Deep learning-aided respiratory motion compensation in PET/CT: addressing motion induced resolution loss, attenuation correction artifacts and PET-CT misalignment.

PURPOSE: Respiratory motion (RM) significantly impacts image quality in thoracoabdominal PET/CT imaging. This study introduces a unified data-driven respiratory motion correction (uRMC) method, utilizing deep learning neural networks, to solve all the major issues caused by RM, i.e., PET resolution loss, attenuation correction artifacts, and PET-CT misalignment. METHODS: In a retrospective study, 737 patients underwent [18F]FDG PET/CT scans using the uMI Panorama PET/CT scanner. Ninety-nine patients, who also had respiration monitoring device (VSM), formed the validation set. The remaining data of the 638 patients were used to train neural networks used in the uRMC. The uRMC primarily consists of three key components: (1) data-driven respiratory signal extraction, (2) attenuation map generation, and (3) PET-CT alignment. SUV metrics were calculated within 906 lesions for three approaches, i.e., data-driven uRMC (proposed), VSM-based uRMC, and OSEM without motion correction (NMC). RM magnitude of major organs were estimated. RESULTS: uRMC enhanced diagnostic capabilities by revealing previously undetected lesions, sharpening lesion contours, increasing SUV values, and improving PET-CT alignment. Compared to NMC, uRMC showed increases of 10% and 17% in SUVmax and SUVmean across 906 lesions. Sub-group analysis showed significant SUV increases in small and medium-sized lesions with uRMC. Minor differences were found between VSM-based and data-driven uRMC methods, with the SUVmax was found statistically marginal significant or insignificant between the two methods. The study observed varied motion amplitudes in major organs, typically ranging from 10 to 20 mm. CONCLUSION: A data-driven solution for respiratory motion in PET/CT has been developed, validated and evaluated. To the best of our knowledge, this is the first unified solution that compensates for the motion blur within PET, the attenuation mismatch artifacts caused by PET-CT misalignment, and the misalignment between PET and CT.

Development and evaluation of two open-source nnU-Net models for automatic segmentation of lung tumors on PET and CT images with and without respiratory motion compensation.

OBJECTIVES: In lung cancer, one of the main limitations for the optimal integration of the biological and anatomical information derived from Positron Emission Tomography (PET) and Computed Tomography (CT) is the time and expertise required for the evaluation of the different respiratory phases. In this study, we present two open-source models able to automatically segment lung tumors on PET and CT, with and without motion compensation. MATERIALS AND METHODS: This study involved time-bin gated (4D) and non-gated (3D) PET/CT images from two prospective lung cancer cohorts (Trials 108237 and 108472) and one retrospective. For model construction, the ground truth (GT) was defined by consensus of two experts, and the nnU-Net with 5-fold cross-validation was applied to 560 4D-images for PET and 100 3D-images for CT. The test sets included 270 4D- images and 19 3D-images for PET and 80 4D-images and 27 3D-images for CT, recruited at 10 different centres. RESULTS: In the performance evaluation with the multicentre test sets, the Dice Similarity Coefficients (DSC) obtained for our PET model were DSC(4D-PET) = 0.74 ± 0.06, improving 19% relative to the DSC between experts and DSC(3D-PET) = 0.82 ± 0.11. The performance for CT was DSC(4D-CT) = 0.61 ± 0.28 and DSC(3D-CT) = 0.63 ± 0.34, improving 4% and 15% relative to DSC between experts. CONCLUSIONS: Performance evaluation demonstrated that the automatic segmentation models have the potential to achieve accuracy comparable to manual segmentation and thus hold promise for clinical application. The resulting models can be freely downloaded and employed to support the integration of 3D- or 4D- PET/CT and to facilitate the evaluation of its impact on lung cancer clinical practice. CLINICAL RELEVANCE STATEMENT: We provide two open-source nnU-Net models for the automatic segmentation of lung tumors on PET/CT to facilitate the optimal integration of biological and anatomical information in clinical practice. The models have superior performance compared to the variability observed in manual segmentations by the different experts for images with and without motion compensation, allowing to take advantage in the clinical practice of the more accurate and robust 4D-quantification. KEY POINTS: Lung tumor segmentation on PET/CT imaging is limited by respiratory motion and manual delineation is time consuming and suffer from inter- and intra-variability. Our segmentation models had superior performance compared to the manual segmentations by different experts. Automating PET image segmentation allows for easier clinical implementation of biological information.

Respiratory motion-corrected T1 mapping of the abdomen.

