Search

Purpose: Functional strain is one of the important clinical indicators for the quantification of heart performance and the early detection of cardiovascular diseases, and functional strain parameters are used to aid therapeutic decisions and follow-up evaluations after cardiac surgery. A comprehensive framework for deriving functional strain parameters at the endocardium, epicardium, and mid-wall of the left ventricle (LV) from conventional cine MRI data was developed and tested., Methods: Cine data were collected using short TR-/TE-balanced steady-state free precession acquisitions on a 1.5T Siemens Espree scanner. The LV wall borders are segmented using a level set-based deformable model guided by a stochastic force derived from a second-order Markov-Gibbs random field model that accounts for the object shape and appearance features. Then, the mid-wall of the segmented LV is determined based on estimating the centerline between the endocardium and epicardium of the LV. Finally, a geometrical Laplace-based method is proposed to track corresponding points on successive myocardial contours throughout the cardiac cycle in order to characterize the strain evolutions. The method was tested using simulated phantom images with predefined point locations of the LV wall throughout the cardiac cycle. The method was tested on 30 in vivo datasets to evaluate the feasibility of the proposed framework to index functional strain parameters., Results: The cine MRI-based model agreed with the ground truth for functional metrics to within 0.30 % for indexing the peak systolic strain change and 0.29 % (per unit time) for indexing systolic and diastolic strain rates. The method was feasible for in vivo extraction of functional strain parameters., Conclusion: Strain indexes of the endocardium, mid-wall, and epicardium can be derived from routine cine images using automated techniques, thereby improving the utility of cine MRI data for characterization of myocardial function. Unlike traditional texture-based tracking, the proposed geometrical method showed the ability to track the LV wall points throughout the cardiac cycle, thus permitting more accurate strain estimation.

A novel automated framework for detecting and quantifying viability from agent enhanced cardiac magnetic resonance images is proposed. The framework identifies the pathological tissues based on a joint Markov-Gibbs random field (MGRF) model that accounts for the 1st-order visual appearance of the myocardial wall (in terms of the pixel-wise intensities) and the 2nd-order spatial interactions between pixels. The pathological tissue is quantified based on two metrics: the percentage area in each segment with respect to the total area of the segment, and the trans-wall extent of the pathological tissue. This transmural extent is estimated using point-to-point correspondences based on a Laplace partial differential equation. Transmural extent was validated using a simulated phantom. We tested the proposed framework on 14 datasets (168 images) and validated against manual expert delineation of the pathological tissue by two observers. Mean Dice similarity coefficients (DSC) of 0.90 and 0.88 were obtained for the observers, approaching the ideal value, 1. The Bland-Altman statistic of infarct volumes estimated by manual versus the MGRF estimation revealed little bias difference, and most values fell within the 95% confidence interval, suggesting very good agreement. Using the DSC measure we documented statistically significant superior segmentation performance for our MGRF method versus established intensity-based methods (greater DSC, and smaller standard deviation). Our Laplace method showed good operating characteristics across the full range of extent of transmural infarct, outperforming conventional methods. Phantom validation and experiments on patient data confirmed the robustness and accuracy of the proposed framework.

A new approach to align 3D CT data of a segmented lung object with a given prototype (reference lung object) using an affine transformation is proposed. Visual appearance of the lung from CT images, after equalizing their signals, is modeled with a new 3D Markov-Gibbs random field (MGRF) with pairwise interaction model. Similarity to the prototype is measured by a Gibbs energy of signal co-occurrences in a characteristic subset of voxel pairs derived automatically from the prototype. An object is aligned by an affine transformation maximizing the similarity by using an automatic initialization followed by a gradient search. Experiments confirm that our approach aligns complex objects better than popular conventional algorithms.

Kidney segmentation is a key step in developing any noninvasive computer-aided diagnosis (CAD) system for early detection of acute renal rejection. This paper describes a new 3-D segmentation approach for the kidney from computed tomography (CT) images. The kidney borders are segmented from the surrounding abdominal tissues with a geometric deformable model guided by a special stochastic speed relationship. The latter accounts for a shape prior and appearance features in terms of voxel-wise image intensities and their pair-wise spatial interactions integrated into a two-level joint Markov-Gibbs random field (MGRF) model of the kidney and its background. The segmentation approach was evaluated on 21 CT data sets with available manual expert segmentation. The performance evaluation based on the receiver operating characteristic (ROC) and Dice similarity coefficient (DSC) between manually drawn and automatically segmented contours confirm the robustness and accuracy of the proposed segmentation approach.

