Automated vertebrae localization and identification by decision forests and image-based refinement on real-world CT data.

Abstract

Development of a fully automatic algorithm for the automatic localization and identification of vertebral bodies in computed tomography (CT). This algorithm was developed using a dataset based on real-world data of 232 thoraco-abdominopelvic CT scans retrospectively collected. In order to achieve an accurate solution, a two-stage automated method was developed: decision forests for a rough prediction of vertebral bodies position, and morphological image processing techniques to refine the previous detection by locating the position of the spinal canal. The mean distance error between the predicted vertebrae centroid position and truth was 13.7mm. The identification rate was 79.6% on the thoracic region and of 74.8% on the lumbar segment. The algorithm provides a new method to detect and identify vertebral bodies from arbitrary field-of-view body CT scans.