Respiratory Motion Compensation Research Articles

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.

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. 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. 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. 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. 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. 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.

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

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. 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. The average values for the XDTS and FTTS correlation errors were 1.38±0.65 versus 1.50±0.26mm (superior-inferior), 1.28±0.48 versus 0.40±0.09mm (left-right), and 0.96±0.32 versus 0.47±0.10mm(anterior-posterior), respectively. The prediction errors for two methods of 0.65±0.16 versus 5.48±3.33mm in the S-I direction, 0.34±0.10 versus 1.41±0.76mm in the A-P direction, and 0.22±0.072 versus 1.22±0.48mm 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. 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.

Current Research Status of Respiratory Motion for Thorax and Abdominal Treatment: A Systematic Review.

Malignant tumors have become one of the serious public health problems in human safety and health, among which the chest and abdomen diseases account for the largest proportion. Early diagnosis and treatment can effectively improve the survival rate of patients. However, respiratory motion in the chest and abdomen can lead to uncertainty in the shape, volume, and location of the tumor, making treatment of the chest and abdomen difficult. Therefore, compensation for respiratory motion is very important in clinical treatment. The purpose of this review was to discuss the research and development of respiratory movement monitoring and prediction in thoracic and abdominal surgery, as well as introduce the current research status. The integration of modern respiratory motion compensation technology with advanced sensor detection technology, medical-image-guided therapy, and artificial intelligence technology is discussed and analyzed. The future research direction of intraoperative thoracic and abdominal respiratory motion compensation should be non-invasive, non-contact, use a low dose, and involve intelligent development. The complexity of the surgical environment, the constraints on the accuracy of existing image guidance devices, and the latency of data transmission are all present technical challenges.

Intra-bin correction and inter-bin compensation of respiratory motion in free-running five-dimensional whole-heart magnetic resonance imaging

BackgroundFree-running cardiac and respiratory motion-resolved whole-heart five-dimensional (5D) cardiovascular magnetic resonance (CMR) can reduce scan planning and provide a means of evaluating respiratory-driven changes in clinical parameters of interest. However, respiratory-resolved imaging can be limited by user-defined parameters which create trade-offs between residual artifact and motion blur. In this work, we develop and validate strategies for both correction of intra-bin and compensation of inter-bin respiratory motion to improve the quality of 5D CMR. MethodsEach component of the reconstruction framework was systematically validated and compared to the previously established 5D approach using simulated free-running data (N = 50) and a cohort of 32 patients with congenital heart disease. The impact of intra-bin respiratory motion correction was evaluated in terms of image sharpness while inter-bin respiratory motion compensation was evaluated in terms of reconstruction error, compression of respiratory motion, and image sharpness. The full reconstruction framework (intra-acquisition correction and inter-acquisition compensation of respiratory motion [IIMC] 5D) was evaluated in terms of image sharpness and scoring of image quality by expert reviewers. ResultsIntra-bin motion correction provides significantly (p < 0.001) sharper images for both simulated and patient data. Inter-bin motion compensation results in significant (p < 0.001) lower reconstruction error, lower motion compression, and higher sharpness in both simulated (10/11) and patient (9/11) data. The combined framework resulted in significantly (p < 0.001) sharper IIMC 5D reconstructions (End-expiration (End-Exp): 0.45 ± 0.09, End-inspiration (End-Ins): 0.46 ± 0.10) relative to the previously established 5D implementation (End-Exp: 0.43 ± 0.08, End-Ins: 0.39 ± 0.09). Similarly, image scoring by three expert reviewers was significantly (p < 0.001) higher using IIMC 5D (End-Exp: 3.39 ± 0.44, End-Ins: 3.32 ± 0.45) relative to 5D images (End-Exp: 3.02 ± 0.54, End-Ins: 2.45 ± 0.52). ConclusionThe proposed IIMC reconstruction significantly improves the quality of 5D whole-heart MRI. This may be exploited for higher resolution or abbreviated scanning. Further investigation of the diagnostic impact of this framework and comparison to gold standards is needed to understand its full clinical utility, including exploration of respiratory-driven changes in physiological measurements of interest.

ADMNet: Adaptive-Weighting Dual Mapping for Online Tracking With Respiratory Motion Estimation in Contrast-Enhanced Ultrasound.

