Novel level set based statistical frameworks for segmentation of MR images

• Main Author: Mahshid Farzinfar
• Other Authors: Teoh Eam Khwang
• Format: Theses and Dissertations
• Language: English
• Published: 2012
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
• Online Access: https://hdl.handle.net/10356/50726
• Institution: Nanyang Technological University

In summary, two automated frameworks for segmentation of medical images are proposed. They are the joint curve evolution and the EM-joint shape based algorithms. In addition, the generalization of our frameworks to 3D models of multiple struc- tures. The resulting implementation is tested on a variety of studies to parceling of anatomical structures. The proposed algorithms can be used for surgery navigation and 3D visualization. They could also be applied to neuroscience studies in finding new diseases related to anatomical characteristics and the increase in reliability in diagnosing of illnesses such as schizophrenia.