Automated segmentation of 3D cine cardiovascular magnetic resonance imaging.

Introduction: As the life expectancy of children with congenital heart disease (CHD) is rapidly increasing and the adult population with CHD is growing, there is an unmet need to improve clinical workflow and efficiency of analysis. Cardiovascular magnetic resonance (CMR) is a noninvasive imaging modality for monitoring patients with CHD. CMR exam is based on multiple breath-hold 2-dimensional (2D) cine acquisitions that should be precisely prescribed and is expert and institution dependent. Moreover, 2D cine images have relatively thick slices, which does not allow for isotropic delineation of ventricular structures. Thus, development of an isotropic 3D cine acquisition and automatic segmentation method is worthwhile to make CMR workflow straightforward and efficient, as the present work aims to establish. Methods: Ninety-nine patients with many types of CHD were imaged using a non-angulated 3D cine CMR sequence covering the whole-heart and great vessels. Automatic supervised and semi-supervised deep-learning-based methods were developed for whole-heart segmentation of 3D cine images to separately delineate the cardiac structures, including both atria, both ventricles, aorta, pulmonary arteries, and superior and inferior vena cavae. The segmentation results derived from the two methods were compared with the manual segmentation in terms of Dice score, a degree of overlap agreement, and atrial and ventricular volume measurements. Results: The semi-supervised method resulted in a better overlap agreement with the manual segmentation than the supervised method for all 8 structures (Dice score 83.23 ± 16.76% vs. 77.98 ± 19.64%; P-value ≤0.001). The mean difference error in atrial and ventricular volumetric measurements between manual segmentation and semi-supervised method was lower (bias ≤ 5.2 ml) than the supervised method (bias ≤ 10.1 ml). Discussion: The proposed semi-supervised method is capable of cardiac segmentation and chamber volume quantification in a CHD population with wide anatomical variability. It accurately delineates the heart chambers and great vessels and can be used to accurately calculate ventricular and atrial volumes throughout the cardiac cycle. Such a segmentation method can reduce inter- and intra- observer variability and make CMR exams more standardized and efficient.

Combined model-based and deep learning-based automated 3D zonal segmentation of the prostate on T2-weighted MR images: clinical evaluation.

OBJECTIVE: To train and to test for prostate zonal segmentation an existing algorithm already trained for whole-gland segmentation. METHODS: The algorithm, combining model-based and deep learning-based approaches, was trained for zonal segmentation using the NCI-ISBI-2013 dataset and 70 T2-weighted datasets acquired at an academic centre. Test datasets were randomly selected among examinations performed at this centre on one of two scanners (General Electric, 1.5 T; Philips, 3 T) not used for training. Automated segmentations were corrected by two independent radiologists. When segmentation was initiated outside the prostate, images were cropped and segmentation repeated. Factors influencing the algorithm's mean Dice similarity coefficient (DSC) and its precision were assessed using beta regression. RESULTS: Eighty-two test datasets were selected; one was excluded. In 13/81 datasets, segmentation started outside the prostate, but zonal segmentation was possible after image cropping. Depending on the radiologist chosen as reference, algorithm's median DSCs were 96.4/97.4%, 91.8/93.0% and 79.9/89.6% for whole-gland, central gland and anterior fibromuscular stroma (AFMS) segmentations, respectively. DSCs comparing radiologists' delineations were 95.8%, 93.6% and 81.7%, respectively. For all segmentation tasks, the scanner used for imaging significantly influenced the mean DSC and its precision, and the mean DSC was significantly lower in cases with initial segmentation outside the prostate. For central gland segmentation, the mean DSC was also significantly lower in larger prostates. The radiologist chosen as reference had no significant impact, except for AFMS segmentation. CONCLUSIONS: The algorithm performance fell within the range of inter-reader variability but remained significantly impacted by the scanner used for imaging. KEY POINTS: • Median Dice similarity coefficients obtained by the algorithm fell within human inter-reader variability for the three segmentation tasks (whole gland, central gland, anterior fibromuscular stroma). • The scanner used for imaging significantly impacted the performance of the automated segmentation for the three segmentation tasks. • The performance of the automated segmentation of the anterior fibromuscular stroma was highly variable across patients and showed also high variability across the two radiologists.

