3D prostate segmentation based on ellipsoid fitting, image tapering and warping

Title3D prostate segmentation based on ellipsoid fitting, image tapering and warping
Publication TypeJournal Article
Year of Publication2008
AuthorsMahdavi, S., and S. E. Salcudean
JournalConf Proc IEEE Eng Med Biol Soc
Volume2008
Pagination2988-91
Abstract

This paper presents a 3D semi-automatic prostate segmentation method for B-mode trans-rectal ultrasound (TRUS) images. Segmentation is based on prior knowledge of the prostate transversal section shape which is assumed to be a tapered ellipse. The approach consists of an initial untapering and warping of the image to make the shape of the prostate approximately elliptical. The prostate contour is found in the untapered, warped images by edge detection and 2D/3D ellipsoidal curve fitting, performed by solving convex optimization problem. This leads to an average total segmentation duration of 7.42s which is more than 40 times faster than manual segmentation. Clinical studies carried out on 58 prostate volume studies show a volume sensitivity and accuracy of approximately 94% and 73% respectively.

URLhttp://dx.doi.org/10.1109/IEMBS.2008.4649831
DOI10.1109/IEMBS.2008.4649831

a place of mind, The University of British Columbia

Electrical and Computer Engineering
2332 Main Mall
Vancouver, BC Canada V6T 1Z4
Tel +1.604.822.2872
Fax +1.604.822.5949
Email:

Emergency Procedures | Accessibility | Contact UBC | © Copyright 2020 The University of British Columbia