Colour Contrast Enhancement on Preselected Cervical Cell for ThinPrep® Images

ThinPrep^reg monolayer cytology was introduced to overcome the limitations of conventional Pap smear test for screening of cervical cancer. The cytological features in ThinPrep^reg images could be improved if unwanted background information and poor contrast could be eliminated. This study proposes a contrast enhancement technique, which is only applied on the cervical cell of interest. The proposed technique is divided into two stages. Firstly, the cervical cells of interest will be selected using the modified seed based region growing algorithm. Then, the contrast of cervical cell of interest in the ThinPrepreg will be enhanced by using three contrast enhancement algorithms. The cervical cell of interest will be applied with linear contrast algorithm and the proposed nonlinear algorithms namely non-linear bright and nonlinear dark contrast to enhance the contrast of the ThinPrepreg images. The results show that the proposed technique improves the image quality. Hence, the resultant image would be rendered more useful for further analysis by pathologists.