Automated Vertebra Identification from X-Ray Images

Automated identification of vertebra bodies from medical images is important for further image processing tasks. This paper presents a graphical model based solution for the vertebra identification from X-ray images. Compared with the existing graphical model based methods, the proposed method does not ask for a training process using training data and it also has the capability to automatically determine the number of vertebrae visible in the image. Experiments on digitially reconstructed radiographs of twenty-one cadaver spine segments verified its performance.