Employing anatomical knowledge in vertebral column labeling

The spinal column constitutes the central axis of human torso and is often used by radiologists to reference the location of organs in the chest and abdomen. However, visually identifying and labeling vertebrae is not trivial and can be timeconsuming. This paper presents an approach to automatically label vertebrae based on two pieces of anatomical knowledge: one vertebra has at most two attached ribs, and ribs are attached only to thoracic vertebrae. The spinal column is first extracted by a hybrid method using the watershed algorithm, directed acyclic graph search and a four-part vertebra model. Then curved reformations in sagittal and coronal directions are computed and aggregated intensity profiles along the spinal cord are analyzed to partition the spinal column into vertebrae. After that, candidates for rib bones are detected using features such as location, orientation, shape, size and density. Then a correspondence matrix is established to match ribs and vertebrae. The last vertebra (from thoracic to lumbar) with attached ribs is identified and labeled as T12. The rest of vertebrae are labeled accordingly. The method was tested on 50 CT scans and successfully labeled 48 of them. The two failed cases were mainly due to rudimentary ribs.