Neural network processing can provide means to catch errors that slip through human screening of pap smears

The problem of the false-negative smear deserves the attention of the cytologic community. We found that by using the PAPNET system, equipped with neural network programming, cancer cells can be detected in repeatedly misdiagnosed Pap smears. The correct diagnosis of these false-negative smears depended on the skills of the diagnostician to recognize the cells on one or more of the 128 tiles of the video display as abnormal, and to make the proper decision when to turn to light microscopy. In 8 of the 10 tested false-negative smears, the cancer cells were found exclusively in epithelial fragments; in two cases there were no more than five abnormal cells in the smear (which were detected by PAPNET). This study gave us insight into the nature of the false-negative problem and showed us that the application of neural network processing can provide means to catch errors that slip through human screening of Pap smears.