Knowledge-based femur detection in conventional radiographs of the pelvis

by: Roland Pilgram, Claudia Walch

Computers in Biology and Medicine, Vol. In Press, Corrected Proof

View FullText article

DOI, ScienceDirect

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

ashko

Find related articles with these CiteULike tags

aam, asm, bone, canny, femur, hip, hough, radiograph, segmentation, shape

Abstract

In this paper we present a knowledge-based femur detection algorithm. The algorithm uses femur corpus constraints, Canny edge detection and Hough lines. For optimal femur template placement in the local area we use cross-correlation. The segmentation itself is done with an optimized active shape modeling technique. Using the knowledge-based technique we have located 95% of the femur shapes of N=117 X-rays. From those 83% of the target femur shapes have been segmented successfully (point-to-point error: ~14 pixels, point-to-boundary error = ~9 pixels).

@article{citeulike:2569835, abstract = {In this paper we present a knowledge-based femur detection algorithm. The algorithm uses femur corpus constraints, Canny edge detection and Hough lines. For optimal femur template placement in the local area we use cross-correlation. The segmentation itself is done with an optimized active shape modeling technique. Using the knowledge-based technique we have located 95\% of the femur shapes of N=117 X-rays. From those 83\% of the target femur shapes have been segmented successfully (point-to-point error: \~{}14 pixels, point-to-boundary error = \~{}9 pixels).}, author = {Pilgram, Roland and Walch, Claudia }, citeulike-article-id = {2569835}, doi = {http://dx.doi.org/10.1016/j.compbiomed.2008.01.010}, journal = {Computers in Biology and Medicine}, keywords = {aam, asm, bone, canny, femur, hip, hough, radiograph, segmentation, shape}, posted-at = {2008-03-21 14:15:12}, priority = {2}, title = {Knowledge-based femur detection in conventional radiographs of the pelvis}, url = {http://dx.doi.org/10.1016/j.compbiomed.2008.01.010}, volume = {In Press, Corrected Proof} }

RIS record

TY - JOUR ID - citeulike:2569835 L3 - citeulike-article-id:2569835 TI - Knowledge-based femur detection in conventional radiographs of the pelvis JF - Computers in Biology and Medicine VL - In Press, Corrected Proof N2 - In this paper we present a knowledge-based femur detection algorithm. The algorithm uses femur corpus constraints, Canny edge detection and Hough lines. For optimal femur template placement in the local area we use cross-correlation. The segmentation itself is done with an optimized active shape modeling technique. Using the knowledge-based technique we have located 95% of the femur shapes of N=117 X-rays. From those 83% of the target femur shapes have been segmented successfully (point-to-point error: ~14 pixels, point-to-boundary error = ~9 pixels). KW - aam KW - asm KW - bone KW - canny KW - femur KW - hip KW - hough KW - radiograph KW - segmentation KW - shape AU - Pilgram, Roland AU - Walch, Claudia UR - http://dx.doi.org/10.1016/j.compbiomed.2008.01.010 ER -

RIS BibTeX