Active Contour Model Based Segmentation of Colposcopy Images of Cervix Uteri Using Gaussian Pyramids

Raad, Viara Van and Bradley, Andrew P. (2002). Active Contour Model Based Segmentation of Colposcopy Images of Cervix Uteri Using Gaussian Pyramids. In: 6th International Symposium on Digital Signal Processing for Communication Systems (DSPCS'02), Sydney, Australia, (). January, 2002.

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
APB_VVR_SnakeTM.pdf APB VVR SnakeTM.pdf application/pdf 390.58KB 250

Author Raad, Viara Van
Bradley, Andrew P.
Title of paper Active Contour Model Based Segmentation of Colposcopy Images of Cervix Uteri Using Gaussian Pyramids
Conference name 6th International Symposium on Digital Signal Processing for Communication Systems (DSPCS'02)
Conference location Sydney, Australia
Conference dates January, 2002
Publication Year 2002
Sub-type Fully published paper
Abstract/Summary Colposcopic images from cervix uteri are subjected to a segmentation algorithm using a combination of an active contour model or snakes on multiresolution levels, using a Gaussian Pyramid (GP). The segmentation aims to outline a specific feature from the cervical images- the Transformation Zone (TZ), where a possible neoplasia (a pre-cancer or cancer tissue stage) can occur. The process includes an implementation of a new snake - the boundary-searching snake, based on both image gradient features and region features. The adaptive 'snake' is executed on a low image resolution level, aiming to avoid a specific artifact in the images-known as a specular reflection. Further, the snake coordinates are propagated to the highest level of the GP. The resulting algorithm segments one of the most complex and variable anatomical shapes as a biological structure in its normal and pre-cancerous stages of the cervix uteri.
Subjects 280203 Image Processing
291501 Clinical Engineering
Keyword colposcopy images
cervix uteri
dynamic boundary
snake
multiscale
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status Unknown

 
Versions
Version Filter Type
Citation counts: Google Scholar Search Google Scholar
Access Statistics: 753 Abstract Views, 250 File Downloads  -  Detailed Statistics
Created: Wed, 23 Nov 2005, 10:00:00 EST by Andrew Bradley on behalf of Library Technology Service