A study on development of automation diagnosis of liquid based cytology

Abstract

Cervical cancer afflicts women worldwide. The patients’ mortality with cancer has been increased by changing to westernized dietary habit and lifestyle. In order to detect early cervical cancer, a liquid-based cytology (LBC) was used to examine the exfoliated cells collected from the cervix. This procedure helps to decrease the mortality rate. However, this test mostly involves manual examination by the pathologists. This procedure needs to develop more efficient tool in detecting cervical cancer which rate kept increasing. As such, this study was designed to develop some methods to increase the effectiveness of LBC. The diagnosis algorithm was also established to diagnose the processed cell images via an imaging process algorithm based on the diagnosis criteria. A cell diagnosis program based on GUI, combined with the imaging process and the diagnosis algorithms were developed to automate the test process. The results of this studies showed that this new program can be used for effective diagnosis of cervical cancer. Moreover, it was deemed to increase the precision and accuracy of diagnosis and save patient time.