Share Email Print

Proceedings Paper

Simultaneous 3D segmentation of three bone compartments on high resolution knee MR images from osteoarthritis initiative (OAI) using graph cuts
Author(s): Hackjoon Shim; C. Kent Kwoh; Il Dong Yun; Sang Uk Lee; Kyongtae Bae
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Osteoarthritis (OA) is associated with degradation of cartilage and related changes in the underlying bone. Quantitative measurement of those changes from MR images is an important biomarker to study the progression of OA and it requires a reliable segmentation of knee bone and cartilage. As the most popular method, manual segmentation of knee joint structures by boundary delineation is highly laborious and subject to user-variation. To overcome these difficulties, we have developed a semi-automated method for segmentation of knee bones, which consisted of two steps: placement of seeds and computation of segmentation. In the first step, seeds were placed by the user on a number of slices and then were propagated automatically to neighboring images. The seed placement could be performed on any of sagittal, coronal, and axial planes. The second step, computation of segmentation, was based on a graph-cuts algorithm where the optimal segmentation is the one that minimizes a cost function, which integrated the seeds specified by the user and both the regional and boundary properties of the regions to be segmented. The algorithm also allows simultaneous segmentation of three compartments of the knee bone (femur, tibia, patella). Our method was tested on the knee MR images of six subjects from the osteoarthritis initiative (OAI). The segmentation processing time (mean±SD) was (22±4)min, which is much shorter than that by the manual boundary delineation method (typically several hours). With this improved efficiency, our segmentation method will facilitate the quantitative morphologic analysis of changes in knee bones associated with osteoarthritis.

Paper Details

Date Published: 27 March 2009
PDF: 8 pages
Proc. SPIE 7259, Medical Imaging 2009: Image Processing, 72593P (27 March 2009); doi: 10.1117/12.812487
Show Author Affiliations
Hackjoon Shim, Seoul National Univ. (Korea, Republic of)
C. Kent Kwoh, Univ. of Pittsburgh (United States)
Il Dong Yun, Hankuk Univ. of Foreign Studies (Korea, Republic of)
Sang Uk Lee, Seoul National Univ. (Korea, Republic of)
Kyongtae Bae, Univ. of Pittsburgh (United States)

Published in SPIE Proceedings Vol. 7259:
Medical Imaging 2009: Image Processing
Josien P. W. Pluim; Benoit M. Dawant, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?