Three-dimensional modeling for functional analysis of cardiac images: a review

A game-theoretic framework for landmark-based image segmentation

A novel game-theoretic framework for landmark-based image segmentation is presented. Landmark detection is formulated as a game, in which landmarks are players, landmark candidate points are strategies, and likelihoods that candidate points represent landmarks are payoffs, determined according to the similarity of image intensities and spatial relationships between the candidate points in the target image and their corresponding landmarks in images from the training set. The solution of the formulated game-theoretic problem is the equilibrium of candidate points that represent landmarks in the target image and is obtained by a novel iterative scheme that solves the segmentation problem in polynomial time. The object boundaries are finally extracted by applying dynamic programming to the optimal path searching problem between the obtained adjacent landmarks. The performance of the proposed framework was evaluated for segmentation of lung fields from chest radiographs and heart ventricles from cardiac magnetic resonance cross sections. The comparison to other landmark-based segmentation techniques shows that the results obtained by the proposed game-theoretic framework are highly accurate and precise in terms of mean boundary distance and area overlap. Moreover, the framework overcomes several shortcomings of the existing techniques, such as sensitivity to initialization and convergence to local optima.

4D statistical shape modeling of the left ventricle in cardiac MR images

PURPOSE

Statistical shape models have shown improved reliability and consistency in cardiac image segmentation. They incorporate a sufficient amount of a priori knowledge from the training datasets and solve some major problems such as noise and image artifacts or partial volume effect. In this paper, we construct a 4D statistical model of the left ventricle using human cardiac short-axis MR images.

METHODS

Kernel PCA is utilized to explore the nonlinear variation of a population. The distribution of the landmarks is divided into the inter- and intra-subject subspaces. We compare the result of Kernel PCA with linear PCA and ICA for each of these subspaces. The initial atlas in natural coordinate system is built for the end-diastolic frame. The landmarks extracted from it are propagated to all frames of all datasets. We apply the 4D KPCA-based ASM for segmentation of all phases of a cardiac cycle and compare it with the conventional ASM.

RESULTS

The proposed statistical model is evaluated by calculating the compactness capacity, specificity and generalization ability measures. We investigate the behavior of the nonlinear model for different values of the kernel parameter. The results show that the model built by KPCA is less compact than PCA but more compact than ICA. Although for a constant number of modes the reconstruction error is a little higher for the KPCA-based statistical model, it produces a statistical model with substantially better specificity than PCA- and ICA-based models.

CONCLUSION

Quantitative analysis of the results demonstrates that our method improves the segmentation accuracy.

MR assessment of regional myocardial mechanics

Regional myocardial function can be measured by several MR techniques including tissue tagging, phase velocity mapping, and more recently, displacement encoding with stimulated echoes (DENSE) and strain encoding (SENC). Each of these techniques was developed separately and has undergone significant change since its original implementation. As a result, in the current literature, the common features and the differences between the techniques and what they measure are often unclear and confusing. This review article delivers an extensively referenced introductory text which clarifies the current methodology from the starting point of the Bloch equations. By doing this in a consistent way for each method, the similarities and differences between them are highlighted. In addition, their capabilities and limitations are discussed, together with their relative advantages and disadvantages. While the focus is on sequence design and development, the principal parameters measured by each technique are also summarized, together with brief results, with the reader being directed to the extensive literature on data processing and clinical applications for more detail.

Validation of continuously tagged MRI for the measurement of dynamic 3D skeletal muscle tissue deformation

PURPOSE

Typically spatial modulation of the magnetization (SPAMM) tagged magnetic resonance imaging (MRI) requires many repeated motion cycles limiting the applicability to highly repeatable tissue motions only. This paper describes the validation of a novel SPAMM tagged MRI and post-processing framework for the measurement of complex and dynamic 3D soft tissue deformation following just three motion cycles. Techniques are applied to indentation induced deformation measurement of the upper arm and a silicone gel phantom.

METHODS

A SPAMM tagged MRI methodology is presented allowing continuous (3.3-3.6 Hz) sampling of 3D dynamic soft tissue deformation using non segmented 3D acquisitions. The 3D deformation is reconstructed by the combination of three mutually orthogonal tagging directions, thus requiring only three repeated motion cycles. In addition a fully automatic post-processing framework is presented employing Gabor scale-space and filter-bank analysis for tag extrema segmentation and triangulated surface fitting aided by Gabor filter bank derived surface normals. Deformation is derived following tracking of tag surface triplet triangle intersections. The dynamic deformation measurements were validated using indentation tests (∼20 mm deep at 12 mm/s) on a silicone gel soft tissue phantom containing contrasting markers which provide a reference measure of deformation. In addition, the techniques were evaluated in vivo for dynamic skeletal muscle tissue deformation measurement during indentation of the biceps region of the upper arm in a volunteer.

RESULTS

For the phantom and volunteer tag point location precision were 44 and 92 μm, respectively resulting in individual displacements precisions of 61 and 91 μm, respectively. For both the phantom and volunteer data cumulative displacement measurement accuracy could be evaluated and the difference between initial and final locations showed a mean and standard deviation of 0.44 and 0.59 mm for the phantom and 0.40 and 0.73 mm for the human data. Finally accuracy of (cumulative) displacement was evaluated using marker tracking in the silicone gel phantom. Differences between true and predicted marker locations showed a mean of 0.35 mm and a standard deviation of 0.63 mm.

CONCLUSIONS

A novel SPAMM tagged MRI and fully automatic post-processing framework for the measurement of complex 3D dynamic soft tissue deformation following just three repeated motion cycles was presented. The techniques demonstrate dynamic measurement of complex 3D soft tissue deformation at subvoxel accuracy and precision and were validated for 3.3-3.6 Hz sampling of deformation speeds up to 12 mm/s.