Lesion localization and tracking are critical for accurate, automated medical imaging analysis. Contrast-enhanced ultrasound (CEUS) significantly enriches traditional B-mode ultrasound with contrast agents to provide high-resolution, real-time images of blood flow in tissues and organs. However, many trackers, designed primarily for natural RGB or B-mode ultrasound images, underutilize the extensive data from dual-screen enhanced images and fail to account for respiratory motion, thus facing challenges in achieving accurate target tracking. To address the existing challenges, we propose an adaptive-weighted dual mapping (ADMNet), an online tracking framework tailored for CEUS. Firstly, we introduced a novel Multimodal Atrous Attention Fusion (MAAF) module, innovatively designed to adapt the weightage between B-mode and enhanced images in dual-screen CEUS, reflecting the clinician's dynamic focus shifts between screens. Secondly, we proposed a Respiratory Motion Compensation (RMC) module to correct motion trajectory interferences due to respiratory motion, effectively leveraging temporal information. We utilized two newly established CEUS datasets, totaling 35,082 frames, to benchmark the ADMNet against various advanced B-mode ultrasound trackers. Our extensive experiments revealed that ADMNet achieves new state-of-the-art performance in CEUS tracking. Ablation studies and visualizations further underline the effectiveness of MAAF and RMC modules, demonstrating the promising potential of ADMNet in clinical CEUS tracing, thus providing novel research avenues in this field.

Development and evaluation of ultrasound image tracking technology based on Mask R-CNN applied to respiratory motion compensation system.

For respiration induced tumor displacement during a radiation therapy, a common method to prevent the extra radiation is image-guided radiation therapy. Moreover, mask region-based convolutional neural networks (Mask R-CNN) is one of the state-of-the-art (SOTA) object detection frameworks capable of conducting object classification, localization, and pixel-level instance segmentation. We developed a novel ultrasound image tracking technology based on Mask R-CNN for stable tracking of the detected diaphragm motion and applied to the respiratory motion compensation system (RMCS). For training Mask R-CNN, 1800 ultrasonic images of the human diaphragm are collected. Subsequently, an ultrasonic image tracking algorithm was developed to compute the mean pixel coordinates of the diaphragm detected by Mask R-CNN. These calculated coordinates are then utilized by the RMCS for compensation purposes. The tracking similarity verification experiment of mask ultrasonic imaging tracking algorithm (M-UITA) is performed. The correlation between the input signal and the signal tracked by M-UITA was evaluated during the experiment. The average discrete Fréchet distance was less than 4 mm. Subsequently, a respiratory displacement compensation experiment was conducted. The proposed method was compared to UITA, and the compensation rates of three different respiratory signals were calculated and compared. The experimental results showed that the proposed method achieved a 6.22% improvement in compensation rate compared to UITA. This study introduces a novel method called M-UITA, which offers high tracking precision and excellent stability for monitoring diaphragm movement. Additionally, it eliminates the need for manual parameter adjustments during operation, which is an added advantage.

Quantification of Hepatocellular Carcinoma Vascular Dynamics With Contrast-Enhanced Ultrasound for LI-RADS Implementation.