OBJECTIVE: The purpose of this study was to investigate an approach for motion-corrected T1 mapping of the abdomen that allows for free breathing data acquisition with 100% scan efficiency. MATERIALS AND METHODS: Data were acquired using a continuous golden radial trajectory and multiple inversion pulses. For the correction of respiratory motion, motion estimation based on a surrogate was performed from the same data used for T1 mapping. Image-based self-navigation allowed for binning and reconstruction of respiratory-resolved images, which were used for the estimation of respiratory motion fields. Finally, motion-corrected T1 maps were calculated from the data applying the estimated motion fields. The method was evaluated in five healthy volunteers. For the assessment of the image-based navigator, we compared it to a simultaneously acquired ultrawide band radar signal. Motion-corrected T1 maps were evaluated qualitatively and quantitatively for different scan times. RESULTS: For all volunteers, the motion-corrected T1 maps showed fewer motion artifacts in the liver as well as sharper kidney structures and blood vessels compared to uncorrected T1 maps. Moreover, the relative error to the reference breathhold T1 maps could be reduced from up to 25% for the uncorrected T1 maps to below 10% for the motion-corrected maps for the average value of a region of interest, while the scan time could be reduced to 6-8 s. DISCUSSION: The proposed approach allows for respiratory motion-corrected T1 mapping in the abdomen and ensures accurate T1 maps without the need for any breathholds.

A robust treatment planning approach for chest motion in postmastectomy chest wall intensity modulated radiation therapy.

PURPOSE: Chest wall postmastectomy radiation therapy (PMRT) should consider the effects of chest wall respiratory motion. The purpose of this study is to evaluate the effectiveness of robustness planning intensity modulated radiation therapy (IMRT) for respiratory movement, considering respiratory motion as a setup error. MATERIAL AND METHODS: This study analyzed 20 patients who underwent PMRT (10 left and 10 right chest walls). The following three treatment plans were created for each case and compared. The treatment plans are a planning target volume (PTV) plan (PP) that covers the PTV within the body contour with the prescribed dose, a virtual bolus plan (VP) that sets a virtual bolus in contact with the body surface and prescribing the dose that includes the PTV outside the body contour, and a robust plan (RP) that considers respiratory movement as a setup uncertainty and performs robust optimization. The isocenter was shifted to reproduce the chest wall motion pattern and the doses were recalculated for comparison for each treatment plan. RESULT: No significant difference was found between the PP and the RP in terms of the tumor dose in the treatment plan. In contrast, VP had 3.5% higher PTV Dmax and 5.5% lower PTV V95% than RP (p < 0.001). The RP demonstrated significantly higher lung V20Gy and Dmean by 1.4% and 0.4 Gy, respectively, than the PP. The RP showed smaller changes in dose distribution affected by chest wall motion and significantly higher tumor dose coverage than the PP and VP. CONCLUSION: We revealed that the RP demonstrated comparable tumor doses to the PP in treatment planning and was robust for respiratory motion compared to both the PP and the VP. However, the organ at risk dose in the RP was slightly higher; therefore, its clinical use should be carefully considered.

Feasibility of surface-guidance combined with CBCT for intra-fractional breath-hold motion management during Ethos RT.

PURPOSE: High-quality CBCT and AI-enhanced adaptive planning techniques allow CBCT-guided stereotactic adaptive radiotherapy (CT-STAR) to account for inter-fractional anatomic changes. Studies of intra-fractional respiratory motion management with a surface imaging solution for CT-STAR have not been fully conducted. We investigated intra-fractional motion management in breath-hold Ethos-based CT-STAR and CT-SBRT (stereotactic body non-adaptive radiotherapy) using optical surface imaging combined with onboard CBCTs. METHODS: Ten cancer patients with mobile lower lung or upper abdominal malignancies participated in an IRB-approved clinical trial (Phase I) of optical surface image-guided Ethos CT-STAR/SBRT. In the clinical trial, a pre-configured gating window (± 2 mm in AP direction) on optical surface imaging was used for manually triggering intra-fractional CBCT acquisition and treatment beam irradiation during breath-hold (seven patients for the end of exhalation and three patients for the end of inhalation). Two inter-fractional CBCTs at the ends of exhalation and inhalation in each fraction were acquired to verify the primary direction and range of the tumor/imaging-surrogate (donut-shaped fiducial) motion. Intra-fractional CBCTs were used to quantify the residual motion of the tumor/imaging-surrogate within the pre-configured breath-hold window in the AP direction. Fifty fractions of Ethos RT were delivered under surface image-guidance: Thirty-two fractions with CT-STAR (adaptive RT) and 18 fractions with CT-SBRT (non-adaptive RT). The residual motion of the tumor was quantified by determining variations in the tumor centroid position. The dosimetric impact on target coverage was calculated based on the residual motion. RESULTS: We used 46 fractions for the analysis of intra-fractional residual motion and 43 fractions for the inter-fractional motion analysis due to study constraints. Using the image registration method, 43 pairs of inter-fractional CBCTs and 100 intra-fractional CBCTs attached to dose maps were analyzed. In the motion range study (image registration) from the inter-fractional CBCTs, the primary motion (mean ± std) was 16.6 ± 9.2 mm in the SI direction (magnitude: 26.4 ± 11.3 mm) for the tumors and 15.5 ± 7.3 mm in the AP direction (magnitude: 20.4 ± 7.0 mm) for the imaging-surrogate, respectively. The residual motion of the tumor (image registration) from intra-fractional breath-hold CBCTs was 2.2 ± 2.0 mm for SI, 1.4 ± 1.4 mm for RL, and 1.3 ± 1.3 mm for AP directions (magnitude: 3.5 ± 2.1 mm). The ratio of the actual dose coverage to 99%, 90%, and 50% of the target volume decreased by 0.95 ± 0.11, 0.96 ± 0.10, 0.99 ± 0.05, respectively. The mean percentage of the target volume covered by the prescribed dose decreased by 2.8 ± 4.4%. CONCLUSION: We demonstrated the intra-fractional motion-managed treatment strategy in breath-hold Ethos CT-STAR/SBRT using optical surface imaging and CBCT. While the controlled residual tumor motion measured at 3.5 mm exceeded the predetermined setup value of 2 mm, it is important to note that this motion still fell within the clinically acceptable range defined by the PTV margin of 5 mm. Nonetheless, additional caution is needed with intra-fractional motion management in breath-hold Ethos CT-STAR/SBRT using optical surface imaging and CBCT.

