Morphometric and clinical comparison of MRI-based synthetic CT to conventional CT of the hip in children.

BACKGROUND: MRI-based synthetic CT (sCT) generates CT-like images from MRI data. OBJECTIVE: To evaluate equivalence, inter- and intraobserver reliability, and image quality of sCT compared to conventional (cCT) for assessing hip morphology and maturity in pediatric patients. MATERIALS AND METHODS: We prospectively enrolled patients <21 years old with cCT and 3T MRI of the hips/pelvis. A dual-echo gradient-echo sequence was used to generate sCT via a commercially available post-processing software (BoneMRI v1.5 research version, MRIguidance BV, Utrecht, NL). Two pediatric musculoskeletal radiologists measured seven morphologic hip parameters. 3D surface distances between cCT and sCT were computed. Physeal status was established at seven locations with cCT as reference standard. Images were qualitatively scored on a 5-point Likert scale regarding diagnostic quality, signal-to-noise ratio, clarity of bony margin, corticomedullary differentiation, and presence and severity of artifacts. Quantitative evaluation of Hounsfield units (HU) was performed in bone, muscle, and fat tissue. Inter- and intraobserver reliability were measured by intraclass correlation coefficients. The cCT-to-sCT intermodal agreement was assessed via Bland-Altman analysis. The equivalence between modalities was tested using paired two one-sided tests. The quality parameter scores of each imaging modality were compared via Wilcoxon signed-rank test. For tissue-specific HU measurements, mean absolute error and mean percentage error values were calculated using the cCT as the reference standard. RESULTS: Thirty-eight hips in 19 patients were included (16.6 ± 3 years, range 9.9-20.9; male = 5). cCT- and sCT-based morphologic measurements demonstrated good to excellent inter- and intraobserver correlation (0.77

Detection of structural lesions of the sacroiliac joints in patients with spondyloarthritis: A comparison of T1-weighted 3D spoiled gradient echo MRI and MRI-based synthetic CT versus T1-weighted turbo spin echo MRI.

OBJECTIVES: To investigate the detection of erosion, sclerosis and ankylosis using 1 mm 3D T1-weighted spoiled gradient echo (T1w-GRE) MRI and 1 mm MRI-based synthetic CT (sCT), compared with conventional 4 mm T1w-TSE. MATERIALS AND METHODS: Prospective, cross-sectional study. Semi-coronal 4 mm T1w-TSE and axial T1w-GRE with 1.6 mm slice thickness and 0.8 mm spacing between overlapping slices were performed. The T1w-GRE images were processed into sCT images using a commercial deep learning algorithm, BoneMRI. Both were reconstructed into 1 mm semi-coronal images. T1w-TSE, T1w-GRE and sCT images were assessed independently by 3 expert and 4 non-expert readers for erosion, sclerosis and ankylosis. Cohen's kappa for inter-reader agreement, exact McNemar test for lesion frequencies and Wilcoxon signed-rank test for confidence in lesion detection were used. RESULTS: Nineteen patients with axial spondyloarthritis were evaluated. T1w-GRE increased inter-reader agreement for detecting erosion (kappa 0.42 vs 0.21 in non-experts), increased detection of erosion (57 vs 43 of 152 joint quadrants) and sclerosis (26 vs 17 of 152 joint quadrants) among experts, and increased reader confidence for scoring erosion and sclerosis. sCT increased inter-reader agreement for detecting sclerosis (kappa 0.69 vs 0.37 in experts) and ankylosis (0.71 vs 0.52 in non-experts), increased detection of sclerosis (34 vs 17 of 152 joint quadrants) and ankylosis (20 vs 13 of 76 joint halves) among experts, and increased reader confidence for scoring erosion, sclerosis and ankylosis. CONCLUSION: T1w-GRE and sCT increase sensitivity and reader confidence for the detection of erosion, sclerosis and ankylosis, compared with T1w-TSE. CLINICAL RELEVANCE STATEMENT: These methods improve the detection of sacroiliac joint structural lesions and might be a useful addition to SIJ MRI protocols both in routine clinical care and as structural outcome measures in clinical trials.

Feasibility of Ethos adaptive treatments of lung tumors and associated quality assurance.

