The invention relates to a method and an according apparatus and system for reliably identifying a specific part of a spine, in particular a specific vertebra, in an image, in particular a computed tomography (CT) image, of a human or animal body, comprising the following steps: a) determining one or more parts, in particular vertebrae, of the spine in the image, b) determining one or more discriminative parameters for each of said parts of the spine in the image, wherein the discriminative parameters relate to at least one anatomical property of each of said parts of the spine, c) classifying the discriminative parameters of said parts of the spine in the image and d) identifying said specific part of the spine based on the classification of the discriminative parameters of said parts of the spine in the image. An accordingly identified vertebra, in particular the T12 vertebra and/or its associated intervertebral discs, can be used advantageously as a starting point of powerful automatic spine labeling algorithms.
