Comparative analysis of nucleus segmentation techniques for malignancy detection of pap smear cervical cells

Pap smear is a microscopic screening process of cervical smear used to detect pre-cancerous and cancerous cells in the cervix region. Cell nuclei segmentation is one of the most significant task in cervical cell image analysis which aids in identifying the different stages of cervical cancer like mild, moderate, severe and carcinoma. Nucleus is the bio-marker which assist in identifying the malignancy of the cervical cell and the numerous literature clearly revealed the importance of nucleus shape, size and texture which enormously assist in identifying the normal and abnormal cells as the appearance of the nucleus of normal cell vary in size, shape and texture as it progresses from benign to malignancy. The main objective of this paper is to compare the different standard segmentation techniques like fuzzy C-means clustering, region based active contours and particle swarm optimization to extract nucleus feature. The statistical measures like precision, sensitivity (recall), specificity and accuracy are calculated and the performance of the extracted nuclei feature is compared with the standard benchmark Herlev database of Pap smear images.