Automated follicle segmentation in ultrasound scans of bovine ovaries

Issue title: Selected Papers from the 13th International Symposium on Applied Electromagnetics and Mechanics (ISEM 2007)

Article type: Research Article

Authors: VanderLaan, Donald J.^a | Khurshid, Khawar^a | Ireland, James J.^b | Jimenez-Krassel, Fermin^b | McGough, Robert J.^{a; *}

Affiliations: [a] Department of Electrical and Computer Engineering, 2120 Engineering Building, Michigan State University, East Lansing, MI 48824-1226, USA | [b] Department of Animal Science, 1290 Anthony Hall, Michigan State University, East Lansing, MI 48824-1226, USA

Correspondence: [*] Corresponding author. E-mail: [email protected]

Abstract: Important reproductive information can be determined by analyzing the follicles in an ultrasound scan of the ovary. The currently used process requires an expert to manually mark and measure the size of the follicles. Manual analysis is time-consuming and often conflicting. A robust computer assisted approach to automatically detect and quantify follicles would improve both the efficiency and accuracy of the process. The multi-step algorithm presented involves coarse ovarian segmentation, follicle detection, and post processing using level sets to automatically determine follicle boundaries. In comparison with expert evaluations, experiments on bovine ovarian images show encouraging results. The algorithm correctly detected approximately 65% of the ovarian follicles.

Keywords: Ultrasound, segmentation, active contours, level sets

DOI: 10.3233/JAE-2008-955

Journal: International Journal of Applied Electromagnetics and Mechanics, vol. 28, no. 1-2, pp. 49-54, 2008