Automatic Localisation of Vertebrae in DXA Images Using Random Forest Regression Voting

We describe a method for automatic detection and localisation of vertebrae in clinical images that was designed to avoid making a priori assumptions of how many vertebrae are visible. Multiple random forest regressors were trained to identify vertebral end-plates, providing estimates of both the location and pose of the vertebrae. The highest-weighted responses from each model were combined using a Hough-style voting array. A graphical approach was then used to extract contiguous sets of detections representing neighbouring vertebrae, by finding a path linking modes of high weight, subject to pose constraints. The method was evaluated on 320 lateral dual-energy X-ray absorptiometry spinal images with a high prevalence of osteoporotic vertebral fractures, and detected 92 % of the vertebrae between T7 and L4 with a mean localisation error of 2.36 mm. When used to initialise a constrained local model segmentation of the vertebrae, the method increased the incidence of fit failures from 1.5 to 2.1 % compared to manual initialisation, and produced no difference in fracture classification using a simple classifier.

[1]  Ben Glocker,et al.  Automatic Localization and Identification of Vertebrae in Arbitrary Field-of-View CT Scans , 2012, MICCAI.

[2]  Ben Glocker,et al.  Vertebrae Localization in Pathological Spine CT via Dense Classification from Sparse Annotations , 2013, MICCAI.

[3]  M. Nevitt,et al.  Vertebral fracture assessment using a semiquantitative technique , 1993, Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research.

[4]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Cristian Lorenz,et al.  Automated model-based vertebra detection, identification, and segmentation in CT images , 2009, Medical Image Anal..

[6]  J A Kanis,et al.  Effects of clodronate on vertebral fracture risk in osteoporosis: a 1-year interim analysis. , 2001, Bone.

[7]  Matthias F. Wucherer,et al.  Regulation of red fluorescent light emission in a cryptic marine fish , 2014, Frontiers in Zoology.

[8]  Marleen de Bruijne,et al.  Quantitative vertebral morphometry using neighbor-conditional shape models , 2007, Medical Image Anal..

[9]  T. Rachner,et al.  Osteoporosis: now and the future , 2011, The Lancet.

[10]  Alejandro F. Frangi,et al.  Recent Advances in Computational Methods and Clinical Applications for Spine Imaging , 2015 .

[11]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[12]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[13]  Anja C. Schunke,et al.  Semi-automatic landmark point annotation for geometric morphometrics , 2014, Frontiers in Zoology.

[14]  S. Cummings,et al.  Epidemiology and outcomes of osteoporotic fractures , 2002, The Lancet.

[15]  Timothy F. Cootes,et al.  Automatic Location of Vertebrae on DXA Images Using Random Forest Regression , 2012, MICCAI.

[16]  Claudia Lindner,et al.  Robust and Accurate Shape Model Matching Using Random Forest Regression-Voting. , 2015, IEEE transactions on pattern analysis and machine intelligence.

[17]  Juergen Gall,et al.  Class-specific Hough forests for object detection , 2009, CVPR.

[18]  Marleen de Bruijne,et al.  Quantitative Vertebral Morphometry Using Neighbor-Conditional Shape Models , 2006, MICCAI.

[19]  H. Genant,et al.  Underdiagnosis of Vertebral Fractures Is a Worldwide Problem: The IMPACT Study , 2004, Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research.

[20]  Tim Cootes,et al.  Localisation of Vertebrae on DXA Images using Constrained Local Models with Random Forest Regression Voting , 2014 .