The aim of this study is to describe a comprehensive contrast-enhanced ultrasound (CEUS) imaging protocol and analysis method to implement CEUS LI-RADS (Liver Imaging Reporting and Data System) in a quantifiable manner. The methods that are validated with a prospective single-center study aim to simplify CEUS LI-RADS evaluation, remove observer bias, and potentially improve the sensitivity of CEUS LI-RADS. This prospective single-center study enrolled patients with hepatocellular carcinoma (April 2021-June 2022; N = 31; mean age ± SD, 67 ± 6 years; 24 men/7 women). For each patient, at least 2 CEUS loops spanning over 5 minutes were collected for different lesion scan planes using an articulated arm to hold the transducer. Automatic respiratory gating and motion compensation algorithms removed errors due to breathing motion. The long axis of the lesion was measured in the contrast and fundamental images to capture nodule size. Parametric processing of time-intensity curve analysis on linearized data provided quantifiable information of the wash-in and washout dynamics via rise time ( RT ) and degree of washout ( DW ) parameters extracted from the time-intensity curve, respectively. A Welch t test was performed between lesion and parenchyma RT for each lesion to confirm statistically significant differences. P values for bootstrapped 95% confidence intervals of the relative degree of washout ( rDW ), ratio of DW between the lesion and surrounding parenchyma, were computed to quantify lesion washout. Coefficient of variation (COV) of RT , DW , and rDW was calculated for each patient between injections for both the lesion and surrounding parenchyma to gauge reproducibility of these metrics. Spearman rank correlation tests were performed among size, RT , DW , and rDW values to evaluate statistical dependence between the variables. The mean ± SD lesion diameter was 23 ± 8 mm. The RT for all lesions, capturing arterial phase hyperenhancement, was shorter than that of surrounding liver parenchyma ( P < 0.05). All lesions also demonstrated significant ( P < 0.05) but variable levels of washout at both 2-minute and 5-minute time points, quantified in rDW . The COV of RT for the lesion and surrounding parenchyma were both 11%, and the COV of DW and rDW at 2 and 5 minutes ranged from 22% to 31%. Statistically significant relationships between lesion and parenchyma RT and between lesion RT and lesion DW at the 2- and 5-minute time points were found ( P < 0.05). The imaging protocol and analysis method presented provide robust, quantitative metrics that describe the dynamic vascular patterns of LI-RADS 5 lesions classified as hepatocellular carcinomas. The RT of the bolus transit quantifies the arterial phase hyperenhancement, and the DW and rDW parameters quantify the washout from linearized CEUS intensity data. This unique methodology is able to implement the CEUS-LIRADS scheme in a quantifiable manner for the first time and remove its existing issues of currently being qualitative and suffering from subjective evaluations.

High-resolution, respiratory-resolved coronary MRA using a Phyllotaxis-reordered variable-density 3D cones trajectory

PurposeTo develop a respiratory-resolved motion-compensation method for free-breathing, high-resolution coronary magnetic resonance angiography (CMRA) using a 3D cones trajectory. MethodsTo achieve respiratory-resolved 0.98 mm resolution images in a clinically relevant scan time, we undersample the imaging data with a variable-density 3D cones trajectory. For retrospective motion compensation, translational estimates from 3D image-based navigators (3D iNAVs) are used to bin the imaging data into four phases from end-expiration to end-inspiration. To ensure pseudo-random undersampling within each respiratory phase, we devise a phyllotaxis readout ordering scheme mindful of eddy current artifacts in steady state free precession imaging. Following binning, residual 3D translational motion within each phase is computed using the 3D iNAVs and corrected for in the imaging data. The noise-like aliasing characteristic of the combined phyllotaxis and cones sampling pattern is leveraged in a compressed sensing reconstruction with spatial and temporal regularization to reduce aliasing in each of the respiratory phases. ResultsIn initial studies of six subjects, respiratory motion compensation using the proposed method yields improved image quality compared to non-respiratory-resolved approaches with no motion correction and with 3D translational correction. Qualitative assessment by two cardiologists and quantitative evaluation with the image edge profile acutance metric indicate the superior sharpness of coronary segments reconstructed with the proposed method (P < 0.01). ConclusionWe have demonstrated a new method for free-breathing, high-resolution CMRA based on a variable-density 3D cones trajectory with modified phyllotaxis ordering and respiratory-resolved motion compensation with 3D iNAVs.

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

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. 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. 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. 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.

Impact of Various Image Reconstruction Methods on Joint Compensation of Respiratory Motion and Partial Volume Effects in Whole-Body 18F-FDG PET/CT Imaging: Patients with Non-Small Cell Lung Cancer

Impact of Various Image Reconstruction Methods on Joint Compensation of Respiratory Motion and Partial Volume Effects in Whole-Body 18F-FDG PET/CT Imaging: Patients with Non-Small Cell Lung Cancer

Combining the wavelet transform with a phase-lead compensator to a respiratory motion compensation system with an ultrasound tracking technique in radiation therapy