Analysis of respiratory-induced motion trajectories of individual liver segments in patients with hepatocellular carcinoma.

PURPOSE: To analyze the respiratory-induced motion trajectories of each liver segment for hepatocellular carcinoma (HCC) to derive a more accurate internal margin and optimize treatment protocol selection. MATERIALS AND METHODS: Ten-phase-gated four-dimensional computed tomography (4DCT) scans of 14 patients with HCC were analyzed. For each patient, eight representative regions of interest (ROI) were delineated on each liver segment in all 10 phases. The coordinates of the center of gravity of each ROI were obtained for each phase, and then the respiratory motion in the left-right (LR), anteroposterior (AP), and craniocaudal (CC) directions was analyzed. Two sets of motion in each direction were also compared in terms of only two extreme phases and all 10 phases. RESULTS: Motion of less than 5 mm was detected in 12 (86%) and 10 patients (71%) in the LR and AP directions, respectively, while none in the CC direction. Motion was largest in the CC direction with a maximal value of 19.5 mm, with significant differences between liver segment 7 (S7) and other segments: S1 (p < 0.036), S2 (p < 0.041), S3 (p < 0.016), S4 (p < 0.041), and S5 (p < 0.027). Of the 112 segments, hysteresis >1 mm was observed in 4 (4%), 2 (2%), and 15 (13%) in the LR, AP, and CC directions, respectively, with a maximal value of 5.0 mm in the CC direction. CONCLUSION: A significant amount of respiratory motion was detected in the CC direction, especially in S7, and S8. Despite the small effect of hysteresis, it can be observed specifically in the right lobe. Therefore, caution is required when using 4DCT to determine IM using only end-inspiration and end-expiration. Understanding the respiratory motion in individual liver segments can be helpful when selecting an appropriate treatment protocol.

Novel utilization and quantification of Xsight diaphragm tracking for respiratory motion compensation in Cyberknife Synchrony treatment of liver tumors.

PURPOSE: The Xsight lung tracking system (XLTS) utilizes an advanced image processing algorithm to precisely identify the position of a tumor and determine its location in orthogonal x-ray images, instead of finding fiducials, thereby minimizing the risk of fiducial insertion-related side effects. To assess and gauge the effectiveness of CyberKnife Synchrony in treating liver tumors located in close proximity to or within the diaphragm, we employed the Xsight diaphragm tracking system (XDTS), which was based on the XLTS. METHODS: We looked back at the treatment logs of 11 patients (8/11 [XDTS], 3/11 [Fiducial-based Target Tracking System-FTTS]) who had liver tumors in close proximity to or within the diaphragm. And the results are compared with the patients who undergo the treatment of FTTS. The breathing data information was calculated as a rolling average to reduce the effect of irregular breathing. We tested the tracking accuracy with a dynamic phantom (18023-A) on the basis of patient-specific respiratory curve. RESULTS: The average values for the XDTS and FTTS correlation errors were 1.38 ± 0.65  versus 1.50 ± 0.26 mm (superior-inferior), 1.28 ± 0.48  versus 0.40 ± 0.09 mm (left-right), and 0.96 ± 0.32  versus 0.47 ± 0.10 mm(anterior-posterior), respectively. The prediction errors for two methods of 0.65 ± 0.16  versus 5.48 ± 3.33 mm in the S-I direction, 0.34 ± 0.10  versus 1.41 ± 0.76 mm in the A-P direction, and 0.22 ± 0.072  versus 1.22 ± 0.48 mm in the L-R direction. The coverage rate of FTTS slightly less than that of XDTS, such as 96.53 ± 8.19% (FTTS) versus 98.03 ± 1.54 (XDTS). The prediction error, the motion amplitude, and the variation of the respiratory center phase were strongly related to each other. Especially, the higher the amplitude and the variation, the higher the prediction error. CONCLUSION: The diaphragm has the potential to serve as an alternative to gold fiducial markers for detecting liver tumors in close proximity or within it. We also found that we needed to reduce the motion amplitude and train the respiration of the patients during liver radiotherapy, as well as control and evaluate their breathing.

