Recovery of the 3-D shape of the left ventricle from echocardiographic images

Abstract

A computational method is reported which allows the fully automated recovery of the three-dimensional shape of the cardiac left ventricle from a reduced set of apical echo views. Two typically ill-posed problems have been faced: 1) the detection of the left ventricle contours in each view, and 2) the integration of the detected contour points (which form a sparse and partially inconsistent data set) into a single surface representation. The authors' solution to these problems is based on a careful integration of standard computer vision algorithms with neural networks. Boundary detection comprises three steps: edge detection, edge grouping, and edge classification. The first and second steps (which are typical early-vision tasks not involving specific domain-knowledge) have been performed through fast, well-established algorithms of computer vision. The higher level task of left ventricle-edge discrimination, which involves the exploitation of specific knowledge about the left ventricle silhouette, has been performed by feedforward neural networks. Following the most recent results in the field of computer vision, the first step in solving the problem of recovering the ventricle surface has been the adoption of a physically inspired model of it. Basically, the authors have modeled the left ventricle surface as a closed, thin, elastic surface and the data as a set of radial springs acting on it. The recovery process is equivalent to the settling of the surface-plus-springs system into a stable configuration of minimum potential energy. The finite element discretization of this model leads directly to an analog neural-network implementation. The efficiency of such an implementation has been remarkably enhanced through a learning algorithm which embeds specific knowledge about the shape of the left ventricle in the network. Experiments using clinical echographic sequences are described. Four apical views (each with a different rotation of the probe) have been acquired during a heartbeat from a set of seven normal subjects. These images have been utilized to set the various processing modules and test their capabilities.

LV volume quantification via spatiotemporal analysis of real-time 3-D echocardiography

“…There are several approaches for defining this potential. In order to attract the snake to minima of the potential force, a simple model is to define an edge map (19) on the image , or…”

“…Several approaches for epicardial and endocardial border 0278-0062/01$10.00 ©2001 IEEE detection from ultrasound data have been reported during the past decade with partial success. Recent studies include methods based on statistical Markov random field models [12]- [15], fuzzy logic [16], [17], neural networks [18], [19], morphological filters [18], [20], active contours, and level sets [21]- [25]. A common motivation for these efforts, which have focused on the development of new methods of volume extraction, is that existing segmentation tools are not adapted to this type of data and do not meet the accuracy requirements of clinical applications.…”

Volume Measurement in Sequential Freehand 3-D Ultrasound

“…Examples include a catheter mounted on a ratcheted device, giving a measurement of drawback [129,174], and rotational scanning with the angle measured from a scale attached to a fixed mechanical arm and the transducer [46]. Clearly this method precludes fast acquisition, which is one of the potential benefits of 3D ultrasound.…”

“…A completely different approach to surface reconstruction by using deformable models is presented in [46], which also contains a review of the application of similar techniques to the heart. Rather than starting with the cross-sections and attempting to extract a surface, this method starts with a model and attempts to fit this to the cross-sections.…”

Genetic algorithm-based interactive segmentation of 3D medical images

“…The reliability of such methods can be improved using techniques for segmentation and data representation based on data-driven elastic models, such as snakes [8] and deformable surface models [9], which have been applied successfully also in the field of medical imaging [10][11][12].…”