Computer-assisted vertebra segmentation in x-ray images is a challenging problem. Inter-subject variability and the generally poor contrast of digitized radiograph images contribute to the segmentation difficulty. In this paper, a semi-automated live wire approach is investigated for vertebrae segmentation. The live wire approach integrates initially selected user points with dynamic programming to generate a closed vertebra boundary. In order to assess the degree to which vertebra features are conserved using the live wire technique, convex hull-based features to characterize anterior osteophytes in lumbar vertebrae are determined for live wire and manually segmented vertebrae. Anterior osteophyte discrimination was performed over 405 lumbar vertebrae, 204 abnormal vertebrae with anterior osteophytes and 201 normal vertebrae. A leave-one-out standard back propagation neural network was used for vertebrae segmentation. Experimental results show that manual segmentation yielded slightly better discrimination results than the live wire technique.

Meeting Name

First International Conference on Emerging Trends in Engineering and Technology (2008: Jul. 16-18, Nagpur, Maharashtra, India)


Electrical and Computer Engineering


Lister Hill National Center for Biomedical Communications
National Institutes of Health (U.S.)
National Library of Medicine

Keywords and Phrases

Live Wire; Lumbar Spine; Neural Networks; Osteophyte; Segmentation; X-ray; Image Processing; Image processing; Osteoarthritis

International Standard Book Number (ISBN)


Document Type

Article - Conference proceedings

Document Version

Final Version

File Type





© 2008 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Publication Date

01 Jul 2008