Contributions to Colon Segmentation Without Previous Preparation in Computer Tomography Images

METHODOLOGY

METHODOLOGY

• Selecting the Volume of Interest (VOI)

• Computing the variance image 5 to 11 neighborhood size

• Defining variance threshold on the variance image

• Selecting of valid regions. Regions to characterize the matter inside colon (air and feces matter)

• Define the first advance vector, which must have the origin and end points in the two different valid and adjacent regions

• Create the explorer beam

METHODOLOGY

• Selecting the Volume of Interest (VOI)

• With the two valid regions inside the colon (air and feces matter).

• Computing the Variance Image

• 3D image computation of the mean and variance values for all the voxels inside the VOI. This procedure generates two new images

METHODOLOGY

• Defining Region Growing Threshold

• The user selects a threshold on the variance image

• The colon wall (high variance) and the different regions inside the colon (rather low variance) are clearly seen, especially those with feces matter.