Automated Diagnosis and Classification of Cervical Cancer from pap-smear Images

Abstract

Globally, cervical cancer ranks as the fourth most prevalent cancer affecting women. However, cervical cancer can be treated if detected at an early stage. Pap-smear is a good tool for screening of cervical cancer but the manual analysis is error-prone, tedious and time-consuming. The objective of this study was to rule out these limitations by automating the process of cervical cancer classification from pap-smear images by using an enhanced fuzzy c-means algorithm. Simulated annealing coupled with a wrapper filter was used for feature selection. The evaluation results showed that our method outperforms many of previous algorithms in classification accuracy (99.35%), specificity (97.93%) and sensitivity (99.85%), when applied to the Herlev benchmark pap-smear dataset. The overall accuracy, sensitivity and specificity of the classifier on prepared pap-smear slides was 95.00%, 100% and 90.00% respectively. False Negative Rate (FNR), False Positive Rate (FPR) and classification error of 0.00%, 10.00% and 5.00% respectively were obtained. The major contribution of this tool in a cervical cancer screening workflow is that it reduces on the time required by the cytotechnician to screen very many pap-smears by eliminating the obvious normal ones, hence more time can be put on the suspicious slides. The proposed tool has the capability of analyzing 1-2 smears per minute as opposed to the 5-10 minutes per slide in the manual analysis.