Authors:
Sebastijan Šprager
;
Boris Cigale
and
Damjan Zazula
Affiliation:
Faculty of Electrical Engineering and Computer Science, Slovenia
Keyword(s):
Medical image processing, 3D ultrasound volume, Ovarian follicle, Image registration, Ovarian follicle growth assessment.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computer Vision, Visualization and Computer Graphics
;
Medical Image Detection, Acquisition, Analysis and Processing
Abstract:
In this paper, a method for assessment of the ovarian follicle growth is presented. 3D ultrasound volumes of ovaries are processed. Ovarian follicles are shown as hypoechogenic areas in the cross-section images. In first phase, global translations and rotations of two observed follicle constellations from two consecutive ovary examinations are detected. In second phase, detailed local deformations are estimated using elastic registration. The proposed method has been tested using artificial simulated models of ultrasound images of ovaries. Preliminary results shows the proposed method is efficient and reliably detects deformations ovarian follicles cause by their growth.