작성자 M.I.D
[논문] Improvement of snake model for ventricle segmentation in MRI
본문
Improvement of snake model for ventricle segmentation in MRI
(뇌실 분할방법 연구)
IEICE technical report
IEICE technical report 108(385), 165-168, 2009-01-12
The Institute of Electronics, Information and Communication Engineers
Choi Seokyoon / Dept. of Medical Engineering, Korea University, Kim Hochul / Dept. of Electronics&Information Engineering, Korea University, Choi Khanghee / Dept. of Electronics&Information Engineering, Korea University, Kim Mingi / Dept. of Electronics&Information Engineering, Korea University
The purpose of our study is ventricle segmentation in MRI. segmentation subdivided an image into its consistency regions or objects. the level detail to which the subdivision is carried depends on the being solved. segmentation should stop when the objects or region of interest in an application have been detected. Active contours, or snakes, are used extensively in computer vision and image processing applications, particularly to locate object boundaries. the most representative algorithm is gradient vector fow (GVF). Our proposed algorithm is new type of external energy of GVF for exact segmentation. experiments show good performance of corpus callosum segmentation in MRI. The results can be quantitative analyzed.
(뇌실 분할방법 연구)
IEICE technical report
IEICE technical report 108(385), 165-168, 2009-01-12
The Institute of Electronics, Information and Communication Engineers
Choi Seokyoon / Dept. of Medical Engineering, Korea University, Kim Hochul / Dept. of Electronics&Information Engineering, Korea University, Choi Khanghee / Dept. of Electronics&Information Engineering, Korea University, Kim Mingi / Dept. of Electronics&Information Engineering, Korea University
The purpose of our study is ventricle segmentation in MRI. segmentation subdivided an image into its consistency regions or objects. the level detail to which the subdivision is carried depends on the being solved. segmentation should stop when the objects or region of interest in an application have been detected. Active contours, or snakes, are used extensively in computer vision and image processing applications, particularly to locate object boundaries. the most representative algorithm is gradient vector fow (GVF). Our proposed algorithm is new type of external energy of GVF for exact segmentation. experiments show good performance of corpus callosum segmentation in MRI. The results can be quantitative analyzed.