Compensation for respiratory motion-induced signal loss and phase corruption in free-breathing self-navigated cine DENSE using deep learning.

PURPOSE: To introduce a model that describes the effects of rigid translation due to respiratory motion in displacement encoding with stimulated echoes (DENSE) and to use the model to develop a deep convolutional neural network to aid in first-order respiratory motion compensation for self-navigated free-breathing cine DENSE of the heart. METHODS: The motion model includes conventional position shifts of magnetization and further describes the phase shift of the stimulated echo due to breathing. These image-domain effects correspond to linear and constant phase errors, respectively, in k-space. The model was validated using phantom experiments and Bloch-equation simulations and was used along with the simulation of respiratory motion to generate synthetic images with phase-shift artifacts to train a U-Net, DENSE-RESP-NET, to perform motion correction. DENSE-RESP-NET-corrected self-navigated free-breathing DENSE was evaluated in human subjects through comparisons with signal averaging, uncorrected self-navigated free-breathing DENSE, and breath-hold DENSE. RESULTS: Phantom experiments and Bloch-equation simulations showed that breathing-induced constant phase errors in segmented DENSE leads to signal loss in magnitude images and phase corruption in phase images of the stimulated echo, and that these artifacts can be corrected using the known respiratory motion and the model. For self-navigated free-breathing DENSE where the respiratory motion is not known, DENSE-RESP-NET corrected the signal loss and phase-corruption artifacts and provided reliable strain measurements for systolic and diastolic parameters. CONCLUSION: DENSE-RESP-NET is an effective method to correct for breathing-associated constant phase errors. DENSE-RESP-NET used in concert with self-navigation methods provides reliable free-breathing DENSE myocardial strain measurement.

Retrospective motion correction through multi-average k-space data elimination (REMAKE) for free-breathing cardiac cine imaging.

PURPOSE: To develop a motion-robust reconstruction technique for free-breathing cine imaging with multiple averages. METHOD: Retrospective motion correction through multiple average k-space data elimination (REMAKE) was developed using iterative removal of k-space segments (from individual k-space samples) that contribute most to motion corruption while combining any remaining segments across multiple signal averages. A variant of REMAKE, termed REMAKE+, was developed to address any losses in SNR due to k-space information removal. With REMAKE+, multiple reconstructions using different initial conditions were performed, co-registered, and averaged. Both techniques were validated against clinical "standard" signal averaging reconstruction in a static phantom (with simulated motion) and 15 patients undergoing free-breathing cine imaging with multiple averages. Quantitative analysis of myocardial sharpness, blood/myocardial SNR, myocardial-blood contrast-to-noise ratio (CNR), as well as subjective assessment of image quality and rate of diagnostic quality images were performed. RESULTS: In phantom, motion artifacts using "standard" (RMS error [RMSE]: 2.2 ± 0.5) were substantially reduced using REMAKE/REMAKE+ (RMSE: 1.5 ± 0.4/1.0 ± 0.4, p < 0.01). In patients, REMAKE/REMAKE+ led to higher myocardial sharpness (0.79 ± 0.09/0.79 ± 0.1 vs. 0.74 ± 0.12 for "standard", p = 0.004/0.04), higher image quality (1.8 ± 0.2/1.9 ± 0.2 vs. 1.6 ± 0.4 for "standard", p = 0.02/0.008), and a higher rate of diagnostic quality images (99%/100% vs. 94% for "standard"). Blood/myocardial SNR for "standard" (94 ± 30/33 ± 10) was higher vs. REMAKE (80 ± 25/28 ± 8, p = 0.002/0.005) and tended to be lower vs. REMAKE+ (105 ± 33/36 ± 12, p = 0.02/0.06). Myocardial-blood CNR for "standard" (61 ± 22) was higher vs. REMAKE (53 ± 19, p = 0.003) and lower vs. REMAKE+ (69 ± 24, p = 0.007). CONCLUSIONS: Compared to "standard" signal averaging reconstruction, REMAKE and REMAKE+ provide improved myocardial sharpness, image quality, and rate of diagnostic quality images.

Live-view 4D GRASP MRI: A framework for robust real-time respiratory motion tracking with a sub-second imaging latency.