Quantitative analysis of 3D mitral complex geometry using support vector machines

Quantitative analysis of 3D mitral complex geometry is crucial for a better understanding of its dysfunction. This work aims to characterize the geometry of the mitral complex and utilize a support-vector-machine-based classifier from geometric parameters to support the diagnosis of congenital mitral regurgitation (MR). The method has the following steps: (1) description of the 3D geometry of the mitral complex and establishment of its local reference coordinate system, (2) calculation of geometric parameters and (3) analysis and classification of these parameters. With a control group of 20 normal young children (11 boys, 9 girls, mean age 5.96 ± 3.12 years) and with the normal structure of mitral apparatus, 20 patients (9 boys, 11 girls, mean age 5.59 ± 3.30 years) suffering from severe congenital MR are studied in this study. The average classification accuracy is up to 90.0% of the present population, with the possibility of exploring quantitative association between the mitral complex geometry and the mechanism of congenital MR.

Automatic model-based contour detection of left ventricle myocardium from cardiac CT images

PURPOSE

For accurate evaluation of myocardial perfusion on computed tomography images, precise identification of the myocardial borders of the left ventricle (LV) is mandatory. In this article, we propose a method to detect the contour of LV myocardium automatically and accurately.

METHODS

Our detection method is based on active shape model. For precise detection, we estimate the pose and shape parameters separately by three steps: LV coordinate system estimation, myocardial shape estimation, and transformation. In LV coordinate system estimation, we detect heart features followed by the entire LV by introducing machine-learning approach. Since the combination of two types feature detection covers the LV variation, such as pose or shape, we can estimate the LV coordinate system robustly. In myocardial shape estimation, we minimize the energy function including pattern error around myocardium with adjustment of pattern model to input image using estimated concentration of contrast dye. Finally, we detect LV myocardial contours in the input images by transforming the estimated myocardial shape using the matrix composed of the vectors calculated by the LV coordinate system estimation.

RESULTS

In our experiments with 211 images from 145 patients, mean myocardial contours point-to-point errors for our method as compared to ground truth were 1.02 mm for LV endocardium and 1.07 mm for LV epicardium. The average computation time was 2.4 s (on a 3.46 GHz processor with 2-multithreading process).

CONCLUSIONS

Our method achieved accurate and fast myocardial contour detection which may be sufficient for myocardial perfusion examination.

Three-dimensional expansion of a dynamic programming method for boundary detection and its application to sequential magnetic resonance imaging (MRI)

This study proposes a fast 3D dynamic programming expansion to find a shortest surface in a 3D matrix. This algorithm can detect boundaries in an image sequence. Using phantom image studies with added uniform distributed noise from different SNRs, the unsigned error of this proposed method is investigated. Comparing the automated results to the gold standard, the best averaged relative unsigned error of the proposed method is 0.77% (SNR = 20 dB), and its corresponding parameter values are reported. We further apply this method to detect the boundary of the real superficial femoral artery (SFA) in MRI sequences without a contrast injection. The manual tracings on the SFA boundaries are performed by well-trained experts to be the gold standard. The comparisons between the manual tracings and automated results are made on 16 MRI sequences (800 total images). The average unsigned error rate is 2.4% (SD = 2.0%). The results demonstrate that the proposed method can perform qualitatively better than the 2D dynamic programming for vessel boundary detection on MRI sequences.

Cardiac motion and deformation recovery from MRI: a review

Magnetic resonance imaging (MRI) is a highly advanced and sophisticated imaging modality for cardiac motion tracking and analysis, capable of providing 3D analysis of global and regional cardiac function with great accuracy and reproducibility. In the past few years, numerous efforts have been devoted to cardiac motion recovery and deformation analysis from MR image sequences. Many approaches have been proposed for tracking cardiac motion and for computing deformation parameters and mechanical properties of the heart from a variety of cardiac MR imaging techniques. In this paper, an updated and critical review of cardiac motion tracking methods including major references and those proposed in the past ten years is provided. The MR imaging and analysis techniques surveyed are based on cine MRI, tagged MRI, phase contrast MRI, DENSE, and SENC. This paper can serve as a tutorial for new researchers entering the field.

An image-based comprehensive approach for automatic segmentation of left ventricle from cardiac short axis cine MR images

Segmentation of the left ventricle is important in the assessment of cardiac functional parameters. Manual segmentation of cardiac cine MR images for acquiring these parameters is time-consuming. Accuracy and automation are the two important criteria in improving cardiac image segmentation methods. In this paper, we present a comprehensive approach to segment the left ventricle from short axis cine cardiac MR images automatically. Our method incorporates a number of image processing and analysis techniques including thresholding, edge detection, mathematical morphology, and image filtering to build an efficient process flow. This process flow makes use of various features in cardiac MR images to achieve high accurate segmentation results. Our method was tested on 45 clinical short axis cine cardiac images and the results are compared with manual delineated ground truth (average perpendicular distance of contours near 2 mm and mean myocardium mass overlapping over 90%). This approach provides cardiac radiologists a practical method for an accurate segmentation of the left ventricle.

Myocardial tagging by cardiovascular magnetic resonance: evolution of techniques--pulse sequences, analysis algorithms, and applications

