Details
| Original language | English |
|---|---|
| Pages (from-to) | 471-482 |
| Number of pages | 12 |
| Journal | Medical image analysis |
| Volume | 13 |
| Issue number | 3 |
| Publication status | Published - 20 Feb 2009 |
Abstract
For many orthopaedic, neurological, and oncological applications, an exact segmentation of the vertebral column including an identification of each vertebra is essential. However, although bony structures show high contrast in CT images, the segmentation and labelling of individual vertebrae is challenging. In this paper, we present a comprehensive solution for automatically detecting, identifying, and segmenting vertebrae in CT images. A framework has been designed that takes an arbitrary CT image, e.g., head-neck, thorax, lumbar, or whole spine, as input and provides a segmentation in form of labelled triangulated vertebra surface models. In order to obtain a robust processing chain, profound prior knowledge is applied through the use of various kinds of models covering shape, gradient, and appearance information. The framework has been tested on 64 CT images even including pathologies. In 56 cases, it was successfully applied resulting in a final mean point-to-surface segmentation error of 1.12 ± 1.04 mm. One key issue is a reliable identification of vertebrae. For a single vertebra, we achieve an identification success of more than 70%. Increasing the number of available vertebrae leads to an increase in the identification rate reaching 100% if 16 or more vertebrae are shown in the image.
Keywords
- Deformable models, Geometric modelling, Vertebra identification, Vertebra labelling, Vertebra segmentation
ASJC Scopus subject areas
- Health Professions(all)
- Radiological and Ultrasound Technology
- Medicine(all)
- Radiology Nuclear Medicine and imaging
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Medicine(all)
- Health Informatics
- Computer Science(all)
- Computer Graphics and Computer-Aided Design
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Medical image analysis, Vol. 13, No. 3, 20.02.2009, p. 471-482.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Automated model-based vertebra detection, identification, and segmentation in CT images
AU - Klinder, Tobias
AU - Ostermann, Jörn
AU - Ehm, Matthias
AU - Franz, Astrid
AU - Kneser, Reinhard
AU - Lorenz, Cristian
PY - 2009/2/20
Y1 - 2009/2/20
N2 - For many orthopaedic, neurological, and oncological applications, an exact segmentation of the vertebral column including an identification of each vertebra is essential. However, although bony structures show high contrast in CT images, the segmentation and labelling of individual vertebrae is challenging. In this paper, we present a comprehensive solution for automatically detecting, identifying, and segmenting vertebrae in CT images. A framework has been designed that takes an arbitrary CT image, e.g., head-neck, thorax, lumbar, or whole spine, as input and provides a segmentation in form of labelled triangulated vertebra surface models. In order to obtain a robust processing chain, profound prior knowledge is applied through the use of various kinds of models covering shape, gradient, and appearance information. The framework has been tested on 64 CT images even including pathologies. In 56 cases, it was successfully applied resulting in a final mean point-to-surface segmentation error of 1.12 ± 1.04 mm. One key issue is a reliable identification of vertebrae. For a single vertebra, we achieve an identification success of more than 70%. Increasing the number of available vertebrae leads to an increase in the identification rate reaching 100% if 16 or more vertebrae are shown in the image.
AB - For many orthopaedic, neurological, and oncological applications, an exact segmentation of the vertebral column including an identification of each vertebra is essential. However, although bony structures show high contrast in CT images, the segmentation and labelling of individual vertebrae is challenging. In this paper, we present a comprehensive solution for automatically detecting, identifying, and segmenting vertebrae in CT images. A framework has been designed that takes an arbitrary CT image, e.g., head-neck, thorax, lumbar, or whole spine, as input and provides a segmentation in form of labelled triangulated vertebra surface models. In order to obtain a robust processing chain, profound prior knowledge is applied through the use of various kinds of models covering shape, gradient, and appearance information. The framework has been tested on 64 CT images even including pathologies. In 56 cases, it was successfully applied resulting in a final mean point-to-surface segmentation error of 1.12 ± 1.04 mm. One key issue is a reliable identification of vertebrae. For a single vertebra, we achieve an identification success of more than 70%. Increasing the number of available vertebrae leads to an increase in the identification rate reaching 100% if 16 or more vertebrae are shown in the image.
KW - Deformable models
KW - Geometric modelling
KW - Vertebra identification
KW - Vertebra labelling
KW - Vertebra segmentation
UR - http://www.scopus.com/inward/record.url?scp=67349192210&partnerID=8YFLogxK
U2 - 10.1016/j.media.2009.02.004
DO - 10.1016/j.media.2009.02.004
M3 - Article
C2 - 19285910
AN - SCOPUS:67349192210
VL - 13
SP - 471
EP - 482
JO - Medical image analysis
JF - Medical image analysis
SN - 1361-8415
IS - 3
ER -