PURPOSE: To propose a framework called live-view golden-angle radial sparse parallel (GRASP) MRI for low-latency and high-fidelity real-time volumetric MRI. METHODS: Live-view GRASP MRI has two stages. The first one is called an off-view stage and the second one is called a live-view stage. In the off-view stage, 3D k-space data and 2D navigators are acquired alternatively using a new navi-stack-of-stars sampling scheme. A 4D motion database is then generated that contains time-resolved MR images at a sub-second temporal resolution, and each image is linked to a 2D navigator. In the live-view stage, only 2D navigators are acquired. At each time point, a live-view 2D navigator is matched to all the off-view 2D navigators. A 3D image that is linked to the best-matched off-view 2D navigator is then selected for this time point. This framework places the typical acquisition and reconstruction burden of MRI in the off-view stage, enabling low-latency real-time 3D imaging in the live-view stage. The accuracy of live-view GRASP MRI and the robustness of 2D navigators for characterizing respiratory variations and/or body movements were assessed. RESULTS: Live-view GRASP MRI can efficiently generate real-time volumetric images that match well with the ground-truth references, with an imaging latency below 500 ms. Compared to 1D navigators, 2D navigators enable more reliable characterization of respiratory variations and/or body movements that may occur throughout the two imaging stages. CONCLUSION: Live-view GRASP MRI represents a novel, accurate, and robust framework for real-time volumetric imaging, which can potentially be applied for motion adaptive radiotherapy on MRI-Linac.

SPECT and CT misregistration reduction in [99mTc]Tc-MAA SPECT/CT for precision liver radioembolization treatment planning.

PURPOSE: Respiration and body movement induce misregistration between static [99mTc]Tc-MAA SPECT and CT, causing lung shunting fraction (LSF) and tumor-to-normal liver ratio (TNR) errors for 90Y radioembolization planning. We aim to alleviate the misregistration between [99mTc]Tc-MAA SPECT and CT using two registration schemes on simulation and clinical data. METHODS: In the simulation study, 70 XCAT phantoms were modeled. The SIMIND Monte Carlo program and OS-EM algorithm were used for projection generation and reconstruction, respectively. Low-dose CT (LDCT) at end-inspiration was simulated for attenuation correction (AC), lungs and liver segmentation, while contrast-enhanced CT (CECT) was simulated for tumor and perfused liver segmentation. In the clinical study, 16 patient data including [99mTc]Tc-MAA SPECT/LDCT and CECT with observed SPECT and CT mismatch were analyzed. Two liver-based registration schemes were studied: SPECT registered to LDCT/CECT and vice versa. Mean count density (MCD) of different volumes-of-interest (VOIs), normalized mutual information (NMI), LSF, TNR, and maximum injected activity (MIA) based on the partition model before and after registration were compared. Wilcoxon signed-rank test was performed. RESULTS: In the simulation study, compared to before registration, registrations significantly reduced estimation errors of MCD of all VOIs, LSF (Scheme 1: - 100.28%, Scheme 2: - 101.59%), and TNR (Scheme 1: - 7.00%, Scheme 2: - 5.67%), as well as MIA (Scheme 1: - 3.22%, Scheme 2: - 2.40%). In the clinical study, Scheme 1 reduced 33.68% LSF and increased 14.75% TNR, while Scheme 2 reduced 38.88% LSF and increased 6.28% TNR compared to before registration. One patient may change from 90Y radioembolization untreatable to treatable and other patients may change the MIA up to 25% after registration. NMI between SPECT and CT was significantly increased after registrations in both studies. CONCLUSION: Registration between static [99mTc]Tc-MAA SPECT and corresponding CTs is feasible to reduce their spatial mismatch and improve dosimetric estimation. The improvement of LSF is larger than TNR. Our method can potentially improve patient selection and personalized treatment planning for liver radioembolization.

Myocardial perfusion imaging with retrospective gating and integrated correction of attenuation, scatter, respiration, motion, and arrhythmia.

BACKGROUND: Absolute quantitative myocardial perfusion SPECT requires addressing of aleatory and epistemic uncertainties in conjunction with providing image quality sufficient for lesion detection and characterization. Iterative reconstruction methods enable the mitigation of the root causes of image degradation. This study aimed to determine the feasibility of a new SPECT/CT method with integrated corrections attempting to enable absolute quantitative cardiac imaging (xSPECT Cardiac; xSC). METHODS: We compared images of prototype xSC and conventional SPECT (Flash3DTM) acquired at rest from 56 patients aged 71 ± 12 y with suspected coronary heart disease. The xSC prototype comprised list-mode acquisitions with continuous rotation and subsequent iterative reconstructions with retrospective electrocardiography (ECG) gating. Besides accurate image formation modeling, patient-specific CT-based attenuation and energy window-based scatter correction, additionally we applied mitigation for patient and organ motion between views (inter-view), and within views (intra-view) for both the gated and ungated reconstruction. We then assessed image quality, semiquantitative regional values, and left ventricular function in the images. RESULTS: The quality of all xSC images was acceptable for clinical purposes. A polar map showed more uniform distribution for xSC compared with Flash3D, while lower apical count and higher defect contrast of myocardial infarction (p = 0.0004) were observed on xSC images. Wall motion, 16-gate volume curve, and ejection fraction were at least acceptable, with indication of improvements. The clinical prospectively gated method rejected beats ≥20% in 6 patients, whereas retrospective gating used an average of 98% beats, excluding 2% of beats. We used the list-mode data to create a product equivalent prospectively gated dataset. The dataset showed that the xSC method generated 18% higher count data and images with less noise, with comparable functional variables of volume and LVEF (p = ns). CONCLUSIONS: Quantitative myocardial perfusion imaging with the list-mode-based prototype xSPECT Cardiac is feasible, resulting in images of at least acceptable image quality.

