Author/Editor		Cigale, Boris; Zazula, Damjan
Title		Segmentation of 3D ovarian ultrasound volumes using continuous wavelet transform
Type		članek
Source		In: Jarm T, Kramar P, Zupanič A, editors. Medicon 2007. IFMBE proceedings from the 11th Mediterranean conference on medical and biological enginering and computing; 2007 Jun 26-30; Ljubljana. New York: Springer,
Publication year		2007
Volume		str. 1017-20
Language		eng
Abstract		A novel algorithm for the segmentation of 3D ul-trasound images of ovary is presented in this paper. The algo-rithm is based on continuous wavelet transform (CWT) and consists of two consecutive steps. In the first step, the centers of follicles are determined by tracing the local maxima from higher tolower scale in the wavelet transform of input images. The center of follicle appears as local maximum near value O when the size of the follicle corresponds to the scale of CWT. In the second step, the shape of the follicleis outlined. This is done by casting the rays in different directions from the center of the follicle in order to find its border. The position of border is connected with the wavelet scale and the position of the first localminimum on each ray. The method was tested on a small set of real 3D ultrasound images. The resuIts were evaluated visually, since we do not have manually annotated images.