MOTIVATION: Online adaptive radiotherapy with Ethos is based on the anatomy determined from daily cone beam computed tomography (CBCT) images. Dose optimization and computation are performed on the density map of a synthetic CT (sCT), a deformable registration of the initial planning CT (pCT) onto the current CBCT. Large density changes as present in the lung region are challenging the system. METHODS: Treatment plans for Ethos were created and delivered for 1, 2, and 3 cm diameter lung lesions in an anthropomorphic phantom, combining different insets in the pCT and during adaptive and non-adaptive treatment sessions. Primary and secondary dose calculations as well as back-projected dose from portal images were evaluated. RESULTS: Density changes due to changed insets were not considered in the sCTs. This resulted in errors in the dose; for example, -15.9% of the mean dose for a plan when changing from a 3 cm inset in the pCT to 1 cm at the time of treatment. Secondary dose calculation is based on the sCT and could therefore not reveal these dose errors. However, dose calculation on the CBCT, either as a recalculation in the treatment planning system or as pre-treatment quality assurance (QA) before the treatment, indicated the differences. EPID in-vivo QA also reported discrepancies between calculated and delivered dose distributions. CONCLUSIONS: An incorrect density distribution in the sCT has an impact on the dose calculation accuracy in the adaptive treatment workflow with the Ethos system. Additional quality checks of the sCT can detect such errors.

Linac- and CyberKnife-based MRI-only treatment planning of prostate SBRT using an optimized synthetic CT calibration curve.

PURPOSE: CT Hounsfield Units (HUs) are converted to electron density using a calibration curve obtained from physical measurements of an electron density phantom. HU values assigned to an MRI-derived synthetic computed tomography (sCT) may present a different relationship with electron density compared to CT HU. Correct assignment of sCT HU values is critical for accurate dose calculation and delivery. The goals of this work were to develop a sCT calibration curve using patient data acquired on a clinically commissioned CT scanner and assess for CyberKnife- and volumetric modulated arc therapy (VMAT)-based MR-only treatment planning of prostate SBRT. METHODS: Same-day CT and MRI simulation in the treatment position were performed on 10 patients treated with SBRT to the prostate. Dixon in-phase and out-of-phase MRIs were acquired on a 3T scanner using a 3D T1-weighted gradient-echo sequence to generate sCTs using a commercial sCT algorithm. CT and sCT datasets were co-registered and HU values compared using mean absolute error (MAE). An optimized HU-to-density calibration curve was created based on average HU values across an institutional patient database for each of the four sCT tissue types. Clinical CyberKnife and VMAT treatment plans were generated on each patient CT and recomputed onto corresponding sCTs. Dose distributions computed using CT and sCT were compared using gamma criteria and dose-volume-histograms. RESULTS: For the optimized calibration curve, HU values were -96, 37, 204, and 1170 and relative electron densities were 0.95, 1.04, 1.1, and 1.7 for adipose, soft tissue, inner bone, and outer bone, respectively. The proposed sCT protocol produced total MAE of 94 ± 20HU. Gamma values mean ± std (min-max) were 98.9% ± 0.9% (97.1%-100%) and 97.7% ± 1.3% (95.3%-99.3%) for VMAT and CyberKnife plans, respectively. CONCLUSION: MRI-derived sCT using the proposed approach shows excellent dosimetric agreement with conventional CT simulation, demonstrating the feasibility of MRI-derived sCT for prostate SBRT treatment planning.

Evaluating the Hounsfield unit assignment and dose differences between CT-based standard and deep learning-based synthetic CT images for MRI-only radiation therapy of the head and neck.

BACKGROUND: Magnetic resonance image only (MRI-only) simulation for head and neck (H&N) radiotherapy (RT) could allow for single-image modality planning with excellent soft tissue contrast. In the MRI-only simulation workflow, synthetic computed tomography (sCT) is generated from MRI to provide electron density information for dose calculation. Bone/air regions produce little MRI signal which could lead to electron density misclassification in sCT. Establishing the dosimetric impact of this error could inform quality assurance (QA) procedures using MRI-only RT planning or compensatory methods for accurate dosimetric calculation. PURPOSE: The aim of this study was to investigate if Hounsfield unit (HU) voxel misassignments from sCT images result in dosimetric errors in clinical treatment plans. METHODS: Fourteen H&N cancer patients undergoing same-day CT and 3T MRI simulation were retrospectively identified. MRI was deformed to the CT using multimodal deformable image registration. sCTs were generated from T1w DIXON MRIs using a commercially available deep learning-based generator (MRIplanner, Spectronic Medical AB, Helsingborg, Sweden). Tissue voxel assignment was quantified by creating a CT-derived HU threshold contour. CT/sCT HU differences for anatomical/target contours and tissue classification regions including air (<250 HU), adipose tissue (-250 HU to -51 HU), soft tissue (-50 HU to 199 HU), spongy (200 HU to 499 HU) and cortical bone (>500 HU) were quantified. t-test was used to determine if sCT/CT HU differences were significant. The frequency of structures that had a HU difference > 80 HU (the CT window-width setting for intra-cranial structures) was computed to establish structure classification accuracy. Clinical intensity modulated radiation therapy (IMRT) treatment plans created on CT were retrospectively recalculated on sCT images and compared using the gamma metric. RESULTS: The mean ratio of sCT HUs relative to CT for air, adipose tissue, soft tissue, spongy and cortical bone were 1.7 ± 0.3, 1.1 ± 0.1, 1.0 ± 0.1, 0.9 ± 0.1 and 0.8 ± 0.1 (value of 1 indicates perfect agreement). T-tests (significance set at t = 0.05) identified differences in HU values for air, spongy and cortical bone in sCT images compared to CT. The structures with sCT/CT HU differences > 80 HU of note were the left and right (L/R) cochlea and mandible (>79% of the tested cohort), the oral cavity (for 57% of the tested cohort), the epiglottis (for 43% of the tested cohort) and the L/R TM joints (occurring > 29% of the cohort). In the case of the cochlea and TM joints, these structures contain dense bone/air interfaces. In the case of the oral cavity and mandible, these structures suffer the additional challenge of being positionally altered in CT versus MRI simulation (due to a non-MR safe immobilizing bite block requiring absence of bite block in MR). Finally, the epiglottis HU assignment suffers from its small size and unstable positionality. Plans recalculated on sCT yielded global/local gamma pass rates of 95.5% ± 2% (3 mm, 3%) and 92.7% ± 2.1% (2 mm, 2%). The largest mean differences in D95, Dmean , D50 dose volume histogram (DVH) metrics for organ-at-risk (OAR) and planning tumor volumes (PTVs) were 2.3% ± 3.0% and 0.7% ± 1.9% respectively. CONCLUSIONS: In this cohort, HU differences of CT and sCT were observed but did not translate into a reduction in gamma pass rates or differences in average PTV/OAR dose metrics greater than 3%. For sites such as the H&N where there are many tissue interfaces we did not observe large scale dose deviations but further studies using larger retrospective cohorts are merited to establish the variation in sCT dosimetric accuracy which could help to inform QA limits on clinical sCT usage.

