Left ventricle automated detection method in gated isotopic ventriculography using fuzzy clustering

Abstract

A method that uses the fuzzy ISODATA clustering algorithm and Fourier analysis is proposed for automated detection of heart left ventricle contours. This operation is used for quantitative analysis of cardiac function. The computation begins by finding the phase image. The fuzzy ISODATA algorithm is first applied to this image to generate a number of clusters that correspond to the organ substructures (ventricles, atria). Second, the ventricles cluster is isolated and the intensities of its points are replaced by the corresponding ones from the original (end diastolic) frame. Finally, a reduced image representing the ventricular region is obtained and an additional clustering is performed to find the left ventricular boundary automatically. This algorithm is tested by application of 105 sets of 16 images each. These results are compared with the measurements obtained with two semi-automatic methods used, respectively, on the Philips and the Sopha Medical gamma cameras.

D-ISODATA: A Distributed Algorithm for Unsupervised Classification of Remotely Sensed Data on Network of Workstations

“…For example, Carmen and Merickel in [4] replaced the heuristic rules that control the ISODATA algorithm with rules that search for the minimum value of an information theoretic criterion as Akaike's information criterion (AIC), and the consistent AIC (CAIC). Under certain situations when each pixel cannot be associated with exactly one class, a continuous classification method, known as fuzzy ISODATA, has been used to allocate relative class memberships to each pixel [1,20]. To reduce the computational complexity of the ISODATA, some variations have been proposed, such as using Mahalanobis distance norm instead of the Euclidean distance norm, lower triangular matrix, and expanded distance function approaches, and the use of the image auto-correlation property [13].…”

Contour extraction of left ventricular cavity from digital subtraction angiograms using a neural edge detector

“…These include methods for US (ultrasonic) images [8][9][10][11][12], methods for X-ray CT (computed tomographic) images or MR (magnetic resonance) images [13][14][15][16][17], and methods for nuclear medical images [18][19][20]. These methods consist of detection of the edges of a contour and integration of the edges as a contour.…”

A multiresolution image segmentation technique based on pyramidal segmentation and fuzzy clustering

“…Application of various automatic and semi-automatic segmentation methods in cardiac imaging has grown in recent years [1]- [13]. Segmentation methods for a number of applications [4]- [7] are based on deformable contour models such as snakes, which conform to various heart shapes and motions.…”

“…By this approach an initial average model of the left ventricle and its associated structures undergo shape deformations that are consistent with a statistical model derived from a number of echocardiographic images. By considering segmentation as a pixel classification task, the fuzzy c-means algorithm has also been applied in [2], [10] and [13] to define the left ventricular boundary in MR images.…”