A 2-DIMENSIONAL EXTENSION OF MINIMUM CROSS-ENTROPY THRESHOLDING FOR THE SEGMENTATION OF ULTRASOUND IMAGES

Segmentation is often an important step in medical image analysis. The local entropy is a possible variable for segmenting ultrasound images containing fluid surrounded by a soft tissue. A commonly used tool fo r image segmentation is thresholding. Recently, a new thresholding tec hnique, known as ''minimum cross entropy thresholding'' (MCE), has bee n proposed. We present a multivariate extension of MCE in which the se gmented variable (gray level) is replaced by a weighted combination of several image parameters. We propose to use a bivariate extension of MCE, which uses a linear combination of the gray level and the local e ntropy. The results obtained are demonstrated for ultrasound images of ovarian cysts. Copyright (C) 1996 World Federation for Ultrasound in Medicine & Biology.