Proton range uncertainty caused by synthetic computed tomography generated with deep learning from pelvic magnetic resonance imaging.

BACKGROUND: In proton therapy, it is disputed whether synthetic computed tomography (sCT), derived from magnetic resonance imaging (MRI), permits accurate dose calculations. On the one hand, an MRI-only workflow could eliminate errors caused by, e.g., MRI-CT registration. On the other hand, the extra error would be induced due to an sCT generation model. This work investigated the systematic and random model error induced by sCT generation of a widely discussed deep learning model, pix2pix. MATERIAL AND METHODS: An open-source image dataset of 19 patients with cancer in the pelvis was employed and split into 10, 5, and 4 for training, testing, and validation of the model, respectively. Proton pencil beams (200 MeV) were simulated on the real CT and generated sCT using the tool for particle simulation (TOPAS). Monte Carlo (MC) dropout was used for error estimation (50 random sCT samples). Systematic and random model errors were investigated for sCT generation and dose calculation on sCT. RESULTS: For sCT generation, random model error near the edge of the body (∼200 HU) was higher than that within the body (∼100 HU near the bone edge and <10 HU in soft tissue). The mean absolute error (MAE) was 49 ± 5, 191 ± 23, and 503 ± 70 HU for the whole body, bone, and air in the patient, respectively. Random model errors of the proton range were small (<0.2 mm) for all spots and evenly distributed throughout the proton fields. Systematic errors of the proton range were -1.0(±2.2) mm and 0.4(±0.9)%, respectively, and were unevenly distributed within the proton fields. For 4.5% of the spots, large errors (>5 mm) were found, which may relate to MRI-CT mismatch due to, e.g., registration, MRI distortion anatomical changes, etc. CONCLUSION: The sCT model was shown to be robust, i.e., had a low random model error. However, further investigation to reduce and even predict and manage systematic error is still needed for future MRI-only proton therapy.

Evaluation of MRI-only based online adaptive radiotherapy of abdominal region on MR-linac.

PURPOSE: A hybrid magnetic resonance linear accelerator (MRL) can perform magnetic resonance imaging (MRI) with high soft-tissue contrast to be used for online adaptive radiotherapy (oART). To obtain electron densities needed for the oART dose calculation, a computed tomography (CT) is often deformably registered to MRI. Our aim was to evaluate an MRI-only based synthetic CT (sCT) generation as an alternative to the deformed CT (dCT)-based oART in the abdominal region. METHODS: The study data consisted of 57 patients who were treated on a 0.35 T MRL system mainly for abdominal tumors. Simulation MRI-CT pairs of 43 patients were used for training and validation of a prototype convolutional neural network sCT-generation algorithm, based on HighRes3DNet, for the abdominal region. For remaining test patients, sCT images were produced from simulation MRIs and daily MRIs. The dCT-based plans were re-calculated on sCT with identical calculation parameters. The sCT and dCT were compared in terms of geometric agreement and calculated dose. RESULTS: The mean and one standard deviation of the geometric agreement metrics over dCT-sCT-pairs were: mean error of 8 ± 10 HU, mean absolute error of 49 ± 10 HU, and Dice similarity coefficient of 55 ± 12%, 60 ± 5%, and 82 ± 15% for bone, fat, and lung tissues, respectively. The dose differences between the sCT and dCT-based dose for planning target volumes were 0.5 ± 0.9%, 0.6 ± 0.8%, and 0.5 ± 0.8% at D2% , D50% , and D98% in physical dose and 0.8 ± 1.4%, 0.8 ± 1.2%, and 0.6 ± 1.1% in biologically effective dose (BED). For organs-at-risk, the dose differences of all evaluated dose-volume histogram points were within [-4.5%, 7.8%] and [-1.1 Gy, 3.5 Gy] in both physical dose and BED. CONCLUSIONS: The geometric agreement metrics were within typically reported values and most average relative dose differences were within 1%. Thus, an MRI-only sCT-based approach is a promising alternative to the current clinical practice of the abdominal oART on MRL.

