Evaluation of an Image-based Automated Detection System in Detecting Ki67 Proliferation Index and Correlation with the Traditional Eye-Ball Method in Gastroenteropancreatic Neuroendocrine Tumors

Abstract

Objective: To design an application which can calculate Ki67 and compare its results with the traditional method in gastroenteropancreatic (GEP)-neuroendocrine tumors (NETs). Study Design: Descriptive analytical study. Place and Duration of Study: Faculties of Medicine and Technology of Mugla Sitki Kocman University between January 2015 to January 2016. Methodology: A new analyser for detecting the exact percentage of positive cells in images captured from different slides retrospectively selected from hospital records was designed and the concordance with results given by an expert pathologist was compared. Demonstrative slides from randomly selected 50 patients diagnosed as GEP-NETs were stained with Ki67 antibody; and images were captured from the hotspots. The images were then uploaded to the application of the analyser designed for detecting the percentage of Ki67-stained cells. Results: Twenty-seven male (54%) and 23 (46%) female patients with a mean age of 52.3 +/- 8.80 years were included. According to the pathologist with eye-ball method, 17 cases were grade 1 (34%), 21 cases were grade 2 (42%) and 12 (24%) cases were grade 3. By software, 8 cases were grade 1 (16%), 36 cases were grade 2 (72%) and 6 cases were grade 3 (12%). Statistical evaluation revealed a kappa value of 0.447 indicating moderate aggreement between the pathologist and the software. Conclusion: The total count of the cells both by the analyser and the pathologist were similar. However, improvements are needed to raise the precision for the detection of positive and negative tumoral cells.