BoneFinder is a fully automatic tool to segment skeletal structures from 2D radiographs by placing a set of points along the bone contour or at key landmark positions. BoneFinder is freely available for non-commercial research purposes. The software and manual can be downloaded from www.click2go.umip.com/i/software/Bonefinder.html.

BoneFinder currently comes with a model to segment the proximal femur from AP pelvic images by placing 65 points along its front-view contour. This model was trained on 1105 AP pelvic radiographs provided by The arcOGEN Consortium; it was designed to segment disease-free bone contours. We are currently working on providing additional models. Please contact me if you would want to discuss the segmentation of alternative skeletal structures (e.g. knees, hands, skulls). 

Please cite the following paper when publishing anything resulting from the usage of BoneFinder:

C. Lindner, S. Thiagarajah, J.M. Wilkinson, The arcOGEN Consortium, G.A. Wallis and T.F. Cootes. "Fully Automatic Segmentation of the Proximal Femur using Random Forest Regression Voting", IEEE Transactions on Medical Imaging, Vol. 32, No. 8, pp. 1462-1472, 2013. doi:10.1109/TMI.2013.2258030