
The PAPNET System is the only device with a neural-network-based-artificial intelligence to detect and show the images of abnormal cells on the monitor to be evaluated in an interactive way. We effectively used the PAPNET in rescreening of conventional cervical smears and we detected its advantages and its disadvantages. In this paper, we report our results from PAPNET-assisted primary screening performed on 20,154 conventional smears. The smears were classified as Negative or as Review. The Negative cases were rapidly rescreened mainly near the coverslip edges, which are the slide areas not analyzed by automated devices because of focusing problems. The Review cases were fully reanalyzed by the optic microscope. In summary, 140 positive smears were detected: 57 cases showed changes due to HPV, 63 LSIL, 15 HSIL, and 5 carcinomas. Therefore, the PAPNET System was confirmed as useful in primary screening of conventional cervical samples as well as rescreening.
Vaginal Smears, Papillomavirus Infections, Reproducibility of Results, Uterine Cervical Neoplasms, Adenocarcinoma, Tumor Virus Infections, Italy, Carcinoma, Squamous Cell, Humans, Mass Screening, Female, Neural Networks, Computer, Papillomaviridae
Vaginal Smears, Papillomavirus Infections, Reproducibility of Results, Uterine Cervical Neoplasms, Adenocarcinoma, Tumor Virus Infections, Italy, Carcinoma, Squamous Cell, Humans, Mass Screening, Female, Neural Networks, Computer, Papillomaviridae
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 15 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Top 10% | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