Cardiovascular magnetic resonance (CMR) tagging has been established as an essential technique for measuring regional myocardial function. It allows quantification of local intramyocardial motion measures, e.g. strain and strain rate. The invention of CMR tagging came in the late eighties, where the technique allowed for the first time for visualizing transmural myocardial movement without having to implant physical markers. This new idea opened the door for a series of developments and improvements that continue up to the present time. Different tagging techniques are currently available that are more extensive, improved, and sophisticated than they were twenty years ago. Each of these techniques has different versions for improved resolution, signal-to-noise ratio (SNR), scan time, anatomical coverage, three-dimensional capability, and image quality. The tagging techniques covered in this article can be broadly divided into two main categories: 1) Basic techniques, which include magnetization saturation, spatial modulation of magnetization (SPAMM), delay alternating with nutations for tailored excitation (DANTE), and complementary SPAMM (CSPAMM); and 2) Advanced techniques, which include harmonic phase (HARP), displacement encoding with stimulated echoes (DENSE), and strain encoding (SENC). Although most of these techniques were developed by separate groups and evolved from different backgrounds, they are in fact closely related to each other, and they can be interpreted from more than one perspective. Some of these techniques even followed parallel paths of developments, as illustrated in the article. As each technique has its own advantages, some efforts have been made to combine different techniques together for improved image quality or composite information acquisition. In this review, different developments in pulse sequences and related image processing techniques are described along with the necessities that led to their invention, which makes this article easy to read and the covered techniques easy to follow. Major studies that applied CMR tagging for studying myocardial mechanics are also summarized. Finally, the current article includes a plethora of ideas and techniques with over 300 references that motivate the reader to think about the future of CMR tagging.

Segmentation of the heart and great vessels in CT images using a model-based adaptation framework

Recently, model-based methods for the automatic segmentation of the heart chambers have been proposed. An important application of these methods is the characterization of the heart function. Heart models are, however, increasingly used for interventional guidance making it necessary to also extract the attached great vessels. It is, for instance, important to extract the left atrium and the proximal part of the pulmonary veins to support guidance of ablation procedures for atrial fibrillation treatment. For cardiac resynchronization therapy, a heart model including the coronary sinus is needed. We present a heart model comprising the four heart chambers and the attached great vessels. By assigning individual linear transformations to the heart chambers and to short tubular segments building the great vessels, variable sizes of the heart chambers and bending of the vessels can be described in a consistent way. A configurable algorithmic framework that we call adaptation engine matches the heart model automatically to cardiac CT angiography images in a multi-stage process. First, the heart is detected using a Generalized Hough Transformation. Subsequently, the heart chambers are adapted. This stage uses parametric as well as deformable mesh adaptation techniques. In the final stage, segments of the large vascular structures are successively activated and adapted. To optimize the computational performance, the adaptation engine can vary the mesh resolution and freeze already adapted mesh parts. The data used for validation were independent from the data used for model-building. Ground truth segmentations were generated for 37 CT data sets reconstructed at several cardiac phases from 17 patients. Segmentation errors were assessed for anatomical sub-structures resulting in a mean surface-to-surface error ranging 0.50-0.82mm for the heart chambers and 0.60-1.32mm for the parts of the great vessels visible in the images.

Validation of SPAMM tagged MRI based measurement of 3D soft tissue deformation

PURPOSE

This study presents and validates a novel (non-ECG-triggered) MRI sequence based on spatial modulation of the magnetization (SPAMM) to noninvasively measure 3D (quasistatic) soft tissue deformations using only six acquisitions (three static and three indentations). In the current SPAMM tagged MRI approaches, data are typically constructed from many repeated motion cycles. This has so far restricted its application to the measurement of highly repeatable and periodic movements (e.g., cardiac deformation). In biomechanical applications where soft tissue deformation is artificially induced, often by indentation, significant repeatability constraints exist, and for clinical applications, discomfort and health issues generally preclude a large number of repetitions.

METHODS

A novel (non-ECG-triggered) SPAMM tagged MRI sequence is presented, whereby a single 1-1 (first order) SPAMM set is acquired following a 3D transient field echo acquisition. Full 3D deformation measurement is achieved through the combination of only six acquisitions (three static and three motion cycles). The 3D deformation measurements were validated using quasistatic indentation tests and marker tracking in a silicone gel soft tissue phantom. In addition, the technique's ability to measure 3D soft tissue deformation in vivo was evaluated using indentation of the biceps region of the upper arm in a volunteer.

RESULTS

Following comparison to marker tracking in the silicone gel phantom, the SPAMM tagged MRI based displacement measurement demonstrated subvoxel accuracy with a mean displacement difference of 72 microm and a standard deviation of 289 microm. In addition, precision of displacement magnitude was evaluated for both the phantom and the volunteer data. The standard deviations of the displacement magnitude with respect to the average displacement magnitude were 75 and 169 microm for the phantom and volunteer data, respectively.

CONCLUSIONS

The subvoxel accuracy and precision demonstrated in the phantom in combination with the precision comparison between the phantom and the volunteer data provide confidence in the methods presented for measurement of soft tissue deformation in vivo. To the author's knowledge, since only six acquisitions are required, the presented methodology is the fastest SPAMM tagged MRI method currently available for the noninvasive measurement of quasistatic 3D soft tissue deformation.

Pulmonary kinematics from image data: a review

The effects of certain lung pathologies include alterations in lung physiology negatively affecting pulmonary compliance. Current approaches to diagnosis and treatment assessment of lung disease commonly rely on pulmonary function testing. Such testing is limited to global measures of lung function, neglecting regional measurements, which are critical for early diagnosis and localization of disease. Increased accessibility to medical image acquisition strategies with high spatiotemporal resolution coupled with the development of sophisticated intensity-based and geometric registration techniques has resulted in the recent exploration of modeling pulmonary motion for calculating local measures of deformation. In this review, the authors provide a broad overview of such research efforts for the estimation of pulmonary deformation. This includes discussion of various techniques, current trends in validation approaches, and the public availability of software and data resources.

Physiological fusion of functional and structural images for cardiac deformation recovery

The recent advances in meaningful constraining models have resulted in increasingly useful quantitative information recovered from cardiac images. Nevertheless, as most frameworks utilize either functional or structural images, the analyses cannot benefit from the complementary information provided by the other image sources. To better characterize subject-specific cardiac physiology and pathology, data fusion of multiple image sources is essential. Traditional image fusion strategies are performed by fusing information of commensurate images through various mathematical operators. Nevertheless, when image data are dissimilar in physical nature and spatiotemporal quantity, such approaches may not provide meaningful connections between different data. In fact, as different image sources provide partial measurements of the same cardiac system dynamics, it is more natural and suitable to utilize cardiac physiological models for the fusions. Therefore, we propose to use the cardiac physiome model as the central link to fuse functional and structural images for more subject-specific cardiac deformation recovery through state-space filtering. Experiments were performed on synthetic and real data for the characteristics and potential clinical applicability of our framework, and the results show an increase of the overall subject specificity of the recovered deformations.

