Four-chamber heart modeling and automatic segmentation for 3-D cardiac CT volumes using marginal space learning and steerable features

CTA coronary labeling through efficient geodesics between trees using anatomy priors

We present an efficient realization of recent work on unique geodesic paths between tree shapes for the application of matching coronary arteries to a standard model of coronary anatomy in order to label the coronary arteries. Automatically labeled coronary arteries would speed reporting for physicians. The efficiency of the approach and the quality of the results are enhanced using the relative position of detected cardiac structures. We explain how to efficiently compute the geodesic paths between tree shapes using Dijkstra's algorithm and we present a methodology to account for missing side branches during matching. For nearly all labels our approach shows promise compared with recent work and we results for 8 additional labels.

Probabilistic sparse matching for robust 3D/3D fusion in minimally invasive surgery

Classical surgery is being overtaken by minimally invasive and transcatheter procedures. As there is no direct view or access to the affected anatomy, advanced imaging techniques such as 3D C-arm computed tomography (CT) and C-arm fluoroscopy are routinely used in clinical practice for intraoperative guidance. However, due to constraints regarding acquisition time and device configuration, intraoperative modalities have limited soft tissue image quality and reliable assessment of the cardiac anatomy typically requires contrast agent, which is harmful to the patient and requires complex acquisition protocols. We propose a probabilistic sparse matching approach to fuse high-quality preoperative CT images and nongated, noncontrast intraoperative C-arm CT images by utilizing robust machine learning and numerical optimization techniques. Thus, high-quality patient-specific models can be extracted from the preoperative CT and mapped to the intraoperative imaging environment to guide minimally invasive procedures. Extensive quantitative experiments on 95 clinical datasets demonstrate that our model-based fusion approach has an average execution time of 1.56 s, while the accuracy of 5.48 mm between the anchor anatomy in both images lies within expert user confidence intervals. In direct comparison with image-to-image registration based on an open-source state-of-the-art medical imaging library and a recently proposed quasi-global, knowledge-driven multi-modal fusion approach for thoracic-abdominal images, our model-based method exhibits superior performance in terms of registration accuracy and robustness with respect to both target anatomy and anchor anatomy alignment errors.

Automated Localization of Multiple Pelvic Bone Structures on MRI

In this paper, we present a fully automated localization method for multiple pelvic bone structures on magnetic resonance images (MRI). Pelvic bone structures are at present identified manually on MRI to locate reference points for measurement and evaluation of pelvic organ prolapse (POP). Given that this is a time-consuming and subjective procedure, there is a need to localize pelvic bone structures automatically. However, bone structures are not easily differentiable from soft tissue on MRI as their pixel intensities tend to be very similar. In this paper, we present a model that combines support vector machines and nonlinear regression capturing global and local information to automatically identify the bounding boxes of bone structures on MRI. The model identifies the location of the pelvic bone structures by establishing the association between their relative locations and using local information such as texture features. Results show that the proposed method is able to locate the bone structures of interest accurately (dice similarity index >0.75) in 87-91% of the images. This research aims to enable accurate, consistent, and fully automated localization of bone structures on MRI to facilitate and improve the diagnosis of health conditions such as female POP.

Thoracic cavity segmentation algorithm using multiorgan extraction and surface fitting in volumetric CT

PURPOSE

To develop and validate a semiautomatic segmentation method for thoracic cavity volumetry and mediastinum fat quantification of patients with chronic obstructive pulmonary disease.

METHODS

The thoracic cavity region was separated by segmenting multiorgans, namely, the rib, lung, heart, and diaphragm. To encompass various lung disease-induced variations, the inner thoracic wall and diaphragm were modeled by using a three-dimensional surface-fitting method. To improve the accuracy of the diaphragm surface model, the heart and its surrounding tissue were segmented by a two-stage level set method using a shape prior. To assess the accuracy of the proposed algorithm, the algorithm results of 50 patients were compared to the manual segmentation results of two experts with more than 5 years of experience (these manual results were confirmed by an expert thoracic radiologist). The proposed method was also compared to three state-of-the-art segmentation methods. The metrics used to evaluate segmentation accuracy were volumetric overlap ratio (VOR), false positive ratio on VOR (FPRV), false negative ratio on VOR (FNRV), average symmetric absolute surface distance (ASASD), average symmetric squared surface distance (ASSSD), and maximum symmetric surface distance (MSSD).

RESULTS

In terms of thoracic cavity volumetry, the mean ± SD VOR, FPRV, and FNRV of the proposed method were (98.17 ± 0.84)%, (0.49 ± 0.23)%, and (1.34 ± 0.83)%, respectively. The ASASD, ASSSD, and MSSD for the thoracic wall were 0.28 ± 0.12, 1.28 ± 0.53, and 23.91 ± 7.64 mm, respectively. The ASASD, ASSSD, and MSSD for the diaphragm surface were 1.73 ± 0.91, 3.92 ± 1.68, and 27.80 ± 10.63 mm, respectively. The proposed method performed significantly better than the other three methods in terms of VOR, ASASD, and ASSSD.

CONCLUSIONS

The proposed semiautomatic thoracic cavity segmentation method, which extracts multiple organs (namely, the rib, thoracic wall, diaphragm, and heart), performed with high accuracy and may be useful for clinical purposes.

