COMPUTER-ASSISTED CERVICAL-CANCER SCREENING USING NEURAL NETWORKS

A practical and effective system for the computer-assisted screening o f conventionally prepared cervical smears is presented and described. Recent developments in neural network technology have made computerize d analysis of the complex cellular scenes found on Pap smears possible . The PAPNET(R) Cytological Screening System uses neural networks to a utomatically analyze conventional smears by locating and recognizing p otentially abnormal cells. It then displays images of these objects fo r review and final diagnosis by qualified cytologists. The results of the studies presented indicate that the PAPNET system could be a usefu l tool for both the screening and rescreening of cervical smears. In a ddition, the system has been shown to be sensitive to some types of ab normalities which have gone undetected during manual screening.