Influence of air mapping errors on the dosimetric accuracy of prostate CBCT-guided online adaptive radiation therapy.

PURPOSE: CBCT-guided online adaptive radiotherapy (oART) plans presently utilize daily synthetic CTs (sCT) that are automatically generated using deformable registration algorithms. These algorithms may have poor performance at reproducing variable volumes of gas present during treatment. Therefore, we have analyzed the air mapping error between the daily CBCTs and the corresponding sCT and explored its dosimetric effect on oART plan calculation. METHODS: Abdominopelvic air volume was contoured on both the daily CBCT images and the corresponding synthetic images for 207 online adaptive pelvic treatments. Air mapping errors were tracked over all fractions. For two case studies representing worst case scenarios, dosimetric effects of air mapping errors were corrected in the sCT images using the daily CBCT air contours, then recalculating dose. Dose volume histogram statistics and 3D gamma passing rates were used to compare the original and air-corrected sCT-based dose calculations. RESULTS: All analyzed patients showed observable air pocket contour differences between the sCT and the CBCT images. The largest air volume difference observed in daily CBCT images for a given patient was 276.3 cc, a difference of more than 386% compared to the sCT. For the two case studies, the largest observed change in DVH metrics was a 2.6% reduction in minimum PTV dose, with all other metrics varying by less than 1.5%. 3D gamma passing rates using 1%/1 mm criteria were above 90% when comparing the uncorrected and corrected dose distributions. CONCLUSION: Current CBCT-based oART workflow can lead to inaccuracies in the mapping of abdominopelvic air pockets from daily CBCT to the sCT images used for the optimization and calculation of the adaptive plan. Despite the large observed mapping errors, the dosimetric effects of such differences on the accuracy of the adapted plan dose calculation are unlikely to cause differences greater than 3% for prostate treatments.

Improving synthetic CT accuracy by combining the benefits of multiple normalized preprocesses.

PURPOSE: To investigate the effect of different normalization preprocesses in deep learning on the accuracy of different tissues in synthetic computed tomography (sCT) and to combine their advantages to improve the accuracy of all tissues. METHODS: The cycle-consistent adversarial network (CycleGAN) model was used to generate sCT images from megavolt cone-beam CT (MVCBCT) images. In this study, 2639 head MVCBCT and CT image pairs from 203 patients were collected as a training set, and 249 image pairs from 29 patients were collected as a test set. We normalized the voxel values in images to 0 to 1 or -1 to 1, using two linear and five nonlinear normalization preprocessing methods to obtain seven data sets and compared the accuracy of different tissues in different sCT obtained from training these data. Finally, to combine the advantages of different normalization preprocessing methods, we obtained sCT_Blur by cropping, stitching, and smoothing (OpenCV's cv2.medianBlur, kernel size 5) each group of sCTs and evaluated its image quality and accuracy of OARs. RESULTS: Different normalization preprocesses made sCT more accurate in different tissues. The proposed sCT_Blur took advantage of multiple normalization preprocessing methods, and all tissues are more accurate than the sCT obtained using a single conventional normalization method. Compared with other sCT images, the structural similarity of sCT_Blur versus CT was improved to 0.906 ± 0.019. The mean absolute errors of the CT numbers were reduced to 15.7 ± 4.1 HU, 23.2 ± 7.1 HU, 11.5 ± 4.1 HU, 212.8 ± 104.6 HU, 219.4 ± 35.1 HU, and 268.8 ± 88.8 HU for the oral cavity, parotid, spinal cord, cavity, mandible, and teeth, respectively. CONCLUSION: The proposed approach combined the advantages of several normalization preprocessing methods to improve the accuracy of all tissues in sCT images, which is promising for improving the accuracy of dose calculations based on CBCT images in adaptive radiotherapy.

Inter-observer variability in library plan selection on iterative CBCT and synthetic CT images of cervical cancer patients.