Automatic localization of the fetal cerebellum on 3D ultrasound volumes

PURPOSE

Assessment of the fetal cerebellar volume on 3D ultrasound data sets is very important in the clinical evaluation of the fetal growth and health. However, the irregular shape of the cerebellum and the strong artifacts of ultrasound images complicate the segmentation without manual intervention. In this paper, the authors propose an approach to locate the cerebellum automatically, which is considered as a prework of the segmentation.

METHODS

The authors present a weighted Hough transform and a constrained randomized Hough transform to detect the fetal brain midline and the skull, respectively. By combining the location information of these two structures with local image features, a constrained probabilistic boosting tree is then proposed to search the cerebellum.

RESULTS

This algorithm was tested on ultrasound volumes of the fetal head with the gestational age ranging from 20 to 33 weeks. Compared with manual measurements, this algorithm obtained a satisfactory performance with the mean Dice similarity coefficient of 0.92 and the average processing time of 0.75 s per case.

CONCLUSIONS

The results demonstrate that the proposed method is an automatic, fast, and accurate tool for searching the fetal cerebellum on ultrasound volumes.

Rapid manufacturing techniques for the tissue engineering of human heart valves

Three-dimensional (3D) printing technologies have reached a level of quality that justifies considering rapid manufacturing for medical applications. Herein, we introduce a new approach using 3D printing to simplify and improve the fabrication of human heart valve scaffolds by tissue engineering (TE). Custom-made human heart valve scaffolds are to be fabricated on a selective laser-sintering 3D printer for subsequent seeding with vascular cells from human umbilical cords. The scaffolds will be produced from resorbable polymers that must feature a number of specific properties: the structure, i.e. particle granularity and shape, and thermic properties must be feasible for the printing process. They must be suitable for the cell-seeding process and at the same time should be resorbable. They must be applicable for implementation in the human body and flexible enough to support the full functionality of the valve. The research focuses mainly on the search for a suitable scaffold material that allows the implementation of both the printing process to produce the scaffolds and the cell-seeding process, while meeting all of the above requirements. Computer tomographic data from patients were transformed into a 3D data model suitable for the 3D printer. Our current activities involve various aspects of the printing process, material research and the implementation of the cell-seeding process. Different resorbable polymeric materials have been examined and used to fabricate heart valve scaffolds by rapid manufacturing. Human vascular cells attached to the scaffold surface should migrate additionally into the inner structure of the polymeric samples. The ultimate intention of our approach is to establish a heart valve fabrication process based on 3D rapid manufacturing and TE. Based on the computer tomographic data of a patient, a custom-made scaffold for a valve will be produced on a 3D printer and populated preferably by autologous cells. The long-term goal is to support the growth of a new valve by a 3D structure resorbed by the human body in the course of the growth process. Our current activities can be characterized as basic research in which the fundamental steps of the technical process and its feasibility are investigated.

Three-dimensional reconstruction of a cardiac outline by magnetocardiography

A 3-D cardiac visualization is significantly helpful toward clinical applications of magnetocardiography (MCG), but the cardiac reconstruction requires a segmentation process using additional image modalities. This paper proposes a 3-D cardiac outline reconstruction method using only MCG measurement data without further imaging techniques. The cardiac outline was reconstructed by a combination of both spatial filtering and coherence mapping method. The strength of cardiac activities was first estimated by the array-gain constraint minimum-norm spatial filter with recursively updated gram matrix (AGMN-RUG). Then, waveforms were reconstructed at whole source grids, and the maximum source points of an atrium and ventricle were selected as a reference, respectively. Next, the coherence between each maximum source point and whole source points was compared by the coherence mapping method. A reconstructed cardiac outline was validated by comparing with an overlapped volume ratio when the reconstructed volume was identically matched with the original volume. The results obtained by the AGMN-RUG were compared to the results by other spatial filters. The accuracy of numerical simulation and phantom experiment by the AGMN-RUG was superior 10% and 8%, respectively, than the accuracy by the standardized low-resolution electromagnetic tomography. This accuracy demonstrated the efficacy of the proposed 3-D cardiac reconstruction method.

Effect of statistically derived fiber models on the estimation of cardiac electrical activation

Myocardial fiber orientation plays a critical role in the electrical activation and subsequent contraction of the heart. To increase the clinical potential of electrophysiological (EP) simulation for the study of cardiac phenomena and the planning of interventions, accurate personalization of the fibers is a necessary yet challenging task. Due to the difficulties associated with the in vivo imaging of cardiac fiber structure, researchers have developed alternative techniques to personalize fibers. Thus far, cardiac simulation was performed mainly based on rule-based fiber models. More recently, there has been a significant interest in data-driven and statistically derived fiber models. In particular, our predictive method in [1] allows us to estimate the unknown subject-specific fiber orientation based on the more easily available shape information. The aim of this work is to estimate the effect of using such statistical predictive models for the estimation of cardiac electrical activation times and patterns. To this end, we perform EP simulations based on a database of ten canine ex vivo diffusion tensor imaging (DTI) datasets that include normal and failing cases. To assess the strength of the fiber models under varying conditions, we consider both sinus rhythm and biventricular pacing simulations. The results show that 1) the statistically derived fibers improve the estimation of the local activation times by an average of 53.7% over traditional rule-based models, and that 2) the obtained electrical activations are consistently similar to those of the DTI-based fibers.

Interventional heart wall motion analysis with cardiac C-arm CT systems

Today, quantitative analysis of three-dimensional (3D) dynamics of the left ventricle (LV) cannot be performed directly in the catheter lab using a current angiographic C-arm system, which is the workhorse imaging modality for cardiac interventions. Therefore, myocardial wall analysis is completely based on the 2D angiographic images or pre-interventional 3D/4D imaging. In this paper, we present a complete framework to study the ventricular wall motion in 4D (3D+t) directly in the catheter lab. From the acquired 2D projection images, a dynamic 3D surface model of the LV is generated, which is then used to detect ventricular dyssynchrony. Different quantitative features to evaluate LV dynamics known from other modalities (ultrasound, magnetic resonance imaging) are transferred to the C-arm CT data. We use the ejection fraction, the systolic dyssynchrony index a 3D fractional shortening and the phase to maximal contraction (ϕi, max) to determine an indicator of LV dyssynchrony and to discriminate regionally pathological from normal myocardium. The proposed analysis tool was evaluated on simulated phantom LV data with and without pathological wall dysfunctions. The LV data used is publicly available online at https://conrad.stanford.edu/data/heart. In addition, the presented framework was tested on eight clinical patient data sets. The first clinical results demonstrate promising performance of the proposed analysis tool and encourage the application of the presented framework to a larger study in clinical practice.

Data-driven estimation of cardiac electrical diffusivity from 12-lead ECG signals

Diagnosis and treatment of dilated cardiomyopathy (DCM) is challenging due to a large variety of causes and disease stages. Computational models of cardiac electrophysiology (EP) can be used to improve the assessment and prognosis of DCM, plan therapies and predict their outcome, but require personalization. In this work, we present a data-driven approach to estimate the electrical diffusivity parameter of an EP model from standard 12-lead electrocardiograms (ECG). An efficient forward model based on a mono-domain, phenomenological Lattice-Boltzmann model of cardiac EP, and a boundary element-based mapping of potentials to the body surface is employed. The electrical diffusivity of myocardium, left ventricle and right ventricle endocardium is then estimated using polynomial regression which takes as input the QRS duration and electrical axis. After validating the forward model, we computed 9500 EP simulations on 19 different DCM patients in just under three seconds each to learn the regression model. Using this database, we quantify the intrinsic uncertainty of electrical diffusion for given ECG features and show in a leave-one-patient-out cross-validation that the regression method is able to predict myocardium diffusion within the uncertainty range. Finally, our approach is tested on the 19 cases using their clinical ECG. 84% of them could be personalized using our method, yielding mean prediction errors of 18.7ms for the QRS duration and 6.5° for the electrical axis, both values being within clinical acceptability. By providing an estimate of diffusion parameters from readily available clinical data, our data-driven approach could therefore constitute a first calibration step toward a more complete personalization of cardiac EP.

Automated quantification of epicardial adipose tissue (EAT) in coronary CT angiography; comparison with manual assessment and correlation with coronary artery disease

BACKGROUND

Epicardial adipose tissue (EAT) is emerging as a risk factor for coronary artery disease (CAD).

OBJECTIVE

The aim of this study was to determine the applicability and efficiency of automated EAT quantification.

METHODS

EAT volume was assessed both manually and automatically in 157 patients undergoing coronary CT angiography. Manual assessment consisted of a short-axis-based manual measurement, whereas automated assessment on both contrast and non-contrast-enhanced data sets was achieved through novel prototype software. Duration of both quantification methods was recorded, and EAT volumes were compared with paired samples t test. Correlation of volumes was determined with intraclass correlation coefficient; agreement was tested with Bland-Altman analysis. The association between EAT and CAD was estimated with logistic regression.

RESULTS

Automated quantification was significantly less time consuming than automated quantification (17 ± 2 seconds vs 280 ± 78 seconds; P < .0001). Although manual EAT volume differed significantly from automated EAT volume (75 ± 33 cm(³) vs 95 ± 45 cm(³); P < .001), a good correlation between both assessments was found (r = 0.76; P < .001). For all methods, EAT volume was positively associated with the presence of CAD. Stronger predictive value for the severity of CAD was achieved through automated quantification on both contrast-enhanced and non-contrast-enhanced data sets.

CONCLUSION

Automated EAT quantification is a quick method to estimate EAT and may serve as a predictor for CAD presence and severity.

Automatic 4D reconstruction of patient-specific cardiac mesh with 1-to-1 vertex correspondence from segmented contours lines

We propose an automatic algorithm for the reconstruction of patient-specific cardiac mesh models with 1-to-1 vertex correspondence. In this framework, a series of 3D meshes depicting the endocardial surface of the heart at each time step is constructed, based on a set of border delineated magnetic resonance imaging (MRI) data of the whole cardiac cycle. The key contribution in this work involves a novel reconstruction technique to generate a 4D (i.e., spatial-temporal) model of the heart with 1-to-1 vertex mapping throughout the time frames. The reconstructed 3D model from the first time step is used as a base template model and then deformed to fit the segmented contours from the subsequent time steps. A method to determine a tree-based connectivity relationship is proposed to ensure robust mapping during mesh deformation. The novel feature is the ability to handle intra- and inter-frame 2D topology changes of the contours, which manifests as a series of merging and splitting of contours when the images are viewed either in a spatial or temporal sequence. Our algorithm has been tested on five acquisitions of cardiac MRI and can successfully reconstruct the full 4D heart model in around 30 minutes per subject. The generated 4D heart model conforms very well with the input segmented contours and the mesh element shape is of reasonably good quality. The work is important in the support of downstream computational simulation activities.

