Segmentation of anti-nuclear antibody images based on the watershed approach

Abstract

Fluorescence patterns at present are usually examined laboriously by experienced physicians through manually inspecting the slides with the help of a microscope. The readings in indirect immunofluorescene (IIF) usually suffer from the disadvantages such as the inter-observer variability that limits the reproducibility. This study proposes a segmented method based on the watershed algorithm to detect the edges of HEp-2 cells automatically. Experimental results show that the system has an overall correct rate of 92.81%. This system can be used as a preprocessing system for an automatic HEp-2 cells identification system.