Limits...
Automatic Liver Segmentation on Volumetric CT Images Using Supervoxel-Based Graph Cuts.

Wu W, Zhou Z, Wu S, Zhang Y - Comput Math Methods Med (2016)

Bottom Line: Despite many years of research, automatic liver segmentation remains a challenging task.Thirty abdominal CT images were used to evaluate the accuracy and efficiency of the proposed algorithm.Experimental results show that the proposed method can detect the liver accurately with significant reduction of processing time, especially when dealing with diseased liver cases.

View Article: PubMed Central - PubMed

Affiliation: College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China.

ABSTRACT
Accurate segmentation of liver from abdominal CT scans is critical for computer-assisted diagnosis and therapy. Despite many years of research, automatic liver segmentation remains a challenging task. In this paper, a novel method was proposed for automatic delineation of liver on CT volume images using supervoxel-based graph cuts. To extract the liver volume of interest (VOI), the region of abdomen was firstly determined based on maximum intensity projection (MIP) and thresholding methods. Then, the patient-specific liver VOI was extracted from the region of abdomen by using a histogram-based adaptive thresholding method and morphological operations. The supervoxels of the liver VOI were generated using the simple linear iterative clustering (SLIC) method. The foreground/background seeds for graph cuts were generated on the largest liver slice, and the graph cuts algorithm was applied to the VOI supervoxels. Thirty abdominal CT images were used to evaluate the accuracy and efficiency of the proposed algorithm. Experimental results show that the proposed method can detect the liver accurately with significant reduction of processing time, especially when dealing with diseased liver cases.

No MeSH data available.


Related in: MedlinePlus

An example of the 3D abdominal region extraction. (a) Coronal MIP image. (b) The binary bone mask of (a). (c) The processed binary mask. Blue line shows the position of spine. Red and green lines show the lower and upper bounding along z-axis, respectively. Yellow lines are corresponding to the in-plane bounding box in (f). (d) Axial MIP image. (e) The binary abdomen mask of (d). (f) The processed binary mask. Yellow rectangle shows the in-plane bounding box. (g) The extraction of lungs. (h) The binary lung mask with the largest lung region area.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4835633&req=5

fig2: An example of the 3D abdominal region extraction. (a) Coronal MIP image. (b) The binary bone mask of (a). (c) The processed binary mask. Blue line shows the position of spine. Red and green lines show the lower and upper bounding along z-axis, respectively. Yellow lines are corresponding to the in-plane bounding box in (f). (d) Axial MIP image. (e) The binary abdomen mask of (d). (f) The processed binary mask. Yellow rectangle shows the in-plane bounding box. (g) The extraction of lungs. (h) The binary lung mask with the largest lung region area.

Mentions: (1) Calculation of the Lower Bounding Coordinate Zmin. For the coronal MIP image Mcoronal (Figure 2(a)), which had a size of ux × uz, segmentation of bones was performed using the Otsu algorithm [33] to obtain the binary bone mask Mbone (Figure 2(b)). Let ntotal denote the total number of pixels in Mbone. The number of bone pixels nb (in white color) was counted.


Automatic Liver Segmentation on Volumetric CT Images Using Supervoxel-Based Graph Cuts.

Wu W, Zhou Z, Wu S, Zhang Y - Comput Math Methods Med (2016)

An example of the 3D abdominal region extraction. (a) Coronal MIP image. (b) The binary bone mask of (a). (c) The processed binary mask. Blue line shows the position of spine. Red and green lines show the lower and upper bounding along z-axis, respectively. Yellow lines are corresponding to the in-plane bounding box in (f). (d) Axial MIP image. (e) The binary abdomen mask of (d). (f) The processed binary mask. Yellow rectangle shows the in-plane bounding box. (g) The extraction of lungs. (h) The binary lung mask with the largest lung region area.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4835633&req=5

fig2: An example of the 3D abdominal region extraction. (a) Coronal MIP image. (b) The binary bone mask of (a). (c) The processed binary mask. Blue line shows the position of spine. Red and green lines show the lower and upper bounding along z-axis, respectively. Yellow lines are corresponding to the in-plane bounding box in (f). (d) Axial MIP image. (e) The binary abdomen mask of (d). (f) The processed binary mask. Yellow rectangle shows the in-plane bounding box. (g) The extraction of lungs. (h) The binary lung mask with the largest lung region area.
Mentions: (1) Calculation of the Lower Bounding Coordinate Zmin. For the coronal MIP image Mcoronal (Figure 2(a)), which had a size of ux × uz, segmentation of bones was performed using the Otsu algorithm [33] to obtain the binary bone mask Mbone (Figure 2(b)). Let ntotal denote the total number of pixels in Mbone. The number of bone pixels nb (in white color) was counted.

Bottom Line: Despite many years of research, automatic liver segmentation remains a challenging task.Thirty abdominal CT images were used to evaluate the accuracy and efficiency of the proposed algorithm.Experimental results show that the proposed method can detect the liver accurately with significant reduction of processing time, especially when dealing with diseased liver cases.

View Article: PubMed Central - PubMed

Affiliation: College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China.

ABSTRACT
Accurate segmentation of liver from abdominal CT scans is critical for computer-assisted diagnosis and therapy. Despite many years of research, automatic liver segmentation remains a challenging task. In this paper, a novel method was proposed for automatic delineation of liver on CT volume images using supervoxel-based graph cuts. To extract the liver volume of interest (VOI), the region of abdomen was firstly determined based on maximum intensity projection (MIP) and thresholding methods. Then, the patient-specific liver VOI was extracted from the region of abdomen by using a histogram-based adaptive thresholding method and morphological operations. The supervoxels of the liver VOI were generated using the simple linear iterative clustering (SLIC) method. The foreground/background seeds for graph cuts were generated on the largest liver slice, and the graph cuts algorithm was applied to the VOI supervoxels. Thirty abdominal CT images were used to evaluate the accuracy and efficiency of the proposed algorithm. Experimental results show that the proposed method can detect the liver accurately with significant reduction of processing time, especially when dealing with diseased liver cases.

No MeSH data available.


Related in: MedlinePlus