Analyzing training information from random forests for improved image segmentation

Labeled training data are used for challenging medical image segmentation problems to learn different characteristics of the relevant domain. In this paper, we examine random forest (RF) classifiers, their learned knowledge during training and ways to exploit it for improved image segmentation. Apart from learning discriminative features, RFs also quantify their importance in classification. Feature importance is used to design a feature selection strategy critical for high segmentation and classification accuracy, and also to design a smoothness cost in a second-order MRF framework for graph cut segmentation. The cost function combines the contribution of different image features like intensity, texture, and curvature information. Experimental results on medical images show that this strategy leads to better segmentation accuracy than conventional graph cut algorithms that use only intensity information in the smoothness cost.

Fitting C² continuous parametric surfaces to frontiers delimiting physiologic structures

We present a technique to fit C(2) continuous parametric surfaces to scattered geometric data points forming frontiers delimiting physiologic structures in segmented images. Such mathematical representation is interesting because it facilitates a large number of operations in modeling. While the fitting of C(2) continuous parametric curves to scattered geometric data points is quite trivial, the fitting of C(2) continuous parametric surfaces is not. The difficulty comes from the fact that each scattered data point should be assigned a unique parametric coordinate, and the fit is quite sensitive to their distribution on the parametric plane. We present a new approach where a polygonal (quadrilateral or triangular) surface is extracted from the segmented image. This surface is subsequently projected onto a parametric plane in a manner to ensure a one-to-one mapping. The resulting polygonal mesh is then regularized for area and edge length. Finally, from this point, surface fitting is relatively trivial. The novelty of our approach lies in the regularization of the polygonal mesh. Process performance is assessed with the reconstruction of a geometric model of mouse heart ventricles from a computerized tomography scan. Our results show an excellent reproduction of the geometric data with surfaces that are C(2) continuous.

A complete system for automatic extraction of left ventricular myocardium from CT images using shape segmentation and contour evolution

The left ventricular myocardium plays a key role in the entire circulation system and an automatic delineation of the myocardium is a prerequisite for most of the subsequent functional analysis. In this paper, we present a complete system for an automatic segmentation of the left ventricular myocardium from cardiac computed tomography (CT) images using the shape information from images to be segmented. The system follows a coarse-to-fine strategy by first localizing the left ventricle and then deforming the myocardial surfaces of the left ventricle to refine the segmentation. In particular, the blood pool of a CT image is extracted and represented as a triangulated surface. Then, the left ventricle is localized as a salient component on this surface using geometric and anatomical characteristics. After that, the myocardial surfaces are initialized from the localization result and evolved by applying forces from the image intensities with a constraint based on the initial myocardial surface locations. The proposed framework has been validated on 34-human and 12-pig CT images, and the robustness and accuracy are demonstrated.

Multi-part modeling and segmentation of left atrium in C-arm CT for image-guided ablation of atrial fibrillation

As a minimally invasive surgery to treat atrial fibrillation (AF), catheter based ablation uses high radio-frequency energy to eliminate potential sources of abnormal electrical events, especially around the ostia of pulmonary veins (PV). Fusing a patient-specific left atrium (LA) model (including LA chamber, appendage, and PVs) with electro-anatomical maps or overlaying the model onto 2-D real-time fluoroscopic images provides valuable visual guidance during the intervention. In this work, we present a fully automatic LA segmentation system on nongated C-arm computed tomography (C-arm CT) data, where thin boundaries between the LA and surrounding tissues are often blurred due to the cardiac motion artifacts. To avoid segmentation leakage, the shape prior should be exploited to guide the segmentation. A single holistic shape model is often not accurate enough to represent the whole LA shape population under anatomical variations, e.g., the left common PVs vs. separate left PVs. Instead, a part based LA model is proposed, which includes the chamber, appendage, four major PVs, and right middle PVs. Each part is a much simpler anatomical structure compared to the holistic one and can be segmented using a model-based approach (except the right middle PVs). After segmenting the LA parts, the gaps and overlaps among the parts are resolved and segmentation of the ostia region is further refined. As a common anatomical variation, some patients may contain extra right middle PVs, which are segmented using a graph cuts algorithm under the constraints from the already extracted major right PVs. Our approach is computationally efficient, taking about 2.6 s to process a volume with 256 × 256 × 245 voxels. Experiments on 687 C-arm CT datasets demonstrate its robustness and state-of-the-art segmentation accuracy.

