Colin B. Compas

Contour tracking in echocardiographic sequences via sparse representation and dictionary learning.

This paper presents a dynamical appearance model based on sparse representation and dictionary learning for tracking both endocardial and epicardial contours of the left ventricle in echocardiographic sequences. Instead of learning offline spatiotemporal priors from databases, we exploit the inherent spatiotemporal coherence of individual data to constraint cardiac contour estimation. The contour tracker is initialized with a manual tracing of the first frame. It employs multiscale sparse representation of local image appearance and learns online multiscale appearance dictionaries in a boosting framework as the image sequence is segmented frame-by-frame sequentially. The weights of multiscale appearance dictionaries are optimized automatically. Our region-based level set segmentation integrates a spectrum of complementary multilevel information including intensity, multiscale local appearance, and dynamical shape prediction. The approach is validated on twenty-six 4D canine echocardiographic images acquired from both healthy and post-infarct canines. The segmentation results agree well with expert manual tracings. The ejection fraction estimates also show good agreement with manual results. Advantages of our approach are demonstrated by comparisons with a conventional pure intensity model, a registration-based contour tracker, and a state-of-the-art database-dependent offline dynamical shape model. We also demonstrate the feasibility of clinical application by applying the method to four 4D human data sets.

Radial Basis Functions for Combining Shape and Speckle Tracking in 4D Echocardiography

Quantitative analysis of left ventricular deformation can provide valuable information about the extent of disease as well as the efficacy of treatment. In this work, we develop an adaptive multi-level compactly supported radial basis approach for deformation analysis in 3D+time echocardiography. Our method combines displacement information from shape tracking of myocardial boundaries (derived from B-mode data) with mid-wall displacements from radio-frequency-based ultrasound speckle tracking. We evaluate our methods on open-chest canines (N=8) and show that our combined approach is better correlated to magnetic resonance tagging-derived strains than either individual method. We also are able to identify regions of myocardial infarction (confirmed by postmortem analysis) using radial strain values obtained with our approach.

A Dynamical Appearance Model Based on Multiscale Sparse Representation: Segmentation of the Left Ventricle from 4D Echocardiography

The spatio-temporal coherence in data plays an important role in echocardiographic segmentation. While learning offline dynamical priors from databases has received considerable attention, these priors may not be suitable for post-infarct patients and children with congenital heart disease. This paper presents a dynamical appearance model (DAM) driven by individual inherent data coherence. It employs multi-scale sparse representation of local appearance, learns online multiscale appearance dictionaries as the image sequence is segmented sequentially, and integrates a spectrum of complementary multiscale appearance information including intensity, multiscale local appearance, and dynamical shape predictions. It overcomes the limitations of database-driven statistical models and applies to a broader range of subjects. Results on 26 4D canine echocardiographic images acquired from both healthy and post-infarct subjects show that our method significantly improves segmentation accuracy and robustness compared to a conventional intensity model and our previous single-scale sparse representation method.

Segmentation of left ventricles from echocardiographic sequences via sparse appearance representation

Sparse representation has proven to be a powerful mathematical framework for studying high-dimensional data and uncovering its structures. Some recent research has shown its promise in discriminating image patterns. This paper presents an approach employing sparse appearance representation for segmenting left ventricular endocardial and epicardial boundaries from 2D echocardiographic sequences. It leverages the inherent spatio-temporal coherence of tissue/blood appearance over the sequence by modeling the different appearance of blood and tissues with different appearance dictionaries and updating the dictionaries in a boosting framework as the frames are segmented sequentially. The appearance of each frame is predicted in the form of appearance dictionaries based on the appearance observed in the preceding frames. The dictionaries discriminate image patterns by reconstructing them in the process of sparse coding resulting in an appearance discriminant that we incorporate into a region-based level set segmentation process. We illustrate the advantages of our approach by comparing it to manual tracings and an intensity-prior-based level set method. Experimental results on 34 2D canine echocardiographic sequences show that sparse appearance representation significantly outperforms intensity in terms of reliability and accuracy of segmentation.

Combining shape and speckle tracking for deformation analysis in echocardiography using radial basis functions

The quantification of left ventricular motion can provide valuable information about cardiac function. Echocardiography provides a non-invasive, readily available method for generating real time images of the left ventricle. Two methods for myocardial deformation tracking that have been used are shape tracking and speckle tracking. These two methods provide complementary information. Shape tracking gives high accuracy on epi- and endocardial boundaries, with speckle tracking providing good displacements across the myocardium. The methods presented here combine the results of these two methods using multilevel radial basis functions. Ultrasound data was acquired on six canines, (three baseline and three post coronary occlusion). Calculated strain values showed significant differences between the baseline and post-occlusion datasets in the occluded regions, while the remote regions did not change much. For one baseline animal, comparison to tagged MRI strain values showed reasonable agreement.

