Translator Disclaimer
18 March 2015 Deep learning for automatic localization, identification, and segmentation of vertebral bodies in volumetric MR images
Author Affiliations +
Abstract
This paper proposes an automatic method for vertebra localization, labeling, and segmentation in multi-slice Magnetic Resonance (MR) images. Prior work in this area on MR images mostly requires user interaction while our method is fully automatic. Cubic intensity-based features are extracted from image voxels. A deep learning approach is used for simultaneous localization and identification of vertebrae. The localized points are refined by local thresholding in the region of the detected vertebral column. Thereafter, a statistical multi-vertebrae model is initialized on the localized vertebrae. An iterative Expectation Maximization technique is used to register the vertebral body of the model to the image edges and obtain a segmentation of the lumbar vertebral bodies. The method is evaluated by applying to nine volumetric MR images of the spine. The results demonstrate 100% vertebra identification and a mean surface error of below 2.8 mm for 3D segmentation. Computation time is less than three minutes per high-resolution volumetric image.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Amin Suzani, Abtin Rasoulian, Alexander Seitel, Sidney Fels, Robert N. Rohling, and Purang Abolmaesumi "Deep learning for automatic localization, identification, and segmentation of vertebral bodies in volumetric MR images", Proc. SPIE 9415, Medical Imaging 2015: Image-Guided Procedures, Robotic Interventions, and Modeling, 941514 (18 March 2015); https://doi.org/10.1117/12.2081542
PROCEEDINGS
7 PAGES


SHARE
Advertisement
Advertisement
Back to Top