Automated cell nuclei segmentation from microscopic images of cervical smear

Malignant tumor, also known as carcinoma, is the first top 10 causes of death in which the cervical carcinoma is the top 5 common cancer of women. With the popularization of Pap test, the rank of cervical carcinoma has a declining trend. The prevention of cervical carcinoma depends on early detection and treatment. Pap test is the most effective method for early screening. With the increase of the screening rate, there were more and more workload to the doctors and medical staff. Subjective view, heavy duty and overworked were causing the mistakes of the screening. Therefore, the automatic computer-aided system for Pap test is the new trend to solve it. In this paper, we used the Bethesda system, a system for reporting cervical or vaginal cytological diagnoses, as the basis of screening, and image processing and computer vision method are applied to retrieve the feature of abnormal cells. Carcinoma cell nucleus segmentation is the key step to automated screening system for Pap test of cervical smear. In this study, we segment the cell of smear image into nucleus and cytoplasm in HSV color space. The color representation of smear image is first transformed from RGB to HSV, and image noise is removed by medium filtering. Then, cell nucleus and cytoplasm can be segmented from image background by color clustering. From the experiments, it is proved that the proposed method is efficient and successful.