Information Technology Reference
In-Depth Information
5.2.2 Spinal Cord and Canal
Many research groups have focused on the segmentation of the spinal cord and the
spinal canal in CT. Early on, Karangelis and Zimeras [
48
] introduced a semi-
automatic 3D method for segmenting the spinal cord and tested that on 14 CT
volumes. On each slice image, they used a boundary tracking method along with
linear interpolation in the z-direction. However, proper selection of the seed point
and the threshold limits its applicability. Meanwhile, Archip et al. [
7
] presented a
top-down knowledge-based technique that identi
ed the spinal cord in CT images.
This approach used an Anatomical Structures Map and a task-oriented architecture
plan solver. They claimed that the method was
flexible enough to handle inter-
patient variation and transparent to the radiologist ensuring that the experts can take
control of undesirable results by image analysis. On 23 cases, the spinal canal was
localized with an accuracy of 92 %, the spinal cord with an accuracy of 85 % and
the lamina with an accuracy of 72 %. Couple years later, Burnett et al. [
12
]
developed a semi-automatic algorithm for spinal canal segmentation of CT scans.
The spinal canal was partially delineated by wavelet-based edge detection and
fl
tted
to a deformable model. Later, the template was aligned manually to
t more
accurately to the spinal canal. Experiments on 557 axial images showed that
automatic delineation of the spinal canal was successful on 91 %, unsuccessful on
2 % and requiring further editing on the rest 7 % of the images. Around same time,
Ny
l et al. [
75
] proposed a semi-automatic method using 2D snakes for segmenting
the spinal cord in a slice-by-slice manner testing that on 27 CT images for the
Thoracic region. The 3D volume is then generated by interpolation. Snakes [
49
] are
highly sensitive for the initialization which is usually performed manually.
On the other hand, because CT scans are better than X-rays and MRIs in terms of
boney structure visualization, there has been great efforts toward building a CAD
system for detection of various abnormalities such as Syndesmophytes (abnormal
bone structures at the vertebral end plates) [
90
], spine Metastases [
38
] and vertebral
fractures [
2
,
29
]. Most of these efforts include localization, labeling, or segmen-
tation work.
Mid last decade, Tan et al. [
90
] provided a quantitative measure of the Syn-
desmophytes using high resolution CT images. They
รบ
first segmented the whole
vertebra using a cascade of successive level sets, and then used curvature infor-
mation to segment and quantify Syndesmophytes achieving 0.898 Pearson corre-
lation between manual (medical expert) and the automated diagnosis which a high
positive correlation level.
More recently, Hammon et al. [
38
] proposed a method of automatic detection of
Lytic and Blastic Thoracolumbar spine Metastases (malignant tumors) from 3D CT
images. They
first detected the vertebral bodies using iterative marginal space
learning and then use a cascade detector consisting of three random forest-based
discriminative models to detect Metastases. Evaluation on 20 patients with 42 Lytic
and on 30 patients with 172 Blastic Metastases (where the CAD system was trained
using CT images of 114 subjects with 102 Lytic and 308 Blastic spinal Metastases)
showed a sensitivity of 88 % for Lytic and 83 % for Blastic Metastases.