3D motion strategy for online volumetric thermometry using simultaneous multi-slice EPI at 1.5T: an evaluation study.

PURPOSE: In presence of respiratory motion, temperature mapping is altered by in-plane and through-plane displacements between successive acquisitions together with periodic phase variations. Fast 2D Echo Planar Imaging (EPI) sequence can accommodate intra-scan motion, but limited volume coverage and inter-scan motion remain a challenge during free-breathing acquisition since position offsets can arise between the different slices. METHOD: To address this limitation, we evaluated a 2D simultaneous multi-slice EPI sequence with multiband (MB) acceleration during radiofrequency ablation on a mobile gel and in the liver of a volunteer (no heating). The sequence was evaluated in terms of resulting inter-scan motion, temperature uncertainty and elevation, potential false-positive heating and repeatability. Lastly, to account for potential through-plane motion, a 3D motion compensation pipeline was implemented and evaluated. RESULTS: In-plane motion was compensated whatever the MB factor and temperature distribution was found in agreement during both the heating and cooling periods. No obvious false-positive temperature was observed under the conditions being investigated. Repeatability of measurements results in a 95% uncertainty below 2 °C for MB1 and MB2. Uncertainty up to 4.5 °C was reported with MB3 together with the presence of aliasing artifacts. Lastly, fast simultaneous multi-slice EPI combined with 3D motion compensation reduce residual out-of-plane motion. CONCLUSION: Volumetric temperature imaging (12 slices/700 ms) could be performed with 2 °C accuracy or less, and offer tradeoffs in acquisition time or volume coverage. Such a strategy is expected to increase procedure safety by monitoring large volumes more rapidly for MR-guided thermotherapy on mobile organs.

Pilot tone-based prospective correction of respiratory motion for free-breathing myocardial T1 mapping.

OBJECTIVE: To provide respiratory motion correction for free-breathing myocardial T1 mapping using a pilot tone (PT) and a continuous golden-angle radial acquisition. MATERIALS AND METHODS: During a 45 s prescan the PT is acquired together with a dynamic sagittal image covering multiple respiratory cycles. From these images, the respiratory heart motion in head-feet and anterior-posterior direction is estimated and two linear models are derived between the PT and heart motion. In the following scan through-plane motion is corrected prospectively with slice tracking based on the PT. In-plane motion is corrected for retrospectively. Our method was evaluated on a motion phantom and 11 healthy subjects. RESULTS: Non-motion corrected measurements using a moving phantom showed T1 errors of 14 ± 4% (p < 0.05) compared to a reference measurement. The proposed motion correction approach reduced this error to 3 ± 4% (p < 0.05). In vivo the respiratory motion led to an overestimation of T1 values by 26 ± 31% compared to breathhold T1 maps, which was successfully corrected to an average difference of 3 ± 2% (p < 0.05) between our free-breathing approach and breathhold data. DISCUSSION: Our proposed PT-based motion correction approach allows for T1 mapping during free-breathing with the same accuracy as a corresponding breathhold T1 mapping scan.

Effects of respiratory and cardiac motion on estimating radiation dose to the left ventricle during radiotherapy for lung cancer.

PURPOSE: Establish a workflow to evaluate radiotherapy (RT) dose variation induced by respiratory and cardiac motion on the left ventricle (LV) and left ventricular myocardium (LVM). METHODS: Eight lung cancer patients underwent 4D-CT, expiratory T1-volumetric-interpolated-breath-hold-examination (VIBE), and cine MRI scans in expiration. Treatment plans were designed on the average intensity projection (AIP) datasets from 4D-CTs. RT dose from AIP was transferred onto 4D-CT respiratory phases. About 50% 4D-CT dose was mapped onto T1-VIBE (following registration) and from there onto average cine MRI datasets. Dose from average cine MRI was transferred onto all cardiac phases. Cumulative cardiac dose was estimated by transferring dose from each cardiac phase onto a reference cine phase following deformable image registration. The LV was contoured on each 4D-CT breathing phase and was called clinical LV (cLV); this structure is blurred by cardiac motion. Additionally, LV, LVM, and an American Heart Association (AHA) model were contoured on all cardiac phases. Relative maximum/mean doses for contoured regions were calculated with respect to each patient's maximum/mean AIP dose. RESULTS: During respiration, relative maximum and mean doses on the cLV ranged from -4.5% to 5.6% and -14.2% to 16.5%, respectively, with significant differences in relative mean doses between inspiration and expiration (P < 0.0145). During cardiac motion at expiration, relative maximum and mean doses on the LV ranged from 1.6% to 59.3%, 0.5% to 27.4%, respectively. Relative mean doses were significantly different between diastole and systole (P = 0.0157). No significant differences were noted between systolic, diastolic, or cumulative cardiac doses compared to the expiratory 4D-CT (P > 0.14). Significant differences were observed in AHA segmental doses depending on tumour proximity compared to global LV doses on expiratory 4D-CT (P < 0.0117). CONCLUSION: In this study, the LV dose was highest during expiration and diastole. Segmental evaluation suggested that future cardiotoxicity evaluations may benefit from regional assessments of dose that account for cardiopulmonary motion.

