Review
Copyright ©The Author(s) 2023.
World J Gastrointest Surg. Nov 27, 2023; 15(11): 2382-2397
Published online Nov 27, 2023. doi: 10.4240/wjgs.v15.i11.2382
Table 1 Selected fully automatic liver segmentation algorithms[28]
Ref.
Key techniques
Dataset
Accuracy
Kumar et al[29], 2013Region growingProprietary98% ± 1%
Chen et al[30], 2012AAM, graph cutSLIVER0793.5% ± 1.8%
Huang et al[31], 2016Template matching (SBLDA)3D-IRCADb92.16% ± 2.95%
Wu et al[32], 2016Linear clustering, graph cutSLIVER0775.2%-71.4%
Mohamed et al[33], 2017Bayesian modelProprietary95.5%
Zheng et al[34], 2022DL (CNN, C-LSTM)SLIVER0782.5% ± 7.7%
Table 2 Selected semiautomatic liver segmentation algorithms[28]
Ref.
Key techniques
Dataset
Accuracy
Chen et al[44], 2009 Quasi-Monte CarloProprietaryNA
Yang et al[41], 2014Level setSLIVER0778.9%
Liao et al[45], 2016Graph cutSLIVER0794.2% ± 3.3%
Lu et al[46], 20173D CNN, graph cut3D-IRCADb90.64% ± 3.34%
Chartrand et al[43], 2017Deformable modelSLIVER0792.38% ± 1.35%
Le et al[23], 2021Mixture model, graph cutSLIVER0792.2% ± 1.5%
Table 3 Sensitivity (in percent) of focal liver tumor detection
Ref.
CT
MRI
CEUS
Langella et al[81], 2019-75.194.5
Huf et al[82], 2017-91.490
Niekel et al[83], 201083.688.2-
Kessel et al[78], 201269.985.7-
Yang et al[63], 201083.2--
Table 4 Average proportion (in percent) of functional segment groups[115]
Ref.Lobe level
Sectional level
AnteriorPosterior
Left
Right
Lateral
Medial
Huang et al[106], 2008396114.124.739.321.9
Ruskó et al[112], 2013326812.22040.227.6
Chen et al[108], 2016455526.718.123.332
Butdee et al[113], 2017406017.922.129.430.6
Le et al[11], 2021326813.319.23037.5