Computer-Aided Diagnosis (CAD) for Cervical Cancer Screening and Diagnosis: A New System Design in Medical Image Processing

摘要

Uterine cervical cancer is the second most common cancer among women worldwide. Physicians visually inspect the cervix for certain distinctly abnormal morphologic features that indicate precursor lesions and invasive cancer. We introduce our vision of a Computer-Aided-Diagnosis (CAD) system for cervical cancer screening and diagnosis and provide the details of our system design and development process. The proposed CAD system is a complex multi-sensor, multi-data and multi-feature image analysis system. The feature set used in our CAD systems includes the same visual features used by physician and could be extended to new features introduced by new instrument technologies, like fluorescence spectroscopy. Preliminary results of our research on detecting the three most important features: blood vessel structures, acetowhite regions and lesion margins are shown.