Title: Automated ovarian classification in digital ultrasound images

Authors: P.S. Hiremath; Jyothi R. Tegnoor

Addresses: Department of Studies and Research in Computer Science, Gulbarga University, Gulbarga, 585106, Karnataka, India ' Department of Studies and Research in Computer Science, Gulbarga University, Gulbarga, 585106, Karnataka, India

Abstract: Knowledge about the status of the female reproductive system is important for addressing fertility problems and age-related family planning. Transvaginal ultrasound imaging of the follicles in the ovary gives important information about the ovarian ageing, i.e. number of follicles, size, position and response to hormonal stimulation. Manual analysis of follicles is laborious and error-prone. In this paper, a novel method for automated classification of the ovaries in digital ultrasound images is proposed which employs the contourlet transform for pre-processing, active contours without edge for segmentation and fuzzy logic for classification. Further, upon the detection of the follicles, the ovary is classified as normal, cystic and polycystic, on the basis of two parameters, namely, the number and the size of follicles in an ovary. The experimental results are compared with inferences drawn by medical expert and demonstrate the efficacy of the method.

Keywords: ovarian follicles; active contours; cystic; polycystic; fuzzy logic; ovarian classification; digital ultrasound images; female reproductive system; transvaginal ultrasound imaging; automated classification; ovaries; contourlet transform.

DOI: 10.1504/IJBET.2013.053709

International Journal of Biomedical Engineering and Technology, 2013 Vol.11 No.1, pp.46 - 65

Published online: 27 Sep 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article