An alternative method of diagnosing malignant lung nodules by their shape, rather than conventional growth rate, is proposed. The 3D surfaces of the detected lung nodules are delineated by spherical harmonic analysis that represents a 3D surface of the lung nodule supported by the unit sphere with a linear combination of special basis functions, called Spherical Harmonics (SHs). The proposed 3D shape analysis is carried out in five steps: (i) 3D lung nodule segmentation with a deformable 3D boundary controlled by a new prior visual appearance model; (ii) 3D Delaunay triangulation to construct a 3D mesh model of the segmented lung nodule surface; (iii) mapping this model to the unit sphere; (iv) computing the SHs for the surface; and (v) determining the number of the SHs to delineate the lung nodule. We describe the lung nodule shape complexity with a new shape index, the estimated number of the SHs, and use it for the K-nearest classification into malignant and benign lung nodules. Preliminary experiments on 327 lung nodules (153 malignant and 174 benign) resulted in a classification accuracy of 93.6%, showing that the proposed method is a promising supplement to current technologies for the early diagnosis of lung cancer.

Abstract. A promising approach for the automatic classification of normal and acute rejection transplants from Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) is proposed. The proposed approach consists of three main steps. The first step segments the kidney from the surrounding abdominal tissues by a level-set based deformable model with a speed function that accounts for a learned spatially variant statistical shape prior, 1st-order visual appearance descriptors of the contour interior and exterior (associated with the object and background, respectively), and a spatially invariant 2nd-order homogeneity descriptor. In the second step, to handle local object deformations due to kidney motion caused by patient breathing, we proposed a new nonrigid approach to align the object by solving Laplace's equation between closed equis-paced contours (iso-contours) of the reference and target objects. Finally, the perfusion curves that show the transportation of the contrast agent into the tissue are obtained from the segmented kidneys and used in the classification of normal and acute rejection transplants. Applications of the proposed approach yield promising results that would, in the near future, replace the use of current technologies such as nuclear imaging and ultrasonography, which are not specific enough to determine the type of kidney dysfunction.

We propose a novel parametric deformable model controlled by shape and visual appearance priors learned from a training subset of co-aligned medical images of goal objects. The shape prior is derived from a linear combination of vectors of distances between the training boundaries and their common centroid. The appearance prior considers gray levels within each training boundary as a sample of a Markov-Gibbs random field with pairwise interaction. Spatially homogeneous interaction geometry and Gibbs potentials are analytically estimated from the training data. To accurately separate a goal object from an arbitrary background, empirical marginal gray level distributions inside and outside of the boundary are modeled with adaptive linear combinations of discrete Gaussians (LCDG). Due to the analytical shape and appearance priors and a simple Expectation-Maximization procedure for getting the object and background LCDG, our segmentation is considerably faster than with most of the known geometric and parametric models. Experiments with various goal images confirm the robustness, accuracy, and speed of our approach.

New techniques for more accurate segmentation of a 3D cerebrovascular system from phase contrast (PC) magnetic resonance angiography (MRA) data are proposed. In this paper, we describe PC-MRA images and desired maps of regions by a joint Markov-Gibbs random field model (MGRF) of independent image signals and interdependent region labels but focus on most accurate model identification. To better specify region borders, each empirical distribution of signals is precisely approximated by a Linear Combination of Discrete Gaussians (LCDG) with positive and negative components. We modified the conventional Expectation-Maximization (EM) algorithm to deal with the LCDG. The initial segmentation based on the LCDG-models is then iteratively refined using a MGRF model with analytically estimated potentials. Experiments with both the phantoms and real data sets confirm high accuracy of the proposed approach.

New techniques for more accurate unsupervised segmentation of lung tissues from Low Dose Computed Tomography (LDCT) are proposed. In this paper we describe LDCT images and desired maps of regions (lung and the other chest tissues) by a joint Markov-Gibbs random field model (MGRF) of independent image signals and interdependent region labels but focus on most accurate model identification. To better specify region borders, each empirical distribution of signals is precisely approximated by a Linear Combination of Discrete Gaussians (LCDG) with positive and negative components. We modify a conventional Expectation-Maximization (EM) algorithm to deal with the LCDG and develop a sequential EM-based technique to get an initial LCDG-approximation for the modified EM algorithm. The initial segmentation based on the LCDG-models is then iteratively refined using a MGRF model with analytically estimated potentials. Experiments on real data sets confirm high accuracy of the proposed approach.

