Estimation of a point along overlapping cervical cell nuclei in Pap smear image using colour space conversion

Abstract

The identification of normal and abnormal cells is considered as one of the most challenging task for computer assisted Pap smear analysis system especially when abnormal cells are hidden behind overlapped cells. The complexity of the problem depends on whether only cytoplasm of two cells are overlapped, or only nuclei are overlapped with disjoint cytoplasm, and in some case both cytoplasm and nuclei are overlapped. Sometimes, Pap smear sample contains mixture of cells with disjoint/overlapped cytoplasm and nuclei. Hence, there is need for algorithm which segments cells from the cluster of overlapped cells. In case of overlapped nuclei, identifying the point of overlapping accurately is one of the significant steps in segmenting overlapped cells. This paper discusses image processing-based method which segment disjoint nuclei and identifies the point of intersection called as concavity point in the cluster of cells where only nuclei are overlapped.