Left ventricular modelling: a quantitative functional assessment tool based on cardiac magnetic resonance imaging

We present the development and testing of a semi-automated tool to support the diagnosis of left ventricle (LV) dysfunctions from cardiac magnetic resonance (CMR). CMR short-axis images of the LVs were obtained in 15 patients and processed to detect endocardial and epicardial contours and compute volume, mass and regional wall motion (WM). Results were compared with those obtained from manual tracing by an expert cardiologist. Nearest neighbour tracking and finite-element theory were merged to calculate local myocardial strains and torsion. The method was tested on a virtual phantom, on a healthy LV and on two ischaemic LVs with different severity of the pathology. Automated analysis of CMR data was feasible in 13/15 patients: computed LV volumes and wall mass correlated well with manually extracted data. The detection of regional WM abnormalities showed good sensitivity (77.8%), specificity (85.1%) and accuracy (82%). On the virtual phantom, computed local strains differed by less than 14 per cent from the results of commercial finite-element solver. Strain calculation on the healthy LV showed uniform and synchronized circumferential strains, with peak shortening of about 20 per cent at end systole, progressively higher systolic wall thickening going from base to apex, and a 10° torsion. In the two pathological LVs, synchronicity and homogeneity were partially lost, anomalies being more evident for the more severely injured LV. Moreover, LV torsion was dramatically reduced. Preliminary testing confirmed the validity of our approach, which allowed for the fast analysis of LV function, even though future improvements are possible.

Evaluation of a multi-atlas based method for segmentation of cardiac CTA data: a large-scale, multicenter, and multivendor study

PURPOSE

Computed tomography angiography (CTA) is increasingly used for the diagnosis of coronary artery disease (CAD). However, CTA is not commonly used for the assessment of ventricular and atrial function, although functional information extracted from CTA data is expected to improve the diagnostic value of the examination. In clinical practice, the extraction of ventricular and atrial functional information, such as stroke volume and ejection fraction, requires accurate delineation of cardiac chambers. In this paper, we investigated the accuracy and robustness of cardiac chamber delineation using a multiatlas based segmentation method on multicenter and multivendor CTA data.

METHODS

A fully automatic multiatlas based method for segmenting the whole heart (i.e., the outer surface of the pericardium) and cardiac chambers from CTA data is presented and evaluated. In the segmentation approach, eight atlas images are registered to a new patient's CTA scan. The eight corresponding manually labeled images are then propagated and combined using a per voxel majority voting procedure, to obtain a cardiac segmentation.

RESULTS

The method was evaluated on a multicenter/multivendor database, consisting of (1) a set of 1380 Siemens scans from 795 patients and (2) a set of 60 multivendor scans (Siemens, Philips, and GE) from different patients, acquired in six different institutions worldwide. A leave-one-out 3D quantitative validation was carried out on the eight atlas images; we obtained a mean surface-to-surface error of 0.94 +/- 1.12 mm and an average Dice coefficient of 0.93 was achieved. A 2D quantitative evaluation was performed on the 60 multivendor data sets. Here, we observed a mean surface-to-surface error of 1.26 +/- 1.25 mm and an average Dice coefficient of 0.91 was achieved. In addition to this quantitative evaluation, a large-scale 2D and 3D qualitative evaluation was performed on 1380 and 140 images, respectively. Experts evaluated that 49% of the 1380 images were very accurately segmented (below 1 mm error) and that 29% were accurately segmented (error between 1 and 3 mm), which demonstrates the robustness of the presented method.

CONCLUSIONS

A fully automatic method for whole heart and cardiac chamber segmentation was presented and evaluated using multicenter/multivendor CTA data. The accuracy and robustness of the method were demonstrated by successfully applying the method to 1420 multicenter/ multivendor data sets.

A novel model-based 3D +time left ventricular segmentation technique

A common approach to model-based segmentation is to assume a top-down modelling strategy. However, this is not feasible for complex 3D +time structures, such as the cardiac left ventricle, due to increased training requirements, aligning difficulties and local minima in resulting models. As our main contribution, we present an alternate bottom-up modelling approach. By combining the variation captured in multiple dimensionally-targeted models at segmentation-time we create a scalable segmentation framework that does not suffer from the "curse of dimensionality." Our second contribution involves a flexible contour coupling technique that allows our segmentation method to adapt to unseen contour configurations outside the training set. This is used to identify the endo- and epicardium contours of the left ventricle by coupling them at segmentation-time, instead of at model-time. We apply our approach to 33 3D +time cardiac MRI datasets and perform comprehensive evaluation against several state-of-the-art works. Quantitative evaluation illustrates that our method requires significantly less training than state-of-the-art model-based methods, while maintaining or improving segmentation accuracy.

An inter-landmark approach to 4-D shape extraction and interpretation: application to myocardial motion assessment in MRI

This paper presents a novel approach to shape extraction and interpretation in 4-D cardiac magnetic resonance imaging data. Statistical modeling of spatiotemporal interlandmark relationships is performed to enable the decomposition of global shape constraints and subsequently of the image analysis tasks. The introduced descriptors furthermore provide invariance to similarity transformations and thus eliminate pose estimation errors in the presence of image artifacts or geometrical inconsistencies. A set of algorithms are derived to address key technical issues related to constrained boundary tracking, dynamic model relaxation, automatic initialization, and dysfunction localization. The proposed framework is validated with a relatively large dataset of 50 subjects and compared to existing statistical shape modeling methods. The results indicate increased adaptation to spatiotemporal variations and imaging conditions.

