Skip to main content

Table 5 The comparison of liver segmentation methods

From: An automated liver segmentation in liver iron concentration map using fuzzy c-means clustering combined with anatomical landmark data

Authors DSC Number of data Run time
López-Mir et al.[22] 0.95 16 exams
59–120 slices/exam
7 s/image
(Intel Corei5 2.80 GHz CPU, 2 GB RAM)
Bereciartua et al. [24] 0.90 18 exams
21 slices/exam
0.53 s/image
(Intel core2quad 3.00 GHz CPU, N/A RAM)
Göçeri [63] 0.95 10 slices 16.80 s/image
(Intel
Pentium 2.40 GHz CPU, 2 GB RAM)
Shen et al. [62] 0.94 40 exams
44 slices/exam
20 min/case
(Intel Corei5 1.3 GHz CPU, 8 GB RAM)
Huynh et al. [61] 0.91 27 exams
44–120 slices/exam
8.4 min/case
(Intel Xeon 2.66 GHz CPU, N/A RAM)
Wang et al. [38] 0.93 (T2*w)
0.95 (T1w)
168 exams (T2*w)
6 slices (TEs)/exam
100 exams (T1w)
N/A
Jansen et al. [64] 0.95 55 exams
100 slices/exam
33 exams for training
3 exams for validation
19 exams for testing
N/A
Proposed method 0.93 537 exams
20 slices (TEs)/exam
441 exams for training
112 exams for testing
0.31 s/image
(Intel Corei7 4.30 GHz, 16 GB RAM)