Sparse appearance learning based automatic coronary sinus segmentation in CTA

Interventional cardiologists are often challenged by a high degree of variability in the coronary venous anatomy during coronary sinus cannulation and left ventricular epicardial lead placement for cardiac resynchronization therapy (CRT), making it important to have a precise and fully-automatic segmentation solution for detecting the coronary sinus. A few approaches have been proposed for automatic segmentation of tubular structures utilizing various vesselness measurements. Although working well on contrasted coronary arteries, these methods fail in segmenting the coronary sinus that has almost no contrast in computed tomography angiography (CTA) data, making it difficult to distinguish from surrounding tissues. In this work we propose a multiscale sparse appearance learning based method for estimating vesselness towards automatically extracting the centerlines. Instead of modeling the subtle discrimination at the low-level intensity, we leverage the flexibility of sparse representation to model the inherent spatial coherence of vessel/background appearance and derive a vesselness measurement. After centerline extraction, the coronary sinus lumen is segmented using a learning based boundary detector and Markov random field (MRF) based optimal surface extraction. Quantitative evaluation on a large cardiac CTA dataset (consisting of 204 3D volumes) demonstrates the superior accuracy of the proposed method in both centerline extraction and lumen segmentation, compared to the state-of-the-art.

An automatic service for the personalization of ventricular cardiac meshes

Computational cardiac physiology has great potential to improve the management of cardiovascular diseases. One of the main bottlenecks in this field is the customization of the computational model to the anatomical and physiological status of the patient. We present a fully automatic service for the geometrical personalization of cardiac ventricular meshes with high-order interpolation from segmented images. The method is versatile (able to work with different species and disease conditions) and robust (fully automatic results fulfilling accuracy and quality requirements in 87% of 255 cases). Results also illustrate the capability to minimize the impact of segmentation errors, to overcome the sparse resolution of dynamic studies and to remove the sometimes unnecessary anatomical detail of papillary and trabecular structures. The smooth meshes produced can be used to simulate cardiac function, and in particular mechanics, or can be used as diagnostic descriptors of anatomical shape by cardiologists. This fully automatic service is deployed in a cloud infrastructure, and has been made available and accessible to the scientific community.

Automatic segmentation of the left atrium from MR images via variational region growing with a moments-based shape prior

The planning and evaluation of left atrial ablation procedures are commonly based on the segmentation of the left atrium, which is a challenging task due to large anatomical variations. In this paper, we propose an automatic approach for segmenting the left atrium from magnetic resonance imagery. The segmentation problem is formulated as a problem in variational region growing. In particular, the method starts locally by searching for a seed region of the left atrium from an MR slice. A global constraint is imposed by applying a shape prior to the left atrium represented by Zernike moments. The overall growing process is guided by the robust statistics of intensities from the seed region along with the shape prior to capture the entire atrial region. The robustness and accuracy of our approach are demonstrated by experimental results from 64 human MR images.

Automatic Detection and Segmentation of Crohn's Disease Tissues From Abdominal MRI

We propose an information processing pipeline for segmenting parts of the bowel in abdominal magnetic resonance images that are affected with Crohn's disease. Given a magnetic resonance imaging test volume, it is first oversegmented into supervoxels and each supervoxel is analyzed to detect presence of Crohn's disease using random forest (RF) classifiers. The supervoxels identified as containing diseased tissues define the volume of interest (VOI). All voxels within the VOI are further investigated to segment the diseased region. Probability maps are generated for each voxel using a second set of RF classifiers which give the probabilities of each voxel being diseased, normal or background. The negative log-likelihood of these maps are used as penalty costs in a graph cut segmentation framework. Low level features like intensity statistics, texture anisotropy and curvature asymmetry, and high level context features are used at different stages. Smoothness constraints are imposed based on semantic information (importance of each feature to the classification task) derived from the second set of learned RF classifiers. Experimental results show that our method achieves high segmentation accuracy with Dice metric values of 0.90 ± 0.04 and Hausdorff distance of 7.3 ± 0.8 mm. Semantic information and context features are an integral part of our method and are robust to different levels of added noise.

Combining multiple dynamic models and deep learning architectures for tracking the left ventricle endocardium in ultrasound data

We present a new statistical pattern recognition approach for the problem of left ventricle endocardium tracking in ultrasound data. The problem is formulated as a sequential importance resampling algorithm such that the expected segmentation of the current time step is estimated based on the appearance, shape, and motion models that take into account all previous and current images and previous segmentation contours produced by the method. The new appearance and shape models decouple the affine and nonrigid segmentations of the left ventricle to reduce the running time complexity. The proposed motion model combines the systole and diastole motion patterns and an observation distribution built by a deep neural network. The functionality of our approach is evaluated using a dataset of diseased cases containing 16 sequences and another dataset of normal cases comprised of four sequences, where both sets present long axis views of the left ventricle. Using a training set comprised of diseased and healthy cases, we show that our approach produces more accurate results than current state-of-the-art endocardium tracking methods in two test sequences from healthy subjects. Using three test sequences containing different types of cardiopathies, we show that our method correlates well with interuser statistics produced by four cardiologists.