INTRODUCTION: In the Library-of-Plans (LoP) approach, correct plan selection is essential for delivering radiotherapy treatment accurately. However, poor image quality of the cone-beam computed tomography (CBCT) may introduce inter-observer variability and thereby hamper accurate plan selection. In this study, we investigated whether new techniques to improve the CBCT image quality and improve consistency in plan selection, affects the accuracy of LoP selection in cervical cancer patients. MATERIALS AND METHODS: CBCT images of 12 patients were used to investigate the inter-observer variability of plan selection based on different CBCT image types. Six observers were asked to individually select a plan based on clinical X-ray Volumetric Imaging (XVI) CBCT, iterative reconstructed CBCT (iCBCT) and synthetic CTs (sCT). Selections were performed before and after a consensus meeting with the entire group, in which guidelines were created. A scoring by all observers on the image quality and plan selection procedure was also included. For plan selection, Fleiss' kappa (κ) statistical test was used to determine the inter-observer variability within one image type. RESULTS: The agreement between observers was significantly higher on sCT compared to CBCT. The consensus meeting improved the duration and inter-observer variability. In this manuscript, the guidelines attributed the overall results in the plan selection. Before the meeting, the gold standard was selected in 76% of the cases on XVI CBCT, 74% on iCBCT, and 76% on sCT. After the meeting, the gold standard was selected in 83% of the cases on XVI CBCT, 81% on iCBCT, and 90% on sCT. CONCLUSION: The use of sCTs can increase the agreement of plan selection among observers and the gold standard was indicated to be selected more often. It is important that clear guidelines for plan selection are implemented in order to benefit from the increased image quality, accurate selection, and decrease inter-observer variability.

Frequency-Domain-Based Structure Losses for CycleGAN-Based Cone-Beam Computed Tomography Translation.

Research exploring CycleGAN-based synthetic image generation has recently accelerated in the medical community due to its ability to leverage unpaired images effectively. However, a commonly established drawback of the CycleGAN, the introduction of artifacts in generated images, makes it unreliable for medical imaging use cases. In an attempt to address this, we explore the effect of structure losses on the CycleGAN and propose a generalized frequency-based loss that aims at preserving the content in the frequency domain. We apply this loss to the use-case of cone-beam computed tomography (CBCT) translation to computed tomography (CT)-like quality. Synthetic CT (sCT) images generated from our methods are compared against baseline CycleGAN along with other existing structure losses proposed in the literature. Our methods (MAE: 85.5, MSE: 20433, NMSE: 0.026, PSNR: 30.02, SSIM: 0.935) quantitatively and qualitatively improve over the baseline CycleGAN (MAE: 88.8, MSE: 24244, NMSE: 0.03, PSNR: 29.37, SSIM: 0.935) across all investigated metrics and are more robust than existing methods. Furthermore, no observable artifacts or loss in image quality were observed. Finally, we demonstrated that sCTs generated using our methods have superior performance compared to the original CBCT images on selected downstream tasks.

The performance of machine learning approaches for attenuation correction of PET in neuroimaging: A meta-analysis.

PURPOSE: This systematic review provides a consensus on the clinical feasibility of machine learning (ML) methods for brain PET attenuation correction (AC). Performance of ML-AC were compared to clinical standards. METHODS: Two hundred and eighty studies were identified through electronic searches of brain PET studies published between January 1, 2008, and August 1, 2022. Reported outcomes for image quality, tissue classification performance, regional and global bias were extracted to evaluate ML-AC performance. Methodological quality of included studies and the quality of evidence of analysed outcomes were assessed using QUADAS-2 and GRADE, respectively. RESULTS: A total of 19 studies (2371 participants) met the inclusion criteria. Overall, the global bias of ML methods was 0.76 ± 1.2%. For image quality, the relative mean square error (RMSE) was 0.20 ± 0.4 while for tissues classification, the Dice similarity coefficient (DSC) for bone/soft tissue/air were 0.82 ± 0.1 / 0.95 ± 0.03 / 0.85 ± 0.14. CONCLUSIONS: In general, ML-AC performance is within acceptable limits for clinical PET imaging. The sparse information on ML-AC robustness and its limited qualitative clinical evaluation may hinder clinical implementation in neuroimaging, especially for PET/MRI or emerging brain PET systems where standard AC approaches are not readily available.

Synthetic CT for the planning of MR-HIFU treatment of bone metastases in pelvic and femoral bones: a feasibility study.