Differences in Regional Brain Volumes Two Months and One Year after Mild Traumatic Brain Injury.

Conventional structural imaging is often normal after mild traumatic brain injury (mTBI). There is a need for structural neuroimaging biomarkers that facilitate detection of milder injuries, allow recovery trajectory monitoring, and identify those at risk for poor functional outcome and disability. We present a novel approach to quantifying volumes of candidate brain regions at risk for injury. Compared to controls, patients with mTBI had significantly smaller volumes in several regions including the caudate, putamen, and thalamus when assessed 2 months after injury. These differences persisted but were reduced in magnitude 1 year after injury, suggesting the possibility of normalization over time in the affected regions. More pronounced differences, however, were found in the amygdala and hippocampus, suggesting the possibility of regionally specific responses to injury.

Automatic determination of differential coronary artery motion minima for cardiac computed tomography optimal phase selection.

RATIONALE AND OBJECTIVES: Selecting the optimal phase for coronary artery evaluation can be challenging, especially at higher heart rates, given that the optimal phase may differ for each of the coronary arteries. This study aimed to evaluate a novel vessel-specific algorithm which automatically outputs the minimum motion phase per coronary artery. MATERIALS AND METHODS: The study included 44 patients who underwent 256-slice cardiac computed tomography for evaluation of chest pain. End-systolic and mid-diastolic minimal motion phases were automatically calculated by a previously validated global motion algorithm and by a new vessel-specific algorithm which calculates the minimum motion for each of the three main coronary arteries, separately. Two readers blindly evaluated all coronary segments for image quality. Median scores per coronary artery were compared by the Wilcoxon signed rank test. RESULTS: The variation, per patient, between the optimal phases of the three coronary arteries was 5.0 ± 4.5% (1%-22%) for end systole and 4.8 ± 4.1% (0%-19%) for mid diastole. The mean image quality scores per coronary artery were 4.0 ± 0.61 for the vessel-specific approach and 3.80 ± 0.69 for the global phase selection (P < .001). Overall, 46 of 122 arteries had a better score with the vessel-specific approach and five with the standard global approach. Interreader agreement was substantial (k = 0.72). CONCLUSIONS: This study has shown that multiple phases are required to ensure optimal image quality for all three coronary arteries and that a vessel-specific phase selection algorithm achieves superior results to the standard global approach.

Objective quantification of aortic valvular structures by cardiac computed tomography angiography in patients considered for transcatheter aortic valve implantation.

PURPOSE: To test the ability of a model-based segmentation of the aortic root for consistent assessment of aortic valve structures in patients considered for transcatheter aortic valve implantation (TAVI) who underwent 256-slice cardiac computed tomography (CT). METHODS: Consecutive patients (n = 49) with symptomatic severe aortic stenosis considered for TAVI and patients without aortic stenosis (n = 17) underwent cardiac CT. Images were evaluated by two independent observers who measured the diameter of the aortic annulus and its distance to both coronary ostia (1) manually and (2) software-assisted. All acquired measures were compared with each other and to (3) fully automatic quantification. RESULTS: High correlations were observed for 3D measures of the aortic annulus conducted on multiple oblique planes (r = 0.87 and 0.84 between observers and model-based measures, and r = 0.81 between observers). Reproducibility was further improved by software-assisted versus manual assessment for all the acquired variables (r = 0.98 versus 0.81 for annulus diameter, r = 0.94 versus 0.85 for distance to the left coronary ostium, P < 0.01 for both). Thus, using software-assisted measurements very low limits of agreement were observed for the annulus diameter (95%CI of -1.2 to 0.6 mm) and within very low time-spent (0.6 ± 0.1 min for software-assisted versus 1.6 ± 0.3 min per patient for manual assessment, P < 0.001). Assessment of the aortic annulus using the 3D model-based instead of manual 2D-coronal measurements would have modified the implantation strategy in 12 of 49 patients (25%) with aortic stenosis. Four of 12 patients with potentially modified implantation strategy yielded postprocedural moderate paravalvular regurgitation, which may have been avoided by implantation of a larger prosthesis, as suggested by automatic 3D measures. CONCLUSION: Our study highlights the usefulness of software-assisted preprocedural assessment of the aortic annulus in patients considered for TAVI.

euHeart: personalized and integrated cardiac care using patient-specific cardiovascular modelling.

