Fully Automatic and Highly Accurate Segmentation of the Proximal Femur in AP Pelvic Radiographs

Our fully automatic segmentation tool outperforms alternative matching techniques significantly when starting searching from the mean shape at true pose. It achieves a mean point-to-curve error of less than 0.9mm for 99% of all images.

 

We tested our fully automatic proximal femur segmentation system on 839 AP pelvic radiographs (527 females, 312 males) using two-fold cross-validation experiments. The aim was to place 65 dense points along the front-view contour of the proximal femur. We report averaged mean point-to-curve errors as a percentage of the shaft width (based on a subset of calibrated images we estimated the latter to be 37mm).

Our femur segmentation system is fully automatic and highly accurate. It achieves a mean point-to-curve error of less than 0.9mm for 99% of all images. This is equally good as a local search started from the mean shape at true pose (see left plot).

 

Examples of segmentation results of the fully automated system (sorted by mean point-to-curve error percentiles): a) median – 0.4mm; b) 91.2% – 0.6mm, highest global search error (ie. the global search had a success rate of 100%); c) 99.0% – 0.9mm; d) maximal overall error – 2.7mm.

Data shown on this page is copyright (c) 2013 IEEE (doi:10.1109/TMI.2013.2258030). Personal use of this material is permitted. However, permission to use this material for any other purposes must be obtained from the IEEE by sending a request to pubs-permissions@ieee.org.