Automatic view planning for cardiac MRI acquisition

Conventional cardiac MRI acquisition involves a multi-step approach, requiring a few double-oblique localizers in order to locate the heart and prescribe long- and short-axis views of the heart. This approach is operator-dependent and time-consuming. We propose a new approach to automating and accelerating the acquisition process to improve the clinical workflow. We capture a highly accelerated static 3D full-chest volume through parallel imaging within one breath-hold. The left ventricle is localized and segmented, including left ventricle outflow tract. A number of cardiac landmarks are then detected to anchor the cardiac chambers and calculate standard 2-, 3-, and 4-chamber long-axis views along with a short-axis stack. Learning-based algorithms are applied to anatomy segmentation and anchor detection. The proposed algorithm is evaluated on 173 localizer acquisitions. The entire view planning is fully automatic and takes less than 10 seconds in our experiments.

Cardiac anchoring in MRI through context modeling

Cardiac magnetic resonance imaging (MRI) has advanced to become a powerful diagnostic tool in clinical practice. Robust and fast cardiac modeling is important for structural and functional analysis of the heart. Cardiac anchors provide strong cues to extract morphological and functional features for diagnosis and disease monitoring. We present a fully automatic method and system that is able to detect these cues. The proposed approach explores expert knowledge embedded in a large annotated database. Exemplar cues in our experiments include left ventricle (LV) base plane and LV apex from long-axis images, and right ventricle (RV) insertion points from short-axis images. We evaluate the proposed approach on 8304 long-axis images from 188 patients and 891 short-axis images from 338 patients that are acquired from different vendors. In addition, another evaluation is conducted on an independent 7140 images from 87 patient studies. Experimental results show promise of the proposed approach.

Automatic cardiac ventricle segmentation in MR images: a validation study

PURPOSE

Segmenting the cardiac ventricles in magnetic resonance (MR) images is required for cardiac function assessment. Numerous segmentation methods have been developed and applied to MR ventriculography. Quantitative validation of these segmentation methods with ground truth is needed prior to clinical use, but requires manual delineation of hundreds of images. We applied a well-established method to this problem and rigorously validated the results.

METHODS

An automatic method based on active contours without edges was used for left and the right ventricle cavity segmentation. A large database of 1,920 MR images obtained from 59 patients who gave informed consent was evaluated. Two standard metrics were used for quantitative error measurement.

RESULTS

Segmentation results are comparable to previously reported values in the literature. Since different points in the cardiac cycle and different slice levels were used in this study, a detailed error analysis is possible. Better performance was obtained at end diastole than at end systole, and on mid-ventricular slices than apical slices. Localization of segmentation errors were highlighted through a study of their spatial distribution.

CONCLUSIONS

Ventricular segmentation based on region-driven active contours provided satisfactory results in MRI, without the use of a priori knowledge. The study of error distribution allows identification of potential improvements in algorithm performance.

A strategic approach for cardiac MR left ventricle segmentation

Quantitative evaluation of cardiac function from cardiac magnetic resonance (CMR) images requires the identification of the myocardial walls. This generally requires the clinician to view the image and interactively trace the contours. Especially, detection of myocardial walls of left ventricle is a difficult task in CMR images that are obtained from subjects having serious diseases. An approach to automated outlining the left ventricular contour is proposed. In order to segment the left ventricle, in this paper, a combination of two approaches is suggested. Difference of Gaussian weighting function (DoG) is newly introduced in random walk approach for blood pool (inner contour) extraction. The myocardial wall (outer contour) is segmented out by a modified active contour method that takes blood pool boundary as the initial contour. Promising experimental results in CMR images demonstrate the potentials of our approach.

Segmentation of the left ventricle from cardiac MR images using a subject-specific dynamical model

Statistical models have shown considerable promise as a basis for segmenting and interpreting cardiac images. While a variety of statistical models have been proposed to improve the segmentation results, most of them are either static models (SMs), which neglect the temporal dynamics of a cardiac sequence, or generic dynamical models (GDMs), which are homogeneous in time and neglect the intersubject variability in cardiac shape and deformation. In this paper, we develop a subject-specific dynamical model (SSDM) that simultaneously handles temporal dynamics (intrasubject variability) and intersubject variability. We also propose a dynamic prediction algorithm that can progressively identify the specific motion patterns of a new cardiac sequence based on the shapes observed in past frames. The incorporation of this SSDM into the segmentation framework is formulated in a recursive Bayesian framework. It starts with a manual segmentation of the first frame, and then segments each frame according to intensity information from the current frame as well as the prediction from past frames. In addition, to reduce error propagation in sequential segmentation, we take into account the periodic nature of cardiac motion and perform segmentation in both forward and backward directions. We perform "leave-one-out" test on 32 canine sequences and 22 human sequences, and compare the experimental results with those from SM, GDM, and active appearance motion model (AAMM). Quantitative analysis of the experimental results shows that SSDM outperforms SM, GDM, and AAMM by having better global and local consistencies with manual segmentation. Moreover, we compare the segmentation results from forward and forward-backward segmentation. Quantitative evaluation shows that forward-backward segmentation suppresses the propagation of segmentation errors.

Automatic left ventricular contour extraction from cardiac magnetic resonance images using cantilever beam and random walk approach

Heart failure is a well-known debilitating disease. From clinical point of view, segmentation of left ventricle (LV) is important in a cardiac magnetic resonance (CMR) image. Accurate parameters are desired for better diagnosis. Proper and fast image segmentation of LV is of paramount importance prior to estimation of these parameters. We prefer random walk approach over other existing techniques due to two of its advantages: (1) robustness to noise and, (2) it does not require any special condition to work. Performance of the method solely depends on the selection of initial seed and parameter β. Problems arise while applying this method to different kind of CMR images bearing different ischemia. It is due due to their implicit geometry definitions unlike general images, where the boundary of LV in the image is not available in an explicit form. This type of images bear multi-labeled LV and the manual seed selection in these images introduces variability in the results. In view of this, the paper presents two modifications in the algorithm: (1) automatic seed selection and, (2) automatic estimation of β from the image. The highlight of our method is its ability to succeed with minimum number of initial seeds.

