Statistical Region Based Segmentation of Ultrasound Images

Ünal, Gözde and Slabaugh, Greg and Wels, Michael and Fang, Tong and Rao, Bimba (2008) Statistical Region Based Segmentation of Ultrasound Images. (Accepted/In Press)

WarningThere is a more recent version of this item available.

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader


Segmentation of ultrasound images is a challenging problem due to speckle, which corrupts the image and can result in weak or missing image boundaries, poor signal to noise ratio, and diminished contrast resolution. Speckle is a random interference pattern that is characterized by an asymmetric distribution as well as significant spatial correla- tion. These attributes of speckle are challenging to model in a segmentation approach, so many previous ultrasound segmentation methods simplify the problem by assuming that the speckle is white and/or Gaussian distributed. Unlike these methods, in this paper we present an ultrasound-specific segmentation approach that addresses both the spatial correlation of the data as well as its intensity distribution. We first decorrelate the image and then apply a region-based active contour whose motion is derived from an appropri- ate parametric distribution for maximum likelihood image segmentation. We consider zero-mean complex Gaussian, Rayleigh, and Fisher-Tippett flows, which are designed to model fully formed speckle in the in-phase/quadrature (IQ), envelope detected, and display (log compressed) images, respectively. We present experimental results demon- strating the effectiveness of our method, and compare the results to other parametric and non-parametric active contours.

Item Type:Article
Uncontrolled Keywords:ultrasound imaging, segmentation, statistical segmentation
Subjects:Q Science > QA Mathematics > QA075 Electronic computers. Computer science
ID Code:10693
Deposited By:Gözde Ünal
Deposited On:13 Nov 2008 15:40
Last Modified:22 Jul 2019 11:04

Available Versions of this Item

Repository Staff Only: item control page