Acute rejection is the most common reason of graft failure after kidney transplantation and early detection is crucial to survive the transplanted kidney function. In this paper, we introduce a new approach for the automatic classification of normal and acute rejection transplants from Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI). The proposed algorithm consists of three main steps; the first step isolates the kidney from the surrounding anatomical structures. In the second step, new motion correction models are employed to account for both the global and local motion of the kidney due to patient moving and breathing. Finally, the perfusion curves that show the transportation of the contrast agent into the tissue are obtained from the kidney and used in the classification of normal and acute rejection transplants.

The importance of accurate early diagnostics of autism that severely affects personal behavior and communication skills cannot be overstated. Neuropathological studies have revealed an abnormal anatomy of the cerebral white matter (CWM) in autistic brains. We explore a possibility of distinguishing between autistic and normal brains by a quantitative shape analysis of CWM gyrifications on 3D proton density MRI (PD-MRI) images. Our approach consists of (i) segmentation of the CWM on a 3D brain image using a deformable 3D boundary; (ii) extraction of gyrifications from the segmented CWM, and (iii) shape analysis to quantify thickness of the extracted gyrifications and classify autistic and normal subjects. The boundary evolution is controlled by two probabilistic models of visual appearance of 3D CWM: the learned prior and the current appearance model. Initial experimental results suggest that the proposed 3D texture analysis is a promising supplement to the current techniques for diagnosing autism.

A new approach to align an image of a medical object with a given prototype is proposed. Visual appearance of the images, after equalizing their signals, is modelled with a new Markov-Gibbs random field with pairwise interaction model. Similarity to the prototype is measured by a Gibbs energy of signal co-occurrences in a characteristic subset of pixel pairs derived automatically from the prototype. An object is aligned by an affine transformation maximizing the similarity by using an automatic initialization followed by gradient search. Experiments confirm that our approach aligns complex objects better than popular conventional algorithms.

To more accurately separate each pulmonary nodule from its background in a low dose computer tomography (LDCT) chest image, two new adaptive probability models of visual appearance of small 2D and large 3D pulmonary nodules are used to control evolution of deformable boundaries. The appearance prior is modeled with a translation and rotation invariant Markov-Gibbs random field of voxel intensities with pairwise interaction analytically identified from a set of training nodules. Appearance of the nodules and their background in a current multi-modal chest image is also represented with a marginal probability distribution of voxel intensities. The nodule appearance model is isolated from the mixed distribution using its close approximation with a linear combination of discrete Gaussians. Experiments with real LDCT chest images confirm high accuracy of the proposed approach.

A new physically justified adaptive probabilistic model of blood vessels on magnetic resonance angiography (MRA) images is proposed. The model accounts for both laminar (for normal subjects) and turbulent blood flow (in abnormal cases like anemia or stenosis) and results in a fast algorithm for extracting a 3D cerebrovascular system from the MRA data. Experiments with synthetic and 50 real data sets confirm the high accuracy of the proposed approach.

Accurate automatic extraction of a 3D cerebrovascular system from images obtained by time-of-flight (TOF) or phase contrast (PC) magnetic resonance angiography (MRA) is a challenging segmentation problem due to small size objects of interest (blood vessels) in each 2D MRA slice and complex surrounding anatomical structures, e.g. fat, bones, or grey and white brain matter. We show that due to a multi-modal nature of MRA data blood vessels can be accurately separated from background in each slice by a voxel-wise classification based on precisely identified probability models of voxel intensities. To identify the models, an empirical marginal probability distribution of intensities is closely approximated with a linear combination of discrete Gaussians (LCDG) with alternate signs, and we modify the conventional Expectation-Maximization (EM) algorithm to deal with the LCDG. To validate the accuracy of our algorithm, a special 3D geometrical phantom motivated by statistical analysis of the MRA-TOF data is designed. Experiments with both the phantom and 50 real data sets confirm high accuracy of the proposed approach.