Abstract :
The automation edge extraction of glomerulus is an important step for analyzing kidney-tissue image in the computer aided diagnosis system of kidney disease. According to the characteristic of these medical images, this paper proposes a glomerulus extraction method based on wavelet transformation and watershed algorithm. First, a LOG filter is applied to the low-resolution image, which corresponds to low frequency sub band after wavelet transformation, so that rough edge information can be obtained. After labeling to remove the noises and thinning, a genetic algorithm is applied to search the best fitting curve, which determines the barycenter position of glomerulus and sets this barycenter as seed. Secondly, the image which contains complete object boundary can be obtained through watershed transform, after region growing operation, glomerulus region can be extracted. With abundant samples, experimental result indicates our method can extract the glomerulus from kidney-tissue image both accurately and availably.
Keywords :
biological tissues; biomedical imaging; diseases; edge detection; feature extraction; filtering theory; genetic algorithms; image denoising; image segmentation; image thinning; kidney; medical image processing; wavelet transforms; LOG filter; automation edge extraction; computer aided diagnosis system; genetic algorithm; glomerulus region; image thinning; kidney disease; kidney-tissue image analysis; medical image segmentation; noise removal; region growing operation; rough edge information; watershed algorithm; wavelet transformation; Automation; Biomedical imaging; Data mining; Diseases; Frequency; Image analysis; Image segmentation; Information filtering; Information filters; Medical diagnostic imaging; Glomerulus; genetic algorithm; watershed algorithm; wavelet transformation;