OBJECTIVES: Visualization of the bone distribution is an important prerequisite for MRI-guided high-intensity focused ultrasound (MRI-HIFU) treatment planning of bone metastases. In this context, we evaluated MRI-based synthetic CT (sCT) imaging for the visualization of cortical bone. METHODS: MR and CT images of nine patients with pelvic and femoral metastases were retrospectively analyzed in this study. The metastatic lesions were osteolytic, osteoblastic or mixed. sCT were generated from pre-treatment or treatment MR images using a UNet-like neural network. sCT was qualitatively and quantitatively compared to CT in the bone (pelvis or femur) containing the metastasis and in a region of interest placed on the metastasis itself, through mean absolute difference (MAD), mean difference (MD), Dice similarity coefficient (DSC), and root mean square surface distance (RMSD). RESULTS: The dataset consisted of 3 osteolytic, 4 osteoblastic and 2 mixed metastases. For most patients, the general morphology of the bone was well represented in the sCT images and osteolytic, osteoblastic and mixed lesions could be discriminated. Despite an average timespan between MR and CT acquisitions of 61 days, in bone, the average (± standard deviation) MAD was 116 ± 26 HU, MD - 14 ± 66 HU, DSC 0.85 ± 0.05, and RMSD 2.05 ± 0.48 mm and, in the lesion, MAD was 132 ± 62 HU, MD - 31 ± 106 HU, DSC 0.75 ± 0.2, and RMSD 2.73 ± 2.28 mm. CONCLUSIONS: Synthetic CT images adequately depicted the cancellous and cortical bone distribution in the different lesion types, which shows its potential for MRI-HIFU treatment planning. KEY POINTS: • Synthetic computed tomography was able to depict bone distribution in metastatic lesions. • Synthetic computed tomography images intrinsically aligned with treatment MR images may have the potential to facilitate MR-HIFU treatment planning of bone metastases, by combining visualization of soft tissues and cancellous and cortical bone.

GAN for synthesizing CT from T2-weighted MRI data towards MR-guided radiation treatment.

OBJECTIVE: In medical domain, cross-modality image synthesis suffers from multiple issues , such as context-misalignment, image distortion, image blurriness, and loss of details. The fundamental objective behind this study is to address these issues in estimating synthetic Computed tomography (sCT) scans from T2-weighted Magnetic Resonance Imaging (MRI) scans to achieve MRI-guided Radiation Treatment (RT). MATERIALS AND METHODS: We proposed a conditional generative adversarial network (cGAN) with multiple residual blocks to estimate sCT from T2-weighted MRI scans using 367 paired brain MR-CT images dataset. Few state-of-the-art deep learning models were implemented to generate sCT including Pix2Pix model, U-Net model, autoencoder model and their results were compared, respectively. RESULTS: Results with paired MR-CT image dataset demonstrate that the proposed model with nine residual blocks in generator architecture results in the smallest mean absolute error (MAE) value of [Formula: see text], and mean squared error (MSE) value of [Formula: see text], and produces the largest Pearson correlation coefficient (PCC) value of [Formula: see text], SSIM value of [Formula: see text] and peak signal-to-noise ratio (PSNR) value of [Formula: see text], respectively. We qualitatively evaluated our result by visual comparisons of generated sCT to original CT of respective MRI input. DISCUSSION: The quantitative and qualitative comparison of this work demonstrates that deep learning-based cGAN model can be used to estimate sCT scan from a reference T2 weighted MRI scan. The overall accuracy of our proposed model outperforms different state-of-the-art deep learning-based models.

Head and neck cancer patient positioning using synthetic CT data in MRI-only radiation therapy.

PURPOSE: The accuracy and precision of patient positioning is crucial in radiotherapy; however, there are no publications available using synthetic computed tomography (sCT) that evaluate rotations in head and neck (H&N) patients positioning or the effect of translation and rotation combined. The aim of this work was to evaluate the differences between using sCT with the CT for 2D- and 3D-patient positioning in a magnetic resonance imaging (MRI)-only workflow. METHODS: This study included 14 H&N cancer patients, with generated sCT data (MRI Planner v2.2) and the CT deformably registered to the MRI. Patient positioning was evaluated by comparing sCT against CT data: 3D cone beam CT (CBCT) was registered to the deformed CT (dCT) and sCT in six degrees of freedom (DoF) with a rigid auto-registration algorithm and bone threshold, and 2D deformed digital reconstructed radiographs (dDRR) and synthetic DRRs (sDRR) were manually registered to orthogonal projections in five DoF by six blinded observers. The difference in displacement in all DoF were calculated for dCT and sCT, as well as for dDRR and sDRR. The interobserver variation was evaluated by separate application of the paired dDRR and sDRR registration matrices to the original coordinates of the planning target volume (PTV) structures and calculation of the Euclidean distance between the corresponding points. The Dice similarity coefficient (DSC) was calculated between dDRR/sDRR-registered PTVs. RESULTS: The mean difference in patient positioning using CBCT was <0.7 mm and <0.3° and using orthogonal projections <0.4 mm and <0.2° in all directions. The maximum Euclidean distance was 5.1 mm, the corresponding mean (1SD) Euclidean distance and mean DSC were 3.5 ± 0.7 mm and 0.93, respectively. CONCLUSIONS: This study shows that the sCT-based patient positioning gives a comparable result with that based on CT images, allowing sCT to replace CT as reference for patient treatment positioning.