Comparing Shape Tracking, Speckle Tracking, and a Combined Method for Deformation Analysis in Echocardiography

Left ventricular (LV) deformation analysis can provide valuable information about cardiac function. Echocardiography is a non-invasive method for imaging the motion of the heart. Two methods that have been used for quantitative deformation analysis in echocardiography are shape tracking and speckle tracking. Shape tracking provides good displacement values on the boundaries of the myocardium, while speckle tracking provides more accurate tracking across the myocardium. Combining these two complementary sources of information can provide more accurate displacement values over the entire myocardium. These methods combine the two information sources using adaptive radial basis functions over multiple frames. Ultrasound data was acquired on three normal canines. Radial strain values were compared between the shape tracking, speckle tracking, and combined methods to show improvement when using both sources of information. Strain values were calculated from MR tagged data for comparison.

Automatic detection of coronary stenosis in X-ray angiography through spatio-temporal tracking

Automatic detection of coronary stenosis in X-ray angiography data is a challenging problem. The low contrast between vessels and surrounding tissue, as well as large intensity gradients within the image, make detection of vessels and stenoses difficult. In this paper we exploit the spatiotemporal nature of the angiography sequences to present a robust method for automatically isolating the coronary artery tree. An arterial width surface is formed for each isolated artery segment by calculating the width along a segment and tracking the segment in each image frame over time. A persistent minima of this surface then corresponds to a stenosis in the artery. Results of testing on a variety of stenosis locations in various coronary arteries are presented and compared to stenosis detected from single frame analysis. This method is able to detect the presence of stenosis in an artery segment with a sensitivity of 86% and a specificity of 97% on 16 patients with a total of 20 image runs. This is the first fully automatic method for stenosis detection in X-ray angiography.

Learning the Correlation Between Images and Disease Labels Using Ambiguous Learning

In this paper, we present a novel approach to candidate ground truth label generation for large-scale medical image collections by combining clinically-relevant textual and visual analysis through the framework of ambiguous label learning. In particular, we present a novel string matching algorithm for extracting disease labels from patient reports associated with imaging studies. These are assigned as ambiguous labels to the images of the study. Visual analysis is then performed on the images of the study and diagnostically relevant features are extracted from relevant regions within images. Finally, we learn the correlation between the ambiguous disease labels and visual features through an ambiguous SVM learning framework. The approach was validated in a large Doppler image collection of over 7000 images showing a scalable way to semi-automatically ground truth large image collections.

Sparsity and Biomechanics Inspired Integration of Shape and Speckle Tracking for Cardiac Deformation Analysis

Cardiac motion analysis, particularly of the left ventricle (LV), can provide valuable information regarding the functional state of the heart. We propose a strategy of combining shape tracking and speckle tracking based displacements to calculate the dense deformation field of the myocardium. We introduce the use and effects of l1 regularization, which induces sparsity, in our integration method. We also introduce regularization to make the dense fields more adhering to cardiac biomechanics. Finally, we motivate the necessity of temporal coherence in the dense fields and demonstrate a way of doing so. We test our method on ultrasound (US) images acquired from six open-chested canine hearts. Baseline and post-occlusion strain results are presented for an animal, where we were able to detect significant change in the ischemic region. Six sets of strain results were also compared to strains obtained from tagged magnetic resonance (MR) data. Median correlation (with MR-tagging) coefficients of 0.73 and 0.82 were obtained for radial and circumferential strains respectively.

A combined shape tracking and speckle tracking approach for 4D deformation analysis in echocardiography

Quantitative analysis of left ventricular function provides valuable information about overall heart health. Echocardiography is non-invasive method for imaging the heart that provides high temporal resolution allowing for imaging cardiac motion. Shape tracking and speckle tracking are two methods that have previously been used to track cardiac deformation in ultrasound. These two methods provide complementary displacement values. Shape tracking gives accurate boundary displacements, while speckle tracking provides accurate displacements across the myocardium. We combine these two methods using adaptive multilevel radial basis functions on 4D echocardiography data. Radial strains were calculated for N=5 open chest canines 6 weeks post-coronary artery occlusion. Radial strain values for three myocardial segments across three short axis slices showed good correlation to corresponding MR tagged data.