Automatic analysis of immunofluorescence patterns of HEp-2 cells

Abstract

The standard screening test for the recognition of autoimmune diseases is the proof of autoantibodies in serum of patients by indirect immunofluorescence (IIF) based on HEp-2 cells. Manual evaluation of this test is very subjective, slow, and there are no objective parameters as guidelines available. Interlaboratory tests showed occasionally large deviations in the test evaluation resulting in a high variance of results. The aim of this project is fast, objective, safe, and economical automatic analysis of HEp-2 IIF patterns. Images of IIF patterns were completely and automatically captured using an inverse motorized fluorescence microscope. Thereby, device-specific parameters were controlled automatically, too. For fast analysis of IIF patterns new algorithms of image processing were developed. Artifacts were recognized and excluded from analysis by the developed software. Analysis of more than 80,000 images clearly demonstrated full automatization and fast processing of IIF patterns. Additionally serum-specific fluorescence could be easily distinguished from background. Even very weak but positive patterns can be recognized and used for diagnosis. A detailed separation into different basic patterns is possible. Objective, fast, and disease-related economical analysis of HEp-2 immunofluorescence patterns is feasible. The implemented software algorithms allowed a mathematical way of describing IIF patterns and can therefore be a useful tool for the needed standardization process.