Nucleus Detection Using Deep Learning Approach on Pap Smear Images

Cervical cancer is caused by the abnormal growth of female cervix cells. It is one of the most familiar factors for women's death worldwide. Therefore., early detection of cervical cancer leads to a reduced mortality rate and increased chance of being alive. The Papanicolaou is a common method for screening and identifying the cancerous cells in a woman's cervix. The resultant pap smear images may help the physician diagnose the cervix cells. The crucial part of the cell is the nucleus. Therefore., auto-detection of the nucleus is the core point in this paper. A deep learning algorithm is employed to segment the nucleus in pap smear images. Two network structures., known as ResNet18 and ResNet50., are exploited to detect the nucleus part in the cell. The results are compared with ground truth and between the two structures. Both networks., ResNet18 and ResNet50., perform almost the same., with test accuracy reaching 92%. This work distinguishes it from other work in simplicity., fast., and accuracy. Therefore., it can be recommended to be used in clinical units and rural countries which suffer from the lack of specialist physician.