Clinical commissioning of an adaptive radiotherapy platform: Results and recommendations.

Online adaptive radiotherapy platforms present a unique challenge for commissioning as guidance is lacking and specialized adaptive equipment, such as deformable phantoms, are rare. We designed a novel adaptive commissioning process consisting of end-to-end tests using standard clinical resources. These tests were designed to simulate anatomical changes regularly observed at patient treatments. The test results will inform users of the magnitude of uncertainty from on-treatment changes during the adaptive workflow and the limitations of their systems. We implemented these tests for the cone-beam computed tomography (CT)-based Varian Ethos online adaptive platform. Many adaptive platforms perform online dose calculation on a synthetic CT (synCT). To assess the impact of the synCT generation and online dose calculation on dosimetric accuracy, we conducted end-to-end tests using commonly available equipment: a CIRS IMRT Thorax phantom, PinPoint ionization chamber, Gafchromic film, and bolus. Four clinical scenarios were evaluated: weight gain and weight loss were simulated by adding and removing bolus, internal target shifts were simulated by editing the CTV during the adaptive workflow to displace it, and changes in gas were simulated by removing and reinserting rods in varying phantom locations. The effect of overriding gas pockets during planning was also assessed. All point dose measurements agreed within 2.7% of the calculated dose, with one exception: a scenario simulating gas present in the planning CT, not overridden during planning, and dissipating at treatment. Relative film measurements passed gamma analysis (3%/3 mm criteria) for all scenarios. Our process validated the Ethos dose calculation for online adapted treatment plans. Based on our results, we made several recommendations for our clinical adaptive workflow. This commissioning process used commonly available equipment and, therefore, can be applied in other clinics for their respective online adaptive platforms.

Assessment of CBCT-based synthetic CT generation accuracy for adaptive radiotherapy planning.

PURPOSE: Cone-beam CT (CBCT)-based synthetic CT (sCT) dose calculation has the potential to make the adaptive radiotherapy (ART) pathway more efficient while removing subjectivity. This study assessed four sCT generation methods using 15 head-and-neck rescanned ART patients. Each patient's planning CT (pCT), rescan CT (rCT), and CBCT post-rCT was acquired with the CBCT deformably registered to the rCT (dCBCT). METHODS: The four methods investigated were as follows: method 1-deformably registering the pCT to the dCBCT. Method 2-assigning six mass density values to the dCBCT. Method 3-iteratively removing artifacts and correcting the dCBCT Hounsfield units (HU). Method 4-using a cycle general adversarial network machine learning model (trained with 45 paired pCT and CBCT). Treatment plans were created on the rCT and recalculated on each sCT. Planning target volume (PTV) and organ-at-risk (OAR) structures were contoured by clinicians on the rCT (high-dose PTV, low-dose PTV, spinal canal, larynx, brainstem, and parotids) to allow the assessment of dose-volume histogram statistics at clinically relevant points. RESULTS: The HU mean absolute error (MAE) and minimum dose gamma index pass rate (2%/2 mm) were calculated, and the generation time was measured for 15 patients using the rCT as the comparator. For methods 1-4 the MAE, gamma index analysis, and generation time were as follows: 59.7 HU, 100.0%, and 143 s; 164.2 HU, 95.2%, and 232 s; 75.7 HU, 99.9%, and 153 s; and 79.4 HU, 99.8%, and 112 s, respectively. Dose differences for PTVs and OARs were all <0.3 Gy except for method 2 (<0.5 Gy). CONCLUSION: All methods were considered clinically viable. The machine learning method was found to be most suitable for clinical implementation due to its high dosimetric accuracy and short generation time. Further investigation is required for larger anatomical changes between the CBCT and pCT and for other anatomical sites.

Abdominopelvic MR to CT registration using a synthetic CT intermediate.