PCG-cut: graph driven segmentation of the prostate central gland

Prostate cancer is the most abundant cancer in men, with over 200,000 expected new cases and around 28,000 deaths in 2012 in the US alone. In this study, the segmentation results for the prostate central gland (PCG) in MR scans are presented. The aim of this research study is to apply a graph-based algorithm to automated segmentation (i.e. delineation) of organ limits for the prostate central gland. The ultimate goal is to apply automated segmentation approach to facilitate efficient MR-guided biopsy and radiation treatment planning. The automated segmentation algorithm used is graph-driven based on a spherical template. Therefore, rays are sent through the surface points of a polyhedron to sample the graph's nodes. After graph construction--which only requires the center of the polyhedron defined by the user and located inside the prostate center gland--the minimal cost closed set on the graph is computed via a polynomial time s-t-cut, which results in the segmentation of the prostate center gland's boundaries and volume. The algorithm has been realized as a C++ module within the medical research platform MeVisLab and the ground truth of the central gland boundaries were manually extracted by clinical experts (interventional radiologists) with several years of experience in prostate treatment. For evaluation the automated segmentations of the proposed scheme have been compared with the manual segmentations, yielding an average Dice Similarity Coefficient (DSC) of 78.94 ± 10.85%.

Reconstructing patient-specific cardiac models from contours via Delaunay triangulation and graph-cuts

This study proposes a novel method to reconstruct the left cardiac structure from contours. Given the contours representing left ventricle (LV), left atrium (LA), and aorta (AO), re-orientation, contour matching, extrapolation, and interpolation are performed sequentially. The processed data are then reconstructed via a variational method. The weighted minimal surface model is revised to handle the multi-phase cases, which happens at the LV-LA-AO junction. A Delaunay-based tetrahedral mesh is generated to discretize the domain while the max-flow/min-cut algorithm is utilized as the minimization tool. The reconstructed model including LV, LA, and AO structure is extracted from the mesh and post-processed further. Numerical examples show the robustness and effectiveness of the proposed method.

Automatic delineation of the myocardial wall from CT images via shape segmentation and variational region growing

Prognosis and diagnosis of cardiac diseases frequently require quantitative evaluation of the ventricle volume, mass, and ejection fraction. The delineation of the myocardial wall is involved in all of these evaluations, which is a challenging task due to large variations in myocardial shapes and image quality. In this paper, we present an automatic method for extracting the myocardial wall of the left and right ventricles from cardiac CT images. In the method, the left and right ventricles are located sequentially, in which each ventricle is detected by first identifying the endocardium and then segmenting the epicardium. To this end, the endocardium is localized by utilizing its geometric features obtained on-line from a CT image. After that, a variational region-growing model is employed to extract the epicardium of the ventricles. In particular, the location of the endocardium of the left ventricle is determined via using an active contour model on the blood-pool surface. To localize the right ventricle, the active contour model is applied on a heart surface extracted based on the left ventricle segmentation result. The robustness and accuracy of the proposed approach is demonstrated by experimental results from 33 human and 12 pig CT images.

Evaluation of interpolation methods for surface-based motion compensated tomographic reconstruction for cardiac angiographic C-arm data

PURPOSE

For interventional cardiac procedures, anatomical and functional information about the cardiac chambers is of major interest. With the technology of angiographic C-arm systems it is possible to reconstruct intraprocedural three-dimensional (3D) images from 2D rotational angiographic projection data (C-arm CT). However, 3D reconstruction of a dynamic object is a fundamental problem in C-arm CT reconstruction. The 2D projections are acquired over a scan time of several seconds, thus the projection data show different states of the heart. A standard FDK reconstruction algorithm would use all acquired data for a filtered backprojection and result in a motion-blurred image. In this approach, a motion compensated reconstruction algorithm requiring knowledge of the 3D heart motion is used. The motion is estimated from a previously presented 3D dynamic surface model. This dynamic surface model results in a sparse motion vector field (MVF) defined at control points. In order to perform a motion compensated reconstruction, a dense motion vector field is required. The dense MVF is generated by interpolation of the sparse MVF. Therefore, the influence of different motion interpolation methods on the reconstructed image quality is evaluated.

METHODS

Four different interpolation methods, thin-plate splines (TPS), Shepard's method, a smoothed weighting function, and a simple averaging, were evaluated. The reconstruction quality was measured on phantom data, a porcine model as well as on in vivo clinical data sets. As a quality index, the 2D overlap of the forward projected motion compensated reconstructed ventricle and the segmented 2D ventricle blood pool was quantitatively measured with the Dice similarity coefficient and the mean deviation between extracted ventricle contours. For the phantom data set, the normalized root mean square error (nRMSE) and the universal quality index (UQI) were also evaluated in 3D image space.

RESULTS

The quantitative evaluation of all experiments showed that TPS interpolation provided the best results. The quantitative results in the phantom experiments showed comparable nRMSE of ≈0.047 ± 0.004 for the TPS and Shepard's method. Only slightly inferior results for the smoothed weighting function and the linear approach were achieved. The UQI resulted in a value of ≈ 99% for all four interpolation methods. On clinical human data sets, the best results were clearly obtained with the TPS interpolation. The mean contour deviation between the TPS reconstruction and the standard FDK reconstruction improved in the three human cases by 1.52, 1.34, and 1.55 mm. The Dice coefficient showed less sensitivity with respect to variations in the ventricle boundary.