Impact of respiratory motion on 18 F-FDG PET radiomics stability: Clinical evaluation with a digital PET scanner.

PURPOSE: 18 F-FDG PET quantitative features are susceptible to respiratory motion. However, studies using clinical patient data to explore the impact of respiratory motion on 18 F-FDG PET radiomic features are limited. In this study, we investigated the impact of respiratory motion on radiomics stability with clinical 18 F-FDG PET images using a data-driven gating (DDG) algorithm on the digital PET scanner. MATERIALS AND METHODS: A total of 101 patients who underwent oncological 18 F-FDG PET scans were retrospectively included. A DDG algorithm combined with a motion compensation technique was used to extract the PET images with respiratory motion correction. 18 F-FDG-avid lesions from the thorax to the upper abdomen were analyzed on the non-DDG and DDG PET images. The lesions were segmented with a 40% threshold of the maximum standardized uptake. A total of 725 radiomic features were computed from the segmented lesions, including first-order, shape, texture, and wavelet features. The intraclass correlation coefficient (ICC) and coefficient of variation (COV) were calculated to evaluate feature stability. An ICC above 0.9 and a COV below 5% were considered high stability. RESULTS: In total, 168 lesions with and without respiratory motion correction were analyzed. Our results indicated that most 18 F-FDG PET radiomic features are sensitive to respiratory motion. Overall, only 27 out of 725 (3.72%) radiomic features were identified as highly stable, including one from the first-order features (entropy), one from the shape features (sphericity), four from the gray-level co-occurrence matrix features (normalized and unnormalized inverse difference moment, joint entropy, and sum entropy), one from the gray-level run-length matrix features (run entropy), and 20 from the wavelet filter-based features. CONCLUSION: Respiratory motion has a significant impact on 18 F-FDG PET radiomics stability. The highly stable features identified in our study may serve as potential candidates for further applications, such as machine learning modeling.

Feasibility study of deep learning-based markerless real-time lung tumor tracking with orthogonal X-ray projection images.

PURPOSE: The feasibility of a deep learning-based markerless real-time tumor tracking (RTTT) method was retrospectively studied with orthogonal kV X-ray images and clinical tracking records acquired during lung cancer treatment. METHODS: Ten patients with lung cancer treated with marker-implanted RTTT were included. The prescription dose was 50 Gy in four fractions, using seven- to nine-port non-coplanar static beams. This corresponds to 14-18 X-ray tube angles for an orthogonal X-ray imaging system rotating with the gantry. All patients underwent 10 respiratory phases four-dimensional computed tomography. After a data augmentation approach, for each X-ray tube angle of a patient, 2250 digitally reconstructed radiograph (DRR) images with gross tumor volume (GTV) contour labeled were obtained. These images were adopted to train the patient and X-ray tube angle-specific GTV contour prediction model. During the testing, the model trained with DRR images predicted GTV contour on X-ray projection images acquired during treatment. The predicted three-dimensional (3D) positions of the GTV were calculated based on the centroids of the contours in the orthogonal images. The 3D positions of GTV determined by the marker-implanted RTTT during the treatment were considered as the ground truth. The 3D deviations between the prediction and the ground truth were calculated to evaluate the performance of the model. RESULTS: The median GTV volume and motion range were 7.42 (range, 1.18-25.74) cm3 and 22 (range, 11-28) mm, respectively. In total, 8993 3D position comparisons were included. The mean calculation time was 85 ms per image. The overall median value of the 3D deviation was 2.27 (interquartile range: 1.66-2.95) mm. The probability of the 3D deviation smaller than 5 mm was 93.6%. CONCLUSIONS: The evaluation results and calculation efficiency show the proposed deep learning-based markerless RTTT method may be feasible for patients with lung cancer.

Predicting successful clinical candidates for fiducial-free lung tumor tracking with a deep learning binary classification model.