3D MRI heart segmentation of mouse embryos

MRI has become an effective tool for anatomical mice studies. Currently, embryologists study the development of mouse embryos in order to understand the mechanisms of human development. The aim of the research presented in this paper, is to develop a semi-automatic image segmentation framework based 3D deformable models to identify cardiac malformations which are a major cause of death in children. The segmentation systems have been used to segment 3D mouse embryos heart structures. Results on the ventricles and on the heart muscle are presented and compared with manually segmented models.

A multidimensional segmentation evaluation for medical image data

Evaluation of segmentation methods is a crucial aspect in image processing, especially in the medical imaging field, where small differences between segmented regions in the anatomy can be of paramount importance. Usually, segmentation evaluation is based on a measure that depends on the number of segmented voxels inside and outside of some reference regions that are called gold standards. Although some other measures have been also used, in this work we propose a set of new similarity measures, based on different features, such as the location and intensity values of the misclassified voxels, and the connectivity and the boundaries of the segmented data. Using the multidimensional information provided by these measures, we propose a new evaluation method whose results are visualized applying a Principal Component Analysis of the data, obtaining a simplified graphical method to compare different segmentation results. We have carried out an intensive study using several classic segmentation methods applied to a set of MRI simulated data of the brain with several noise and RF inhomogeneity levels, and also to real data, showing that the new measures proposed here and the results that we have obtained from the multidimensional evaluation, improve the robustness of the evaluation and provides better understanding about the difference between segmentation methods.

Cardiac C-arm CT: a unified framework for motion estimation and dynamic CT

Generating 3-D images of the heart during interventional procedures is a significant challenge. In addition to real time fluoroscopy, angiographic C-arm systems can also now be used to generate 3-D/4-D CT images on the same system. One protocol for cardiac CT uses ECG triggered multisweep scans. A 3-D volume of the heart at a particular cardiac phase is then reconstructed by applying Feldkamp (FDK) reconstruction to the projection images with retrospective ECG gating. In this work we introduce a unified framework for heart motion estimation and dynamic cone-beam reconstruction using motion corrections. The benefits of motion correction are 1) increased temporal and spatial resolution by removing cardiac motion which may still exist in the ECG gated data sets and 2) increased signal-to-noise ratio (SNR) by using more projection data than is used in standard ECG gated methods. Three signal-enhanced reconstruction methods are introduced that make use of all of the acquired projection data to generate a 3-D reconstruction of the desired cardiac phase. The first averages all motion corrected back-projections; the second and third perform a weighted averaging according to 1) intensity variations and 2) temporal distance relative to a time resolved and motion corrected reference FDK reconstruction. In a comparison study seven methods are compared: nongated FDK, ECG-gated FDK, ECG-gated, and motion corrected FDK, the three signal-enhanced approaches, and temporally aligned and averaged ECG-gated FDK reconstructions. The quality measures used for comparison are spatial resolution and SNR. Evaluation is performed using phantom data and animal models. We show that data driven and subject-specific motion estimation combined with motion correction can decrease motion-related blurring substantially. Furthermore, SNR can be increased by up to 70% while maintaining spatial resolution at the same level as is provided by the ECG-gated FDK. The presented framework provides excellent image quality for cardiac C-arm CT.

Characterization of 3-D coronary tree motion from MSCT angiography

This paper describes a method for the characterization of coronary artery motion using multislice computed tomography (MSCT) volume sequences. Coronary trees are first extracted by a spatial vessel tracking method in each volume of MSCT sequence. A point-based matching algorithm, with feature landmarks constraint, is then applied to match the 3-D extracted centerlines between two consecutive instants over a complete cardiac cycle. The transformation functions and correspondence matrices are estimated simultaneously, and allow deformable fitting of the vessels over the volume series. Either point-based or branch-based motion features can be derived. Experiments have been conducted in order to evaluate the performance of the method with a matching error analysis.

Meshfree implementation of individualized active cardiac dynamics

The cardiac physiome model has been proven to be useful for cardiac simulation, and has been more recently utilized to medical image analysis. To perform individualized analysis, structural images are necessary to provide subject-specific cardiac geometries. Although finite element methods have been extensively used for the spatial discretization of the myocardium, their complicated meshing procedures and element-based interpolation functions often result in algorithms which are either easy to implement but numerically inaccurate, or accurate but labor-intensive. In consequence, we have adopted the meshfree platform which provides element-free approximations for computational cardiology. Complicated volume meshing procedures are excluded, and no re-meshing is needed for improving spatial accuracy when deformation occurs. Furthermore, the polynomial bases for spatial approximation are not limited by the element structure. As a result, the meshfree platform is more adaptive to different cardiac geometries and thus beneficial to individualized analysis. In this paper, the cardiac physiome model tailored for medical image analysis is presented with its detailed 3D implementation using the meshfree methods. Experiments were performed to compare the meshfree methods with the finite element methods, and simulations were done on a cubical object to investigate the local behaviors of the cardiac physiome model, and on a human heart geometry extracted from a magnetic resonance image to verify its physiological plausibility.

Automated frame-by-frame endocardial border detection from cardiac magnetic resonance images for quantitative assessment of left ventricular function: validation and clinical feasibility

PURPOSE

To develop a technique based on image noise distribution for automated endocardial border detection from cardiac magnetic resonance (CMR) images throughout the cardiac cycle, validate it, and test its clinical utility.