This study evaluated the feasibility of applying the wavelet transform (WT) combined with a phase-lead compensator (PLC) to our previously developed two-dimensional respiratory motion compensation system (RMCS). This system automatically and instantaneously adjusts PLC parameters according to different respiration signals to reduce influences of the system delay time, improving the compensation effect of the RMCS during respiratory motion compensation. This study performed respiratory movement compensation experiments with a two-dimensional respiratory motion simulation system (RMSS) and the RMCS. Human respiratory signals were captured using our previously developed ultrasound image tracking algorithm (UITA). In this study, a displacement compensation RMCS algorithm based on the combination of WT and PLC was developed by LabVIEW, which allows an automatic adjustment of the PLC parameters according to various respiratory waveforms, achieving a better compensation effect. The experiment results indicated that the compensation rate (CR) of right-left and superior-inferior directions had both improved 67.96–88.05% and 70.38–91.43%, respectively. In this study, the proposed method combined with WT and PLC applied in respiratory movement compensation experiments; the UITA was used for tracking diaphragm motion which substitutes for tumor motion. This noninvasive monitoring method also helps reduce side effects after treatment. The experimental results indicated that the effect of using the WT combined with the PLC to compensate for various respiratory signals was improved over our previously developed compensation algorithm.

A personalized image-guided intervention system for peripheral lung cancer on patient-specific respiratory motion model.

Due to respiratory motion, precise tracking of lung nodule movement is a persistent challenge for guiding percutaneous lung biopsy during image-guided intervention. We developed an automated image-guided system incorporating effective and robust tracking algorithms to address this challenge. Accurate lung motion prediction and personalized image-guided intervention are the key technological contributions of this work. A patient-specific respiratory motion model is developed to predict pulmonary movements of individual patients. It is based on the relation between the artificial 4D CT and corresponding positions tracked by position sensors attached on the chest using an electromagnetic (EM) tracking system. The 4D CT image of the thorax during breathing is calculated through deformable registration of two 3D CT scans acquired at inspiratory and expiratory breath-hold. The robustness and accuracy of the image-guided intervention system were assessed on a static thorax phantom under differentclinical parametric combinations. Real 4D CT images of ten patients were used to evaluate the accuracy of the respiratory motion model. The mean error of the model in different breathing phases was 1.59 ± 0.66mm. Using a static thorax phantom, we achieved an average targeting accuracy of 3.18 ± 1.2mm across 50 independent tests with different intervention parameters. The positive results demonstrate the robustness and accuracy of our system for personalized lung cancer intervention. The proposed system integrates a patient-specific respiratory motion compensation model to reduce the effect of respiratory motion during percutaneous lung biopsy and help interventional radiologists target the lesion efficiently. Our preclinical studies indicate that the image-guided system has the ability to accurately predict and track lung nodules of individual patients and has the potential for use in the diagnosis and treatment of early stage lung cancer.

Offline and online LSTM networks for respiratory motion prediction in MR-guided radiotherapy

Objective. Gated beam delivery is the current clinical practice for respiratory motion compensation in MR-guided radiotherapy, and further research is ongoing to implement tracking. To manage intra-fractional motion using multileaf collimator tracking the total system latency needs to be accounted for in real-time. In this study, long short-term memory (LSTM) networks were optimized for the prediction of superior–inferior tumor centroid positions extracted from clinically acquired 2D cine MRIs. Approach. We used 88 patients treated at the University Hospital of the LMU Munich for training and validation (70 patients, 13.1 h), and for testing (18 patients, 3.0 h). Three patients treated at Fondazione Policlinico Universitario Agostino Gemelli were used as a second testing set (1.5 h). The performance of the LSTMs in terms of root mean square error (RMSE) was compared to baseline linear regression (LR) models for forecasted time spans of 250 ms, 500 ms and 750 ms. Both the LSTM and the LR were trained with offline (offline LSTM and offline LR) and online schemes (offline+online LSTM and online LR), the latter to allow for continuous adaptation to recent respiratory patterns. Main results. We found the offline+online LSTM to perform best for all investigated forecasts. Specifically, when predicting 500 ms ahead it achieved a mean RMSE of 1.20 mm and 1.00 mm, while the best performing LR model achieved a mean RMSE of 1.42 mm and 1.22 mm for the LMU and Gemelli testing set, respectively. Significance. This indicates that LSTM networks have potential as respiratory motion predictors and that continuous online re-optimization can enhance their performance.

