Development of image processing algorithm for cytological diagnosis of uterine cervical cancer tissue examination

In this study is relevant to cell area extraction for cytological diagnosis of liquid-based cell examination being used for early diagnosis of uterine cervical cancer by utilizing image processing. As existing cytological diagnosis process has been performed manually by cytotechnologist, the amount of cell image that could be processed was limited. Therefore, in this study, cellular domain extraction through which automatic processing of cytological diagnosis process is enabled was performed and its condition was established depending on the size of cell nucleus based on cytological diagnosis standard of uterine cervical cancer cell. Obtained cell image was processed by hough transform matching with cell image by using matlab through preprocessing phase. As a result, 28 sample images among total 30 sample images were succeeded in finding out target cell and two sample images failed to find it. In the future, modification and verification for such failure case may be required to be performed. It is expected that the result of this study could be utilized for diagnosis process automation of liquid-based cell examination.