Diagnosis of recurrent miscarriage due to abnormally high number of uterine natural killer (uNK) cells has recently been made possible by a protocol devised by Quenby et al. Hum Reprod 2009;24(1):45-54. The diagnosis involves detection and counting of stromal and uNK cell nuclei in endometrial biopsy slides immunohistochemically stained with haematoxylin for staining cell nuclei and CD56 as a marker for the uNK cells. However, manual diagnosis is a laborious process, fraught with subjective errors. In this paper, we present a novel method for detection of uterine natural killer (uNK) cells in the human female uterus lining and localisation of the luminal epithelium edge in endometrial biopsies. Specifically, we employ a local phase symmetry based method to detect stromal cell nuclei and propose an adaptive background removal method that significantly eases the segmentation of uNK cell nuclei regions. We also propose a novel method using alpha shapes for the identification of epithelial cell nuclei and B-Spline curve fitting on identified cell nuclei to localise the luminal epithelium edge. The objective of edge localisation is to avoid cell nuclei near the luminal epithelium edge being counted in the diagnosis process due to their non-relevance to the calculation of stromal to uNK cell ratio that determines the diagnosis of recurrent miscarriages in the end. The resulting algorithm offers a promising potential for computer-assisted diagnosis of recurrent miscarriage due to its high accuracy.
Keywords: Luminal epithelium edge localisation; Stained background removal; Stromal and uNK cell nuclei detection.
Copyright © 2014 Elsevier Ltd. All rights reserved.