Clinical feasibility and impact of data-driven respiratory motion compensation studied in 200 whole-body 18F-FDG PET/CT scans

BackgroundThis study examines the clinical feasibility and impact of implementing a fully automated whole-body PET protocol with data-driven respiratory gating in patients with a broad range of oncological and non-oncological pathologies 592 FDG PET/CT patients were prospectively included. 200 patients with lesions in the torso were selected for further analysis, and ungated (UG), belt gated (BG) and data-driven gating (DDG) images were reconstructed. All images were reconstructed using the same data and without prolonged acquisition time for gated images. Images were quantitatively analysed for lesion uptake and metabolic volume, complemented by a qualitative analysis of visual lesion detection. In addition, the impact of gating on treatment response evaluation was evaluated in 23 patients with malignant lymphoma.ResultsPlacement of the belt needed for BG was associated with problems in 27% of the BG scans, whereas no issues were reported using DDG imaging. For lesion quantification, DDG and BG images had significantly greater SUV values and smaller volumes than UG. The physicians reported notable image blurring in 44% of the UG images that was problematic for clinical evaluation in 4.5% of cases.ConclusionRespiratory motion compensation using DDG is readily integrated into clinical routine and produce images with more accurate and significantly greater SUV values and smaller metabolic volumes. In our broad cohort of patients, the physicians overwhelmingly preferred gated over ungated images, with a slight preference for DDG images. However, even in patients with malignant disease in the torso, no additional diagnostic information was obtained by the gated images that could not be derived from the ungated images.

Ultrasound-Based Navigation for Open Liver Surgery with Active Tumor Tracking and Deformation Compensation: Preliminary Results

Introduction: Intraoperative ultrasound (US) localization of lesions after neoadjuvant chemotherapy is challenging because their size may decrease beyond the ultrasound resolution. To improve their localization, we introduce an ultrasound-based electromagnetic (EM) navigation system which maps the preoperative image with the intraoperative ultrasound, thus highlighting their location. Methods: Based on MRI or CT, a 3D model of the liver, lesions, hepatic and portal vein was generated and matched with the intraoperative organ position either by 1) identifying common landmarks between the pre- and intraoperative image or 2) automatically using deformable modeling of hepatic and portal vasculature extracted from 3DUS using deep learning. Accuracy was assessed as Euclidean distance between the lesion imaged in the preoperative image and the one identified in intraoperative 3DUS. Results: From March 2019 to May 2021, 45 navigated procedures were safely performed. Navigation provided additional localization features by overlaying preoperative 3D models of liver lesions, vasculature and biliary anatomy onto the intraoperative ultrasound. Accuracy, calculated in 36 patients, was 8.5 ± 4.2 mm for the landmark method (n=20), and 5.7 ± 3.6 mm for automatic generation of the vasculature (n=16) (p=0.043). Surgical navigation was available on average after 13.4 minutes. Conclusion: The proposed navigation system allows to accurately localize liver lesions and is improved by automatic vasculature detection in the US image and compensation of respiratory motion and liver manipulation.

Data-driven respiratory signal estimation from temporally finely sampled projection data in conventional cardiac perfusion SPECT imaging.