CONCLUSIONS

In this work, the influence of different motion interpolation methods on left ventricle motion compensated tomographic reconstructions was investigated. The best quantitative reconstruction results of a phantom, a porcine, and human clinical data sets were achieved with the TPS approach. In general, the framework of motion estimation using a surface model and motion interpolation to a dense MVF provides the ability for tomographic reconstruction using a motion compensation technique.

A framework for personalization of coronary flow computations during rest and hyperemia

We introduce a Computational Fluid Dynamics (CFD) based method for performing patient-specific coronary hemodynamic computations under two conditions: at rest and during drug-induced hyperemia. The proposed method is based on a novel estimation procedure for determining the boundary conditions from non-invasively acquired patient data at rest. A multi-variable feedback control framework ensures that the computed mean arterial pressure and the flow distribution matches the estimated values for an individual patient during the rest state. The boundary conditions at hyperemia are derived from the respective rest-state values via a transfer function that models the vasodilation phenomenon. Simulations are performed on a coronary tree where a 65% diameter stenosis is introduced in the left anterior descending (LAD) artery, with the boundary conditions estimated using the proposed method. The results demonstrate that the estimation of the hyperemic resistances is crucial in order to obtain accurate values for pressure and flow rates. Results from an exhaustive sensitivity analysis have been presented for analyzing the variability of trans-stenotic pressure drop and Fractional Flow Reserve (FFR) values with respect to various measurements and assumptions.

Automatic segmentation of the left atrium from MRI images using salient feature and contour evolution

We propose an automatic approach for segmenting the left atrium from MRI images. In particular, the thoracic aorta is detected and used as a salient feature to find a seed region that lies inside the left atrium. A hybrid energy that combines robust statistics and localized region intensity information is employed to evolve active contours from the seed region to capture the whole left atrium. The experimental results demonstrate the accuracy and robustness of our approach.

3D cardiac motion reconstruction from CT data and tagged MRI

In this paper we present a novel method for left ventricle (LV) endocardium motion reconstruction using high resolution CT data and tagged MRI. High resolution CT data provide anatomic details on the LV endocardial surface, such as the papillary muscle and trabeculae carneae. Tagged MRI provides better time resolution. The combination of these two imaging techniques can give us better understanding on left ventricle motion. The high resolution CT images are segmented with mean shift method and generate the LV endocardium mesh. The meshless deformable model built with high resolution endocardium surface from CT data fit to the tagged MRI of the same phase. 3D deformation of the myocardium is computed with the Lagrangian dynamics and local Laplacian deformation. The segmented inner surface of left ventricle is compared with the heart inner surface picture and show high agreement. The papillary muscles are attached to the inner surface with roots. The free wall of the left ventricle inner surface is covered with trabeculae carneae. The deformation of the heart wall and the papillary muscle in the first half of the cardiac cycle is presented. The motion reconstruction results are very close to the live heart video.

Automated quantification of mitral regurgitation by three dimensional real time full volume color Doppler transthoracic echocardiography: a validation with cardiac magnetic resonance imaging and comparison with two dimensional quantitative methods

BACKGROUND

Accurate assessment of mitral regurgitation (MR) severity is crucial for clinical decision-making and optimizing patient outcomes. Recent advances in real-time three dimensional (3D) echocardiography provide the option of real-time full volume color Doppler echocardiography (FVCD) measurements. This makes it practical to quantify MR by subtracting aortic stroke volume from the volume of mitral inflow in an automated manner.

METHODS

Thirty-two patients with more than a moderate degree of MR assessed by transthoracic echocardiography (TTE) were consecutively enrolled during this study. MR volume was measured by 1) two dimensional (2D) Doppler TTE, using the proximal isovelocity surface area (PISA) and the volumetric quantification methods (VM). Then, 2) real time 3D-FVCD was subsequently obtained, and dedicated software was used to quantify the MR volume. MR volume was also measured using 3) phase contrast cardiac magnetic resonance imaging (PC-CMR). In each patient, all these measurements were obtained within the same day. Automated MR quantification was feasible in 30 of 32 patients.

RESULTS

The mean regurgitant volume quantified by 2D-PISA, 2D-VM, 3D-FVCD, and PC-CMR was 72.1 ± 27.7, 79.9 ± 36.9, 69.9 ± 31.5, and 64.2 ± 30.7 mL, respectively (p = 0.304). There was an excellent correlation between the MR volume measured by PC-CMR and 3D-FVCD (r = 0.85, 95% CI 0.70-0.93, p < 0.001). Compared with PC-CMR, Bland-Altman analysis for 3D-FVCD showed a good agreement (2 standard deviations: 34.3 mL) than did 2D-PISA or 2D-VM (60.0 and 62.8 mL, respectively).

CONCLUSION

Automated quantification of MR with 3D-FVCD is feasible and accurate. It is a promising tool for the real-time 3D echocardiographic assessment of patients with MR.