The loss of cardiac pump function accounts for a significant increase in both mortality and morbidity in Western society, where there is currently a one in four lifetime risk, and costs associated with acute and long-term hospital treatments are accelerating. The significance of cardiac disease has motivated the application of state-of-the-art clinical imaging techniques and functional signal analysis to aid diagnosis and clinical planning. Measurements of cardiac function currently provide high-resolution datasets for characterizing cardiac patients. However, the clinical practice of using population-based metrics derived from separate image or signal-based datasets often indicates contradictory treatments plans owing to inter-individual variability in pathophysiology. To address this issue, the goal of our work, demonstrated in this study through four specific clinical applications, is to integrate multiple types of functional data into a consistent framework using multi-scale computational modelling.

Using flow information to support 3D vessel reconstruction from rotational angiography.

For the assessment of cerebrovascular diseases, it is beneficial to obtain three-dimensional (3D) morphologic and hemodynamic information about the vessel system. Rotational angiography is routinely used to image the 3D vascular geometry and we have shown previously that rotational subtraction angiography has the potential to also give quantitative information about blood flow. Flow information can be determined when the angiographic sequence shows inflow and possibly outflow of contrast agent. However, a standard volume reconstruction assumes that the vessel tree is uniformly filled with contrast agent during the whole acquisition. If this is not the case, the reconstruction exhibits artifacts. Here, we show how flow information can be used to support the reconstruction of the 3D vessel centerline and radii in this case. Our method uses the fast marching algorithm to determine the order in which voxels are analyzed. For every voxel, the rotational time intensity curve (R-TIC) is determined from the image intensities at the projection points of the current voxel. Next, the bolus arrival time of the contrast agent at the voxel is estimated from the R-TIC. Then, a measure of the intensity and duration of the enhancement is determined, from which a speed value is calculated that steers the propagation of the fast marching algorithm. The results of the fast marching algorithm are used to determine the 3D centerline by backtracking. The 3D radius is reconstructed from 2D radius estimates on the projection images. The proposed method was tested on computer simulated rotational angiography sequences with systematically varied x-ray acquisition, blood flow, and contrast agent injection parameters and on datasets from an experimental setup using an anthropomorphic cerebrovascular phantom. For the computer simulation, the mean absolute error of the 3D centerline and 3D radius estimation was 0.42 and 0.25 mm, respectively. For the experimental datasets, the mean absolute error of the 3D centerline was 0.45 mm. Under pulsatile and nonpulsatile conditions, flow information can be used to enable a 3D vessel reconstruction from rotational angiography with inflow and possibly outflow of contrast agent. We found that the most important parameter for the quality of the reconstruction of centerline and radii is the range through which the x-ray system rotates in the time span of the injection. Good results were obtained if this range was at least 135 degrees. As a standard c-arm can rotate 205 degrees, typically one third of the acquisition can show inflow or outflow of contrast agent, which is required for the quantification of blood flow from rotational angiography.

Model-based blood flow quantification from rotational angiography.

For assessment of cerebrovascular diseases, it is beneficial to obtain three-dimensional (3D) information on vessel morphology and haemodynamics. Rotational angiography is routinely used to determine the 3D geometry. In this paper, we propose a method to exploit the same acquisition to determine the blood flow waveform and the mean volumetric flow rate in the large cerebral arteries. The method uses a model of contrast agent dispersion to determine the flow parameters from the spatial and temporal progression of the contrast agent concentration, represented by a flow map. Furthermore, it overcomes artefacts due to the rotation (overlapping vessels and foreshortened vessels at some projection angles) of the C-arm using a reliability map. The method was validated on images from different phantom experiments. We analysed different properties of the flow quantification method, including the influence of noise and the influence of the length of the analysed blood vessel. In most cases, the relative error was between 5% and 10% for the volumetric mean flow rate and between 10% and 15% for the blood flow waveform. The manual interaction took at most one minute and the computational time for the flow quantification was between 4 and 20 min on a PC. From this, we conclude that the method has the potential to give quantitative estimates of blood flow parameters during cerebrovascular interventions.