OBJECTIVES: The CyberKnife system is a robotic radiosurgery platform that allows the delivery of lung SBRT treatments using fiducial-free soft-tissue tracking. However, not all lung cancer patients are eligible for lung tumor tracking. Tumor size, density, and location impact the ability to successfully detect and track a lung lesion in 2D orthogonal X-ray images. The standard workflow to identify successful candidates for lung tumor tracking is called Lung Optimized Treatment (LOT) simulation, and involves multiple steps from CT acquisition to the execution of the simulation plan on CyberKnife. The aim of the study is to develop a deep learning classification model to predict which patients can be successfully treated with lung tumor tracking, thus circumventing the LOT simulation process. METHODS: Target tracking is achieved by matching orthogonal X-ray images with a library of digital radiographs reconstructed from the simulation CT scan (DRRs). We developed a deep learning model to create a binary classification of lung lesions as being trackable or untrackable based on tumor template DRR extracted from the CyberKnife system, and tested five different network architectures. The study included a total of 271 images (230 trackable, 41 untrackable) from 129 patients with one or multiple lung lesions. Eighty percent of the images were used for training, 10% for validation, and the remaining 10% for testing. RESULTS: For all five convolutional neural networks, the binary classification accuracy reached 100% after training, both in the validation and the test set, without any false classifications. CONCLUSIONS: A deep learning model can distinguish features of trackable and untrackable lesions in DRR images, and can predict successful candidates for fiducial-free lung tumor tracking.

Pilot tone navigation for respiratory and cardiac motion-resolved free-running 5D flow MRI.

PURPOSE: In this work, we integrated the pilot tone (PT) navigation system into a reconstruction framework for respiratory and cardiac motion-resolved 5D flow. We tested the hypotheses that PT would provide equivalent respiratory curves, cardiac triggers, and corresponding flow measurements to a previously established self-gating (SG) technique while being independent from changes to the acquisition parameters. METHODS: Fifteen volunteers and 9 patients were scanned with a free-running 5D flow sequence, with PT integrated. Respiratory curves and cardiac triggers from PT and SG were compared across all subjects. Flow measurements from 5D flow reconstructions using both PT and SG were compared to each other and to a reference electrocardiogram-gated and respiratory triggered 4D flow acquisition. Radial trajectories with variable readouts per interleave were also tested in 1 subject to compare cardiac trigger quality between PT and SG. RESULTS: The correlation between PT and SG respiratory curves were 0.95 ± 0.06 for volunteers and 0.95 ± 0.04 for patients. Heartbeat duration measurements in volunteers and patients showed a bias to electrocardiogram measurements of, respectively, 0.16 ± 64.94 ms and 0.01 ± 39.29 ms for PT versus electrocardiogram and of 0.24 ± 63.68 ms and 0.09 ± 32.79 ms for SG versus electrocardiogram. No significant differences were reported for the flow measurements between 5D flow PT and from 5D flow SG. A decrease in the cardiac triggering quality of SG was observed for increasing readouts per interleave, whereas PT quality remained constant. CONCLUSION: PT has been successfully integrated in 5D flow MRI and has shown equivalent results to the previously described 5D flow SG technique, while being completely acquisition-independent.

MR-assisted PET respiratory motion correction using deep-learning based short-scan motion fields.

PURPOSE: We evaluated the impact of PET respiratory motion correction (MoCo) in a phantom and patients. Moreover, we proposed and examined a PET MoCo approach using motion vector fields (MVFs) from a deep-learning reconstructed short MRI scan. METHODS: The evaluation of PET MoCo was performed in a respiratory motion phantom study with varying lesion sizes and tumor to background ratios (TBRs) using a static scan as the ground truth. MRI-based MVFs were derived from either 2000 spokes (MoCo2000 , 5-6 min acquisition time) using a Fourier transform reconstruction or 200 spokes (MoCoP2P200 , 30-40 s acquisition time) using a deep-learning Phase2Phase (P2P) reconstruction and then incorporated into PET MoCo reconstruction. For six patients with hepatic lesions, the performance of PET MoCo was evaluated using quantitative metrics (SUVmax , SUVpeak , SUVmean , lesion volume) and a blinded radiological review on lesion conspicuity. RESULTS: MRI-assisted PET MoCo methods provided similar results to static scans across most lesions with varying TBRs in the phantom. Both MoCo2000 and MoCoP2P200 PET images had significantly higher SUVmax , SUVpeak , SUVmean and significantly lower lesion volume than non-motion-corrected (non-MoCo) PET images. There was no statistical difference between MoCo2000 and MoCoP2P200 PET images for SUVmax , SUVpeak , SUVmean or lesion volume. Both radiological reviewers found that MoCo2000 and MoCoP2P200 PET significantly improved lesion conspicuity. CONCLUSION: An MRI-assisted PET MoCo method was evaluated using the ground truth in a phantom study. In patients with hepatic lesions, PET MoCo images improved quantitative and qualitative metrics based on only 30-40 s of MRI motion modeling data.