Information Technology Reference
In-Depth Information
Fig. 13 Comparison between manual (red) and automated (green) segmentation of syndesmo-
phytes on a 3D surface reconstructions, b, c sagittal slices. The yellow line in a indicates the
position of the sagittal slices. The overlap similarity index in this example is 0.77
2 V
1
\
ð
V
2
Þ
OSI
¼
ð
15
Þ
V
1
þ
V
2
where V
1
and V
2
are the two volumes compared. OSI is always comprised between
0 and 1, with 1 indicating perfect overlap. Out of the 12 IDSs processed, the mean
(
0.06). Considering that syndesmophytes are small objects, an
OSI of 0.76 indicates good agreement. Figure
13
shows an example of syndes-
mophyte segmentations by the manual and automated methods.
In a more extensive validation study involving 38 patients, the syndesmophyte
volumes computed by the algorithm were compared with the readings of physicians
[
56
]. Two physicians scored 152 IDSs (4 IDSs per patient) using a 4-point grading
system (0 = no syndesmophyte; 1 = small isolated syndesmophytes involving less
than a quarter of the vertebral rim and no bridging; 2 = syndesmophyte involving
more than a quarter of the vertebral rim or focal bridging; 3 = bridging involving more
than a quarter of the vertebral rim). The physicians examined the IDSs in the axial,
coronal and sagittal views of the CT reconstructions. Figure
14
shows the association
of computed volumes with the physicians
±
std) OSI was 0.76 (
±
'
ratings. Volumes computed by the algo-
'
rithm increased with the readers
Wallis
trend test accounting for non-independence of observations within patients [
57
]).
scores (p < 0.0001 using a strati
ed Kruskal
-
3.2 Reliability/Precision
The precision of the algorithm was evaluated by comparing the results of 2 scans
performed on the same day in 9 patients [
56
]. The protocol was approved by the
institutional review board and all subjects provided written informed consent. After
