Title :
A deformable model for human organ extraction
Author :
Gao, Jean ; Kosaka, Akio ; Kak, Avi
Author_Institution :
Sch. of Electr. & Comput. Eng., Purdue Univ., West Lafayette, IN, USA
Abstract :
We present a modification of the well-known snakes algorithm for extracting contours in noisy images. Our modification addresses the issues of selection of the control points on an estimate of the contour and the determination of the weighting coefficients. The weighting coefficients are determined dynamically on the basis of the distance between the control points and the local curvature of the contour. We show results obtained in extracting the liver from cross-sectional images of the abdomen
Keywords :
edge detection; feature extraction; image segmentation; liver; medical image processing; noise; abdomen; contour estimation; contours extraction; control points distance; control points selection; cross-sectional images; deformable model; edge detection; human organ extraction; image segmentation; liver; local curvature; noisy images; snakes algorithm; weighting coefficients; Abdomen; Automatic control; Computed tomography; Deformable models; Hepatectomy; Humans; Image segmentation; Liver; Markov random fields; Metastasis;
Conference_Titel :
Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on
Conference_Location :
Chicago, IL
Print_ISBN :
0-8186-8821-1
DOI :
10.1109/ICIP.1998.999022