Accurate coregistration of computed tomography (CT) and magnetic resonance (MR) imaging can provide clinically relevant and complementary information and can serve to facilitate multiple clinical tasks including surgical and radiation treatment planning, and generating a virtual Positron Emission Tomography (PET)/MR for the sites that do not have a PET/MR system available. Despite the long-standing interest in multimodality co-registration, a robust, routine clinical solution remains an unmet need. Part of the challenge may be the use of mutual information (MI) maximization and local phase difference (LPD) as similarity metrics, which have limited robustness, efficiency, and are difficult to optimize. Accordingly, we propose registering MR to CT by mapping the MR to a synthetic CT intermediate (sCT) and further using it in a sCT-CT deformable image registration (DIR) that minimizes the sum of squared differences. The resultant deformation field of a sCT-CT DIR is applied to the MRI to register it with the CT. Twenty-five sets of abdominopelvic imaging data are used for evaluation. The proposed method is compared to standard MI- and LPD-based methods, and the multimodality DIR provided by a state of the art, commercially available FDA-cleared clinical software package. The results are compared using global similarity metrics, Modified Hausdorff Distance, and Dice Similarity Index on six structures. Further, four physicians visually assessed and scored registered images for their registration accuracy. As evident from both quantitative and qualitative evaluation, the proposed method achieved registration accuracy superior to LPD- and MI-based methods and can refine the results of the commercial package DIR when using its results as a starting point. Supported by these, this manuscript concludes the proposed registration method is more robust, accurate, and efficient than the MI- and LPD-based methods.

Development of an anthropomorphic multimodality pelvic phantom for quantitative evaluation of a deep-learning-based synthetic computed tomography generation technique.

PURPOSE: The objective of this study was to fabricate an anthropomorphic multimodality pelvic phantom to evaluate a deep-learning-based synthetic computed tomography (CT) algorithm for magnetic resonance (MR)-only radiotherapy. METHODS: Polyurethane-based and silicone-based materials with various silicone oil concentrations were scanned using 0.35 T MR and CT scanner to determine the tissue surrogate. Five tissue surrogates were determined by comparing the organ intensity with patient CT and MR images. Patient-specific organ modeling for three-dimensional printing was performed by manually delineating the structures of interest. The phantom was finally fabricated by casting materials for each structure. For the quantitative evaluation, the mean and standard deviations were measured within the regions of interest on the MR, simulation CT (CTsim ), and synthetic CT (CTsyn ) images. Intensity-modulated radiation therapy plans were generated to assess the impact of different electron density assignments on plan quality using CTsim and CTsyn . The dose calculation accuracy was investigated in terms of gamma analysis and dose-volume histogram parameters. RESULTS: For the prostate site, the mean MR intensities for the patient and phantom were 78.1 ± 13.8 and 86.5 ± 19.3, respectively. The mean intensity of the synthetic image was 30.9 Hounsfield unit (HU), which was comparable to that of the real CT phantom image. The original and synthetic CT intensities of the fat tissue in the phantom were -105.8 ± 4.9 HU and -107.8 ± 7.8 HU, respectively. For the target volume, the difference in D95% was 0.32 Gy using CTsyn with respect to CTsim values. The V65Gy values for the bladder in the plans using CTsim and CTsyn were 0.31% and 0.15%, respectively. CONCLUSION: This work demonstrated that the anthropomorphic phantom was physiologically and geometrically similar to the patient organs and was employed to quantitatively evaluate the deep-learning-based synthetic CT algorithm.

Development of an unsupervised cycle contrastive unpaired translation network for MRI-to-CT synthesis.

PURPOSE: The purpose of this work is to develop and evaluate a novel cycle-contrastive unpaired translation network (cycleCUT) for synthetic computed tomography (sCT) generation from T1-weighted magnetic resonance images (MRI). METHODS: The cycleCUT proposed in this work integrated the contrastive learning module from contrastive unpaired translation network (CUT) into the cycle-consistent generative adversarial network (cycleGAN) framework to effectively achieve unsupervised CT synthesis from MRI. The diagnostic MRI and radiotherapy planning CT images of 24 brain cancer patients were obtained and reshuffled to train the network. For comparison, the traditional cycleGAN and CUT were also implemented. The sCT images were then imported into a treatment planning system to verify their feasibility for radiotherapy planning. The mean absolute error (MAE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) between the sCT and the corresponding real CT images were calculated. Gamma analysis between sCT- and CT-based dose distributions was also conducted. RESULTS: Quantitative evaluation of an independent test set of six patients showed that the average MAE was 69.62 ± 5.68 Hounsfield Units (HU) for the proposed cycleCUT, significantly (p-value < 0.05) lower than that for cycleGAN (77.02 ± 6.00 HU) and CUT (78.05 ± 8.29). The average PSNR was 28.73 ± 0.46 decibels (dB) for cycleCUT, significantly larger than that for cycleGAN (27.96 ± 0.49 dB) and CUT (27.95 ± 0.69 dB). The average SSIM for cycleCUT (0.918 ± 0.012) was also significantly higher than that for cycleGAN (0.906 ± 0.012) and CUT (0.903 ± 0.015). Regarding gamma analysis, cycleCUT achieved the highest passing rate (97.95 ± 1.24% at the 2%/2 mm criteria and 10% dose threshold) but was not significantly different from the others. CONCLUSION: The proposed cycleCUT could be effectively trained using unaligned image data, and could generate better sCT images than cycleGAN and CUT in terms of HU number accuracy and fine structural details.