UBC Theses and Dissertations
Automatic vertebrae localization, identification, and segmentation using deep learning and statistical models Suzani, Amin
Automatic localization and identification of vertebrae in medical images of the spine are core requirements for building computer-aided systems for spine diagnosis. Automated algorithms for segmentation of vertebral structures can also benefit these systems for diagnosis of a range of spine pathologies. The fundamental challenges associated with the above-stated tasks arise from the repetitive nature of vertebral structures, restrictions in field of view, presence of spine pathologies or surgical implants, and poor contrast of the target structures in some imaging modalities. This thesis presents an automatic method for localization, identification, and segmentation of vertebrae in volumetric computed tomography (CT) scans and magnetic resonance (MR) images of the spine. The method makes no assumptions about which section of the vertebral column is visible in the image. An efficient deep learning approach is used to predict the location of each vertebra based on its contextual information in the image. Then, a statistical multi-vertebrae model is initialized by the localized vertebrae from the previous step. An iterative expectation maximization technique is used to register the statistical multi-vertebrae model to the edge points of the image in order to achieve a fast and reliable segmentation of vertebral bodies. State-of-the-art results are obtained for vertebrae localization in a public dataset of 224 arbitrary-field-of-view CT scans of pathological cases. Promising results are also obtained from quantitative evaluation of the automated segmentation method on volumetric MR images of the spine.
Item Citations and Data
Attribution-NonCommercial-NoDerivs 2.5 Canada