Article Text

Download PDFPDF

265 Evaluation of the constructed the device along with the software for digital archiving, sending the data and supporting the diagnosis of cervical cancer
  1. J Gronwald1,
  2. Ł Lasyk2,
  3. J Barbasz3,
  4. A Prusaczyk4,
  5. P Żuk4,
  6. T Włodarczyk2,
  7. E Prokurat4,
  8. W Olszewski5 and
  9. M Bidziński6
  1. 1Pomeranian Medical University, Department of Genetics and Pathology, Szczecin, Poland
  2. 2Digitmed Sp. z o.o., Department of Research and Development, Oleśnica, Poland
  3. 3Polish Academy of Sciences, Institute of Catalysis and Surface Chemistry, Kraków, Poland
  4. 4Medical and Diagnostic Center Sp. z o.o., Department of Research and Development, Siedlce, Poland
  5. 5Maria Skłodowska-Curie Institute Oncology Center, Department of Pathology, Warsaw, Poland
  6. 6Maria Skłodowska-Curie Institute Oncology Center, Department of Gynecological Oncology, Warsaw, Poland


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.

Statistics from

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.