Biomedical Engineering Reference
In-Depth Information
(a)
(b)
(c)
Figure 9.12: (a) Segmented lung using the proposed algorithm, error
=
1.09%.
(b) Output of segmentation algorithm by selecting parameters for high-level
process randomly, error
=
1.86%. (c) Segmented lung by radiologist.
the following results:
α
=
1,
θ
1
=
0
.
89,
θ
2
=
0
.
8,
θ
3
=
0
.
78,
θ
4
=
0
.
69,
θ
5
=
0
.
54,
θ
6
=
0
.
61,
θ
7
=
0
.
89 ,
θ
8
=
0
.
56, and
θ
9
=
0
.
99.
The result of segmentation for the image shown in Fig. 9.4 using these pa-
rameters is shown in Fig. 9.12. Figure 9.12(a) shows the results of proposed algo-
rithm. Figure 9.12(b) shows output of the Metropolis algorithm by selecting pa-
rameters randomly. Figure 9.12(c) shows the segmentation done by a radiologist.
As shown in Fig. 9.12(a) the accuracy of our algorithm seems good if it is
compared with the segmentation of the radiologist. Figure 9.13 shows compari-
son between our results and the results obtained by iterative threshold method
which was proposed by Hu and Hoffman [23]. It is clear from Fig. 9.13 that the
error
2.1%
=
error
=
9.1%
error
3.01%
error
=
0.41%
=
(a)
(b)
(c)
(d)
Figure 9.13:
(a) Original CT, (b) segmented lung using the proposed model, (c)
segmented lung using the iterative threshold method, and (d) segmented lung
by radiologist. The errors with respect to this ground truth are highlighted by
red color.
