Title :
Segmentation of ultrasound images by using wavelet transform
Author :
Kurnaz, M.N. ; Dokur, Z. ; Ölmez, T.
Author_Institution :
Dept. of Electron. & Commun. Eng., Istanbul Tech. Univ., Turkey
Abstract :
This paper presents a new feature extraction method for the segmentation of ultrasound images. Wavelet transform is proposed for determination of the textures in the ultrasound images. Elements of the feature vectors are formed by the wavelet coefficients at several decomposition level. In this study, incremental self-organized neural network (INeN) is proposed as the classifier. The classification performance is increased by using the wavelet transform and the INeN together.
Keywords :
biomedical ultrasonics; feature extraction; image classification; image segmentation; image texture; medical image processing; self-organising feature maps; wavelet transforms; INeN; classification performance; feature extraction; image textures; incremental self-organized neural network; segmentation; ultrasound images; wavelet transform; Artificial neural networks; Biomedical imaging; Data mining; Filters; Frequency; Image segmentation; Network topology; Neural networks; Ultrasonic imaging; Wavelet transforms;
Conference_Titel :
Engineering in Medicine and Biology Society, 2003. Proceedings of the 25th Annual International Conference of the IEEE
Print_ISBN :
0-7803-7789-3
DOI :
10.1109/IEMBS.2003.1279845
