Please use this identifier to cite or link to this item:
Title: Segmentation of magnetic resonance images of the spine
Authors: YUAN YI
Keywords: iterative, double-front, level set, weighted, leaking, initialized
Issue Date: 20-Sep-2005
Citation: YUAN YI (2005-09-20). Segmentation of magnetic resonance images of the spine. ScholarBank@NUS Repository.
Abstract: It is much easier to get precise segmentation of CT images than of MR images. Both CT and MR scans need to be obtained of a patient for the spinal surgery. Therefore the CT segmentation results can be good initialization for the MRI segmentation. Then the MRI segmentation results would be registered to the segmented CT, which is used as reference. Resampling the MR images after translation and rotation can make the initial CT surface match the MR surface better. This iterative process is carried on until the CT surface matches the target MR surface accurately. At this stage, the CT and the MR scans have been precisely registered as we desire. The segmentation with an initialization process is much faster than a non-initialized one in that the search area is significantly reduced. The feedback process helps to prevent the registration from being stuck in a local minimum.
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Thesis_YuanYi.pdf6.02 MBAdobe PDF



Page view(s)

checked on Apr 12, 2019


checked on Apr 12, 2019

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.