Title :
Automatic segmentation of hippocampus from brain MRI using deformable contours
Author :
Ghanei, A. ; Soltanian-Zadeh, Hamid ; Windham, Joe P.
Author_Institution :
Lab. of Med. Image Anal., Henry Ford Hospital, Detroit, MI, USA
Abstract :
The application of deformable contours for segmentation of the hippocampus has been investigated. Common problems of dynamic contours in this case and cases like this have been discussed and solved. A new method for extracting the discontinuous boundary of a structure with multiple unwanted edges near it has been developed. The method is based on detecting and following the edge by external forces. The final oscillation of the contour has been remedied by using interpolation of external energy and limiting the movements of the contour. Also, the problem of optimizing the weights has been overcome by making them dependent on the amount of forces
Keywords :
biomedical NMR; brain; edge detection; image segmentation; interpolation; medical image processing; automatic segmentation; brain MRI; contour movements limitation; deformable contours; discontinuous boundary; dynamic contours; external energy interpolation; hippocampus; magnetic resonance imaging; medical diagnostic imaging; multiple unwanted edges; Biomedical imaging; Clocks; Geometry; Hippocampus; Image edge detection; Image segmentation; Laboratories; Magnetic resonance imaging; Shape; Solid modeling;
Conference_Titel :
Image Processing, 1996. Proceedings., International Conference on
Conference_Location :
Lausanne
Print_ISBN :
0-7803-3259-8
DOI :
10.1109/ICIP.1996.560761
