Medical Image Registration at Pap Smear for Early Identification of Cervical Cancer

The complexity of the cell structure and high overlap causes poor image contrast. Complex imaging factors in lighting differences, dye concentrations, other variables such as drying air, excess blood, mucus, bacteria, or inflammation can make automatic visual interpretation more difficult. This study proposes an approach model by combining basic processing techniques deep learning for segmentation nucleus Overlap Cell Image Pap Smear Cervical Cancer patients. purpose this research is to segment increasing identification accuracy smear images on RepomedUNM public data. results have best performance seen MSE value, lowest RMSE value 0.2024253 PSNR 0.04009707 highest 65.3826018 dB. So, be used a reference identifying Nucleus Medical Registration (MIR)