The aim of this work was to revisit the data-driven approach of axial center-of-mass (COM) measurements to recover a surrogate respiratory signal from finely sampled (100ms) single photon emission computed tomography (SPECT) projection data derived from list-mode acquisitions. For our initial evaluation, we acquired list-mode projection data from an anthropomorphic cardiac phantom mounted on a Quasar respiratory motion platform simulating 15mm amplitude respiratory motion. We also selected 302 consecutive patients (138 males, 164 females) with list-mode acquisitions, external respiratory motion tracking, and written consent to evaluate the clinical efficacy of our data-driven approach. Linear regression, Pearson's correlation coefficient (r), and standard error of the estimates (SEE) between the respiratory signals obtained with a visual tracking system (VTS) and COM measurements were calculated for individual projection data sets and for the patient group as a whole. Both the VTS- and COM-derived respiratory signals were used to estimate and correct respiratory motion. The reconstruction for six-degree of freedom rigid-body motion estimation was done in two ways: (1) using three iterations of ordered-subsets expectation-maximization (OSEM) with four subsets (16 projection angles per subset), or 12 iterations of maximum-likelihood expectation-maximization (MLEM). Respiratory motion compensation was done employing either OSEM with 16 subsets (four projection angles per subset) and five iterations or MLEM and 80 iterations, using the two respiratory estimates, respectively. Polar map quantification was also performed, calculating the percentage count difference (%Diff) between polar maps without and with respiratory motion included. Average % Diff was calculated in 17 segments (defined according to ASNC Guidelines). Paired t-tests were used to determine significance (p-values). The r-value calculated when comparing the VTS and COM respiratory signals varied widely between -0.01 and 0.96 with an average of 0.70, while the SEE varied between 0.80 and 6.48mm with an average of 2.05mm for our patient set, while the same values for the one anthropomorphic phantom acquisition are 0.91 and 1.11mm, respectively. A comparison between the respiratory motion estimates for VTS and COM in the S-I direction yielded an r=0.90 (0.94), and an SEE of 1.56mm (1.20mm) for OSEM (MLEM), respectively. Bland-Altman plots and calculated intraclass correlation coefficients also showed excellent agreement between the VTS and COM respiratory motion estimates. Average S-I respiratory estimates for the VTS (COM) were 9.04 (9.2mm) and 9.01mm (9.14mm) for the OSEM and MLEM, respectively. The paired t-test approached significance when comparing VTS and COM estimated respiratory signals with p-values of 0.069 and 0.051 for OSEM and MLEM. The respiratory estimates from the anthropomorphic cardiac phantom experiment using the VTS (COM) were 12.62 (14.10mm) and 12.55mm (14.29mm) for OSEM and MLEM, respectively. Polar map quantification yielded average % Diff consistently better when employing VTS-derived respiratory estimates to correct for respiration compared to the COM-derived estimates. The results indicate that our COM method has the potential to provide an automated data-driven correction of cardiac respiratory motion without the drawbacks of our VTS methodology. However, it is not generally equivalent to the VTS method in extent of correction.

Quantitative contrast-enhanced ultrasound for the evaluation and early detection of hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is the most common primary liver malignancy with high mortality mainly due to pre-existing liver disease and delay in diagnosis, limiting treatment options. Currently, the state-of-the-art diagnostic metric for HCC is LiRADS (Liver Imaging Reporting and Data System), a qualitative image assessment based on the bolus transit characteristics of microbubbles that stratifies liver tumors suspected for HCC. However, with contrast-enhanced ultrasound, liver tumor perfusion can be quantifiably characterized to identify abnormal arterial flow after an initial portal venous and hepatic arterial flow reduction in the liver, which are typical features of HCCs. The image intensity in a region of interest (ROI) in the HCC is used to form a time-intensity curve (TIC) of the bolus transit (wash-in/washout). A lognormal curve is fitted to the TIC and parameters related to blood flow in the tumor are extracted. Respiratory gating and motion compensation are applied to the video loops before forming the TIC to remove noise and improve the accuracy of the HCC perfusion measurements. Parametric images of the rise time and peak intensity provide an HCC classification algorithm. Utilizing this approach, we provide an improvement to the LiRADS method for an earlier and more accurate diagnosis of HCC.

The feasibility of an approximate irregular field dose distribution simulation program applied to a respiratory motion compensation system.

This study optimized our previously proposed simulation program for the approximate irregular field dose distribution (SPAD) and applied it to a respiratory motion compensation system (RMCS) and respiratory motion simulation system (RMSS). The main purpose was to rapidly analyze the two-dimensional dose distribution and evaluate the compensation effect of the RMCS during radiotherapy. This study modified the SPAD to improve the rapid analysis of the dose distribution. In the experimental setup, four different respiratory signal patterns were input to the RMSS for actuation, and an ultrasound image tracking algorithm was used to capture the real-time respiratory displacement, which was input to the RMCS for actuation. A linear accelerator simultaneously irradiated the EBT3 film. The gamma passing rate was used to verify the dose similarity between the EBT3 film and the SPAD, and conformity index (CI) and compensation rate (CR) were used to quantify the compensation effect. The Gamma passing rates were 70.48-81.39% (2%/2mm) and 88.23-96.23% (5%/3mm) for various collimator opening patterns. However, the passing rates of the SPAD and EBT3 film ranged from 61.85% to 99.85% at each treatment time point. Under the four different respiratory signal patterns, CR ranged between 21% and 75%. After compensation, the CI for 85%, 90%, and 95% isodose constraints were 0.78, 0.57, and 0.12, respectively. This study has demonstrated that the dose change during each stage of the treatment process can be analyzed rapidly using the improved SPAD. After compensation, applying the RMCS can reduce the treatment errors caused by respiratory movements.