MATERIALS AND METHODS

Images obtained in 36 patients were analyzed using custom software to obtain left ventricular (LV) volume throughout the cardiac cycle, end-systolic and end-diastolic LV volumes, and ejection fraction (EF). Validation against manually-traced endocardial boundaries included intertechnique comparisons of LV volumes, slice areas, and border positions. Then, the clinical feasibility of the dynamic automated analysis of LV function was tested in 14 patients with normal LV function, 12 patients with systolic dysfunction, and 10 patients with diastolic dysfunction.

RESULTS

Analysis time for one cardiac cycle was <15 minutes. Intertechnique comparisons resulted in high correlation (r>0.96), small biases (volumes: -6 mL; EF: 4.6%) and narrow limits of agreement (volumes: 17.6 mL; EF: 9.2%). We found significant intergroup differences in multiple quantitative indices of systolic and diastolic function.

CONCLUSION

Fast, automated, dynamic detection of LV endocardial boundaries is feasible and allows accurate quantification of LV size and function, which is potentially clinically useful for objective assessment of systolic and diastolic dysfunction.

Left Ventricle Segmentation Using Model Fitting and Active Surfaces

A method to perform 4D (3D over time) segmentation of the left ventricle of a mouse heart using a set of B mode cine slices acquired in vivo from a series of short axis scans is described. We incorporate previously suggested methods such as temporal propagation, the gradient vector flow active surface, superquadric models, etc. into our proposed 4D segmentation of the left ventricle. The contributions of this paper are incorporation of a novel despeckling method and the use of locally fitted superellipsoid models to provide a better initialization for the active surface segmentation algorithm. Average distances of the improved surface segmentation to a manually segmented surface throughout the entire cardiac cycle and cross-sectional contours are provided to demonstrate the improvements produced by the proposed 4D segmentation.

Quantitative analysis of left ventricular performance from sequences of cardiac magnetic resonance imaging using active mesh model

In this study, the local and global left ventricular function are estimated by fitting three-dimensional active mesh model (3D-AMM) to the initial sparse displacement which is measured from an establishing point correspondence procedure. To evaluate the performance of the algorithm, eight image sequences were used and the results were compared with those reported by other researchers. The findings were consistent with previously published values and the clinical evidence as well. The results demonstrated the superiority of the novel strategy with respect to formerly presented algorithm reported by author et al. Furthermore, the results are comparable to the current state-of-the-art methods.

Region-based endocardium tracking on real-time three-dimensional ultrasound

Matrix-phased array transducers for real-time 3-D ultrasound enable fast, noninvasive visualization of cardiac ventricles. Typically, 3-D ultrasound images are semiautomatically segmented to extract the left ventricular endocardial surface at end-diastole and end-systole. Automatic segmentation and propagation of this surface throughout the entire cardiac cycle is a challenging and cumbersome task. If the position of the endocardial surface is provided at one or two time frames during the cardiac cycle, automated tracking of the surface over the remaining time frames could reduce the workload of cardiologists and optimize analysis of 3-D ultrasound data. In this paper, we applied a region-based tracking algorithm to track the endocardial surface between two reference frames that were manually segmented. To evaluate the tracking of the endocardium, the method was applied to 40 open-chest dog datasets with 484 frames in total. Ventricular geometry and volumes derived from region-based endocardial surfaces and manual tracing were quantitatively compared, showing strong correlation between the two approaches. Statistical analysis showed that the errors from tracking were within the range of interobserver variability of manual tracing. Moreover, our algorithm performed well on ischemia datasets, suggesting that the method is robust-to-abnormal wall motion. In conclusion, the proposed optical flow-based surface tracking method is very efficient and accurate, providing dynamic "interpolation" of segmented endocardial surfaces.

Motion-guided segmentation for cine DENSE MRI

Defining myocardial contours is often the most time-consuming portion of dynamic cardiac MRI image analysis. Displacement encoding with stimulated echoes (DENSE) is a quantitative MRI technique that encodes tissue displacement into the phase of the complex MRI images. Cine DENSE provides a time series of these images, thus facilitating the non-invasive study of myocardial kinematics. Epicardial and endocardial contours need to be defined at each frame on cine DENSE images for the quantification of regional displacement and strain as a function of time. This work presents a reliable and effective two-dimensional semi-automated segmentation technique that uses the encoded motion to project a manually-defined region of interest through time. Contours can then easily be extracted for each cardiac phase. This method boasts several advantages, including, (1) parameters are based on practical physiological limits, (2) contours are calculated for the first few cardiac phases, where it is difficult to visually distinguish blood from myocardium, and (3) the method is independent of the shape of the tissue delineated and can be applied to short- or long-axis views, and on arbitrary regions of interest. Motion-guided contours were compared to manual contours for six conventional and six slice-followed mid-ventricular short-axis cine DENSE datasets. Using an area measure of segmentation error, the accuracy of the segmentation algorithm was shown to be similar to inter-observer variability. In addition, a radial segmentation error metric was introduced for short-axis data. The average radial epicardial segmentation error was 0.36+/-0.08 and 0.40+/-0.10 pixels for slice-followed and conventional cine DENSE, respectively, and the average radial endocardial segmentation error was 0.46+/-0.12 and 0.46+/-0.16 pixels for slice following and conventional cine DENSE, respectively. Motion-guided segmentation employs the displacement-encoded phase shifts intrinsic to DENSE MRI to accurately propagate a single set of pre-defined contours throughout the remaining cardiac phases.

Computational modeling of cardiac disease: potential for personalized medicine

Cardiovascular diseases are leading causes of death, reduce life quality and consume almost half a trillion dollars in healthcare expenses in the USA alone. Cardiac modeling and simulation technologies hold promise as important tools to improve cardiac care and are already in use to elucidate the fundamental mechanisms of cardiac physiology and pathophysiology. However, the emphasis has been on simulating average or exemplar cases. This report describes two classes of cardiac modeling efforts. First, electrophysiological models of channelopathies simulate the altered electrical activity that is thought to promote arrhythmias. Second, electromechanical models attempt to capture both the electrophysiological and mechanical aspects of heart function. One goal of the community is to develop models with sufficient patient customization to assist in personalized treatment planning. Some model aspects can be customized with existing data collection techniques to more closely represent individual patients while other model aspects will likely remain based on generic data. Despite important challenges, cardiac models hold promise to be important enablers of personalized medicine.

