Counting touching cell nuclei using fast ellipse detection to assess in vitro cell characteristics: a feasibility study

In this article, we describe a new image analysis software that allows rapid segmentation and separation of fluorescently stained cell nuclei using a fast ellipse detection algorithm. Detection time ranged between 1.84 and 3.14 s. Segmentation results were compared with manual evaluation. The achieved over-segmentation rate was 0.11 (0.1 double counts and 0.01 false positive detections), and the under-segmentation rate was of 0.03 over all images. We demonstrate the applicability of the proposed algorithm to automated counting of fluorescent-labeled cell nuclei and to tissue characterization. Moreover, the performance of the proposed algorithm is compared with preexisting automated image analysis techniques described by others.

Brullmann, D., A. Pabst, K. Lehmann,T. Ziebart, M. Klein, B. d'Hoedt

Clinical Oral Investigations

16 (1)





(USA): 800-640-6380
(Intl): +001-607-272-5070