Gray level models for segmenting myocardium and blood in cardiac ultrasound images

Suggests some simple empirical models for first-order speckle statistics for use in segmentation of cardiac ultrasound images. The models are created by analyzing over 100 images obtained from commercial ultrasound machines in clinical settings. Four families of scalable distributions are compared with image data using goodness-of-fit and misclassification tests. Following the analysis, one of families is chosen as the appropriate model. Preliminary segmentation results are also reported.