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

We propose an automatic four-chamber heart segmentation system for the quantitative functional analysis of the heart from cardiac computed tomography (CT) volumes. Two topics are discussed: heart modeling and automatic model fitting to an unseen volume. Heart modeling is a nontrivial task since the heart is a complex nonrigid organ. The model must be anatomically accurate, allow manual editing, and provide sufficient information to guide automatic detection and segmentation. Unlike previous work, we explicitly represent important landmarks (such as the valves and the ventricular septum cusps) among the control points of the model. The control points can be detected reliably to guide the automatic model fitting process. Using this model, we develop an efficient and robust approach for automatic heart chamber segmentation in 3-D CT volumes. We formulate the segmentation as a two-step learning problem: anatomical structure localization and boundary delineation. In both steps, we exploit the recent advances in learning discriminative models. A novel algorithm, marginal space learning (MSL), is introduced to solve the 9-D similarity transformation search problem for localizing the heart chambers. After determining the pose of the heart chambers, we estimate the 3-D shape through learning-based boundary delineation. The proposed method has been extensively tested on the largest dataset (with 323 volumes from 137 patients) ever reported in the literature. To the best of our knowledge, our system is the fastest with a speed of 4.0 s per volume (on a dual-core 3.2-GHz processor) for the automatic segmentation of all four chambers.

Automatic construction of 3D-ASM intensity models by simulating image acquisition: application to myocardial gated SPECT studies

Active shape models bear a great promise for model-based medical image analysis. Their practical use, though, is undermined due to the need to train such models on large image databases. Automatic building of point distribution models (PDMs) has been successfully addressed and a number of autolandmarking techniques are currently available. However, the need for strategies to automatically build intensity models around each landmark has been largely overlooked in the literature. This work demonstrates the potential of creating intensity models automatically by simulating image generation. We show that it is possible to reuse a 3D PDM built from computed tomography (CT) to segment gated single photon emission computed tomography (gSPECT) studies. Training is performed on a realistic virtual population where image acquisition and formation have been modeled using the SIMIND Monte Carlo simulator and ASPIRE image reconstruction software, respectively. The dataset comprised 208 digital phantoms (4D-NCAT) and 20 clinical studies. The evaluation is accomplished by comparing point-to-surface and volume errors against a proper gold standard. Results show that gSPECT studies can be successfully segmented by models trained under this scheme with subvoxel accuracy. The accuracy in estimated LV function parameters, such as end diastolic volume, end systolic volume, and ejection fraction, ranged from 90.0% to 94.5% for the virtual population and from 87.0% to 89.5% for the clinical population.

Toward patient-specific myocardial models of the heart

This article presents a framework for building patient-specific models of the myocardium, to help diagnosis, therapy planning, and procedure guidance. The aim is to be able to introduce such models in clinical applications. Thus, there is a need to design models that can be adjusted from clinical data, images, or signals, which are sparse and noisy. The authors describe the three main components of a myocardial model: the anatomy, the electrophysiology, and the biomechanics. For each of these components, the authors try to obtain the best balance between prior knowledge and observable parameters to be able to adjust these models to patient data. To achieve this, there is a need to design models with the right level of complexity and a computational cost compatible with clinical constraints.

Maximum a posteriori strategy for the simultaneous motion and material property estimation of the heart

In addition to its technical merits as a challenging nonrigid motion and structural integrity analysis problem, quantitative estimation of cardiac regional functions and material characteristics has significant physiological and clinical value. We developed a stochastic finite-element framework for the simultaneous recovery of myocardial motion and material parameters from medical image sequences with an extended Kalman filter approach, and we have shown that this simultaneous estimation strategy achieves more accurate and robust results than separated motion and material estimation efforts. In this paper, we present a new computational strategy for the framework based upon the maximum a posteriori estimation principles, realized through the extended Kalman smoother, that produces a sequence of kinematics state and material parameter estimation of the entire myocardium, including the endocardial, epicardial, and midwall tissues. The system dynamics equations of the heart are constructed using a biomechanical model with stochastic parameters, and the tissue material and deformation parameters are jointly estimated from the periodic imaging data. Noise-corrupted synthetic image sequences with known kinematics and material parameters are used to assess the accuracy and robustness of the framework. Experiments with canine magnetic resonance tagging and phase-contrast image sequences have been conducted with very promising results, as validated through comparison to the histological staining of postmortem myocardium.

Automatic model-based segmentation of the heart in CT images

Automatic image processing methods are a prerequisite to efficiently analyze the large amount of image data produced by computed tomography (CT) scanners during cardiac exams. This paper introduces a model-based approach for the fully automatic segmentation of the whole heart (four chambers, myocardium, and great vessels) from 3-D CT images. Model adaptation is done by progressively increasing the degrees-of-freedom of the allowed deformations. This improves convergence as well as segmentation accuracy. The heart is first localized in the image using a 3-D implementation of the generalized Hough transform. Pose misalignment is corrected by matching the model to the image making use of a global similarity transformation. The complex initialization of the multicompartment mesh is then addressed by assigning an affine transformation to each anatomical region of the model. Finally, a deformable adaptation is performed to accurately match the boundaries of the patient's anatomy. A mean surface-to-surface error of 0.82 mm was measured in a leave-one-out quantitative validation carried out on 28 images. Moreover, the piecewise affine transformation introduced for mesh initialization and adaptation shows better interphase and interpatient shape variability characterization than commonly used principal component analysis.