Temporally aware volumetric generative adversarial network-based MR image reconstruction with simultaneous respiratory motion compensation: Initial feasibility in 3D dynamic cine cardiac MRI.

Develop a novel three-dimensional (3D) generative adversarial network (GAN)-based technique for simultaneous image reconstruction and respiratory motion compensation of 4D MRI. Our goal was to enable high-acceleration factors 10.7X-15.8X, while maintaining robust and diagnostic image quality superior to state-of-the-art self-gating (SG) compressed sensing wavelet (CS-WV) reconstruction at lower acceleration factors 3.5X-7.9X. Our GAN was trained based on pixel-wise content loss functions, adversarial loss function, and a novel data-driven temporal aware loss function to maintain anatomical accuracy and temporal coherence. Besides image reconstruction, our network also performs respiratory motion compensation for free-breathing scans. A novel progressive growing-based strategy was adapted to make the training process possible for the proposed GAN-based structure. The proposed method was developed and thoroughly evaluated qualitatively and quantitatively based on 3D cardiac cine data from 42 patients. Our proposed method achieved significantly better scores in general image quality and image artifacts at 10.7X-15.8X acceleration than the SG CS-WV approach at 3.5X-7.9X acceleration (4.53 ± 0.540 vs. 3.13 ± 0.681 for general image quality, 4.12 ± 0.429 vs. 2.97 ± 0.434 for image artifacts, P < .05 for both). No spurious anatomical structures were observed in our images. The proposed method enabled similar cardiac-function quantification as conventional SG CS-WV. The proposed method achieved faster central processing unit-based image reconstruction (6 s/cardiac phase) than the SG CS-WV (312 s/cardiac phase). The proposed method showed promising potential for high-resolution (1 mm3 ) free-breathing 4D MR data acquisition with simultaneous respiratory motion compensation and fast reconstruction time.

Deep-learning based super-resolution for 3D isotropic coronary MR angiography in less than a minute.

To develop and evaluate a novel and generalizable super-resolution (SR) deep-learning framework for motion-compensated isotropic 3D coronary MR angiography (CMRA), which allows free-breathing acquisitions in less than a minute. Undersampled motion-corrected reconstructions have enabled free-breathing isotropic 3D CMRA in ~5-10 min acquisition times. In this work, we propose a deep-learning-based SR framework, combined with non-rigid respiratory motion compensation, to shorten the acquisition time to less than 1 min. A generative adversarial network (GAN) is proposed consisting of two cascaded Enhanced Deep Residual Network generator, a trainable discriminator, and a perceptual loss network. A 16-fold increase in spatial resolution is achieved by reconstructing a high-resolution (HR) isotropic CMRA (0.9 mm3 or 1.2 mm3 ) from a low-resolution (LR) anisotropic CMRA (0.9 × 3.6 × 3.6 mm3 or 1.2 × 4.8 × 4.8 mm3 ). The impact and generalization of the proposed SRGAN approach to different input resolutions and operation on image and patch-level is investigated. SRGAN was evaluated on a retrospective downsampled cohort of 50 patients and on 16 prospective patients that were scanned with LR-CMRA in ~50 s under free-breathing. Vessel sharpness and length of the coronary arteries from the SR-CMRA is compared against the HR-CMRA. SR-CMRA showed statistically significant (P < .001) improved vessel sharpness 34.1% ± 12.3% and length 41.5% ± 8.1% compared with LR-CMRA. Good generalization to input resolution and image/patch-level processing was found. SR-CMRA enabled recovery of coronary stenosis similar to HR-CMRA with comparable qualitative performance. The proposed SR-CMRA provides a 16-fold increase in spatial resolution with comparable image quality to HR-CMRA while reducing the predictable scan time to <1 min.