Influence of Active Shape Model Segmentation Method on Optical Reconstruction

Fig. 1. Left kidney image segmentation results obtained by different methods. (a) ASM1 method; (b) ASM2 method; (c) ASM3 method; (d) ASM4 method; (e) Snake method; (f) manual segmentation

Download full size

Fig. 2. Reconstruction results of the new grids obtained by different methods and the original grid. (a) ASM1 method; (b) ASM2 method; (c) ASM3 method; (d) ASM4 method; (e) Snake method; (f) original grid

Download full size

Table 1. Optical parameters of digital mouse modelmm-1
View table
Table 1. Optical parameters of digital mouse modelmm-1
Organ μ_ax μ_sx μ_am μ_sm
Muscle 0.0052 1.08 0.0068 1.03
Heart 0.0083 1.01 0.0104 0.99
Lung 0.0133 1.97 0.0203 1.95
Liver 0.0329 0.70 0.0176 0.65
Kidney 0.0660 2.25 0.0380 2.02
Stomach 0.0114 1.74 0.0070 1.36

Table 2. Accuracy of segmentation based on active shape models and Snake model
View table
Table 2. Accuracy of segmentation based on active shape models and Snake model
Method Dice coefficient Hausdorff distance /mm
ASM1 0.80 0.98
ASM2 0.86 0.52
ASM3 0.89 0.41
ASM4 0.90 0.30
Snake 0.84 0.78

Table 3. Reconstruction results

View table

Table 3. Reconstruction results

Method	$\begin{matrix} {d_{f}}_{} \end{matrix}$ /mm	Reconstructed density /(nW·mm^-3)	Number of nodes	Number of tetrahedrons
ASM1	3.85	2.86×10^-2	3878	18852
ASM2	2.33	3.19×10^-2	3926	19099
ASM3	1.96	3.18×10^-2	3851	18636
ASM4	1.75	3.03×10^-2	3917	19011
Snake	2.92	2.97×10^-2	3872	18767
Original	1.70	3.13×10^-2	3823	18504

Tools

Get Citation

Copy Citation Text

Yuqing Hou, Haowen Hu, Fengjun Zhao, Xuelei He, Huangjian Yi, Xiaowei He. Influence of Active Shape Model Segmentation Method on Optical Reconstruction[J]. Acta Optica Sinica, 2018, 38(2): 0211001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites