-MV, and kV-MC Velocity produced similar mean and maximum error values. mim, however, produced gross errors for all three of these scenarios, with maximum errors ranging from 33.4 to 41.6 mm., Conclusions: The application of DIR across different imaging modalities is particularly difficult, due to differences in tissue HUs and the presence of imaging artifacts. For this reason, DIR algorithms must be validated specifically for this purpose. The developed H&N phantom is an effective tool for this purpose.