Objectives The incidence and mortality of cervical cancer are high in Poland. There are effective methods of the prevention and the early diagnosis however, they require well-trained medical professionals. Within this project, we built a prototype of a new device together with implemented software, to convert the currently used microscopes, to fully independent scanning systems for cytological samples. The device is intended to improve the effectiveness of cytological screening and registration of cytological tests’ results. The features of the software include digital backup, transmission and telemedicine evaluation.

Methods The software uses the artificial neural network (U-NET) designed to recognize suspicious regions and enhanced CNN neural network, allowing to determine the type of disorder such as: ASCUS, ASC-H, HIS, AGC, cancer. 7128 liquid based cytology (LBC) samples were evaluated by cyto-sreeners. Cytological abnormalities: ASCUS, ASC-H, HIS, AGC, cancer were found in 254 (3.6%) cases. All samples were scanned and archived. Selected samples with diagnosed abnormality, were a model to teach U-NET/CNN.

Results During LBC screening tests (distinguishing between positive and negative results) a 99,6% efficiency compliance with results obtained using standard methods were achieved. There were no positive results misinterpreted. In the field of distinguishing cytological abnormalities: ASCUS, ASC-H, HIS, AGC, CA - 95,72% efficiency was achieved.

Conclusions The obtained results indicate high efficiency of the artificial neural networks, in supporting diagnosticians. The use of U-NET/ANN is a promising for increasing the effectiveness of cervical screening. The low cost of neural networks usage increases the potential areas of application of the presented method.