Boundary Regression for Human Vertebrae Segmentation

The diagnosis and treatment of pathologies like Low back pain, Osteoporosis, Spondyflolisthesis etc. require detailed analysis of spinal images. Manual segmentation of vertebrae in spinal images is difficult. In this paper we discuss an automatic method for segmentation of vertebrae. In this work, segmentation is implemented as a boundary regression problem.

[1]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[2]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[3]  Dit-Yan Yeung,et al.  Sparse Kernel Machines , 2008 .

[4]  Timothy F. Cootes,et al.  Segmentation of Lumbar Vertebrae Using Part-Based Graphs and Active Appearance Models , 2009, MICCAI.

[5]  Yadwinder Kaur,et al.  Review of Different Local and Global Contrast Enhancement Techniques for a Digital Image , 2014 .

[6]  Manik Varma,et al.  More generality in efficient multiple kernel learning , 2009, ICML '09.

[7]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[8]  Fernando Pérez-Cruz,et al.  Fast Training of Support Vector Classifiers , 2000, NIPS.

[9]  Takeo Kanade,et al.  Real-time topometric localization , 2012, 2012 IEEE International Conference on Robotics and Automation.

[10]  Andrew Zisserman,et al.  Vertebrae Detection and Labelling in Lumbar MR Images , 2014 .

[11]  Fernando Pérez-Cruz,et al.  SVM multiregression for nonlinear channel estimation in multiple-input multiple-output systems , 2004, IEEE Transactions on Signal Processing.

[12]  Jason J. Corso,et al.  Labeling of Lumbar Discs Using Both Pixel- and Object-Level Features With a Two-Level Probabilistic Model , 2011, IEEE Transactions on Medical Imaging.

[13]  Fernando Pérez-Cruz,et al.  Multi-dimensional Function Approximation and Regression Estimation , 2002, ICANN.