AUTOMATED COUNTING OF SQUAMOUS EPITHELIAL CELLS IN LIQUID-BASED CYTOLOGY SAMPLES

Abstract

Cytologic screening is only effective with adequate material. The Bethesda System (TBS), an international system for standardizing the results of cervical cytology, establishes criteria for adequacy. According to the TBS, a sample prepared by liquid-based cytology (LBC) can be classified as adequate if it contains not less than 5,000 squamous epithelial cells. There are methods of manual assessment of the cellularity of cytological samples. However, the uniformity of cellular material distribution of LBC samples makes possible the application of automatic tools for assessing the adequacy of the material based on the cellularity criterion. This paper compares the results of digital LBC samples adequacy assessment using the automated artificial neural network method Vision Cyto Pap and the manual assessment method. Analysis of the results of counting squamous epithelial cells in 506 LBC samples showed a significant correlation (r = 0.93) between the automated and manual method. The high diagnostic parameters (sensitivity = 93.8 % and specificity = 99.2 %) of the automated Vision Cyto Pap method allow to conclude that the algorithms of such a tool can be used to determine the adequacy of the cytological material by the number of squamous epithelium cells with sufficient reliability.