Robust infrarenal aortic aneurysm lumen centerline detection for rupture status classification

The objective of this work is to develop a robust method for human abdominal aortic aneurysm (AAA) centerline detection that can contribute to the accurate computation of features for the prediction of AAA rupture risk. A semiautomatic algorithm is proposed for detecting the lumen centerline in contrast-enhanced abdominal computed tomography images based on online adaboost classifiers, which does not require prior image segmentation. The algorithm was developed and applied to thirty ruptured and thirty unruptured AAA image data sets and the tortuosities of the detected centerline were measured to assess the correlation between AAA tortuosity and the binary ruptured and unruptured labels. The lumen of each data set was segmented manually by a trained radiologist and the resulting centerlines of each data set were defined as the gold standard to evaluate the accuracy of the algorithm and to compare it against two widely used segmentation techniques. The average mean relative accuracy of the offline adaboost classifier is 91.9% with a standard deviation of 1.6%; for the online adaboost classifier it is 93.6% with a standard deviation of 1.9% (p<0.05). The online adaboost classifier outperforms the offline adaboost classifier while their computational costs are similar. Aneurysm tortuosity computed from an accurately derived lumen centerline using online adaboost is statistically higher for ruptured aneurysms compared to unruptured aneurysms, indicating that tortuosity can be used to assess rupture risk in the vascular clinic.

Benchmarking framework for myocardial tracking and deformation algorithms: an open access database

In this paper we present a benchmarking framework for the validation of cardiac motion analysis algorithms. The reported methods are the response to an open challenge that was issued to the medical imaging community through a MICCAI workshop. The database included magnetic resonance (MR) and 3D ultrasound (3DUS) datasets from a dynamic phantom and 15 healthy volunteers. Participants processed 3D tagged MR datasets (3DTAG), cine steady state free precession MR datasets (SSFP) and 3DUS datasets, amounting to 1158 image volumes. Ground-truth for motion tracking was based on 12 landmarks (4 walls at 3 ventricular levels). They were manually tracked by two observers in the 3DTAG data over the whole cardiac cycle, using an in-house application with 4D visualization capabilities. The median of the inter-observer variability was computed for the phantom dataset (0.77 mm) and for the volunteer datasets (0.84 mm). The ground-truth was registered to 3DUS coordinates using a point based similarity transform. Four institutions responded to the challenge by providing motion estimates for the data: Fraunhofer MEVIS (MEVIS), Bremen, Germany; Imperial College London - University College London (IUCL), UK; Universitat Pompeu Fabra (UPF), Barcelona, Spain; Inria-Asclepios project (INRIA), France. Details on the implementation and evaluation of the four methodologies are presented in this manuscript. The manually tracked landmarks were used to evaluate tracking accuracy of all methodologies. For 3DTAG, median values were computed over all time frames for the phantom dataset (MEVIS=1.20mm, IUCL=0.73 mm, UPF=1.10mm, INRIA=1.09 mm) and for the volunteer datasets (MEVIS=1.33 mm, IUCL=1.52 mm, UPF=1.09 mm, INRIA=1.32 mm). For 3DUS, median values were computed at end diastole and end systole for the phantom dataset (MEVIS=4.40 mm, UPF=3.48 mm, INRIA=4.78 mm) and for the volunteer datasets (MEVIS=3.51 mm, UPF=3.71 mm, INRIA=4.07 mm). For SSFP, median values were computed at end diastole and end systole for the phantom dataset(UPF=6.18 mm, INRIA=3.93 mm) and for the volunteer datasets (UPF=3.09 mm, INRIA=4.78 mm). Finally, strain curves were generated and qualitatively compared. Good agreement was found between the different modalities and methodologies, except for radial strain that showed a high variability in cases of lower image quality.

Generating anatomical models of the heart and the aorta from medical images for personalized physiological simulations

The anatomy and motion of the heart and the aorta are essential for patient-specific simulations of cardiac electrophysiology, wall mechanics and hemodynamics. Within the European integrated project euHeart, algorithms have been developed that allow to efficiently generate patient-specific anatomical models from medical images from multiple imaging modalities. These models, for instance, account for myocardial deformation, cardiac wall motion, and patient-specific tissue information like myocardial scar location. Furthermore, integration of algorithms for anatomy extraction and physiological simulations has been brought forward. Physiological simulations are linked closer to anatomical models by encoding tissue properties, like the muscle fibers, into segmentation meshes. Biophysical constraints are also utilized in combination with image analysis to assess tissue properties. Both examples show directions of how physiological simulations could provide new challenges and stimuli for image analysis research in the future.

LBM-EP: Lattice-Boltzmann method for fast cardiac electrophysiology simulation from 3D images

Current treatments of heart rhythm troubles require careful planning and guidance for optimal outcomes. Computational models of cardiac electrophysiology are being proposed for therapy planning but current approaches are either too simplified or too computationally intensive for patient-specific simulations in clinical practice. This paper presents a novel approach, LBM-EP, to solve any type of mono-domain cardiac electrophysiology models at near real-time that is especially tailored for patient-specific simulations. The domain is discretized on a Cartesian grid with a level-set representation of patient's heart geometry, previously estimated from images automatically. The cell model is calculated node-wise, while the transmembrane potential is diffused using Lattice-Boltzmann method within the domain defined by the level-set. Experiments on synthetic cases, on a data set from CESC'10 and on one patient with myocardium scar showed that LBM-EP provides results comparable to an FEM implementation, while being 10 - 45 times faster. Fast, accurate, scalable and requiring no specific meshing, LBM-EP paves the way to efficient and detailed models of cardiac electrophysiology for therapy planning.