DocumentCode :
2973286
Title :
A deformable region model for locating the boundary of brain tumor
Author :
Zhu, Hui ; Chan, Francis H Y ; Lam, F.K. ; Poon, Paul W F
Author_Institution :
Dept. of Electr. & Electron. Eng., Hong Kong Univ., Hong Kong
Volume :
1
fYear :
1995
fDate :
20-25 Sep 1995
Firstpage :
411
Abstract :
We propose a new deformable region model to represent a brain tumor in MRI, and use a shrinking-growing method to locate its boundary from a designated initial plan. The shrinking-growing process maximizes the area of an object under the condition that the object and its boundary have the same gray level distributions. Compared to the deformable contour models (also called active contour model, or snake), our method dose not require the initial plan to be in as close proximity to the boundary as in contour models
Keywords :
biomedical NMR; brain; edge detection; iterative methods; medical image processing; MRI; brain tumor boundary location; deformable region model; gray level distributions; initial plan; shrinking-growing method; Active contours; Biomedical imaging; Brain modeling; Deformable models; Design engineering; Image segmentation; Neoplasms; Physiology; Pixel; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Engineering in Medicine and Biology Society, 1995., IEEE 17th Annual Conference
Conference_Location :
Montreal, Que.
Print_ISBN :
0-7803-2475-7
Type :
conf
DOI :
10.1109/IEMBS.1995.575175
Filename :
575175
Link To Document :
بازگشت