Automatic detection of antinuclear autoantibodies cells in indirect immunofluorescence images

Indirect immunofluorescence (IIF) with HEp-2 cells is used for the detection of antinuclear autoantibodies (ANAs) in systemic autoimmune diseases. The ANA testing allows to scan a broad range of autoantibody entities and to describe them by distinct fluorescence patterns. The identification of patterns has recently by a human inspecting the slides with a microscope. The lacking automation of this technique has resulted in the development of alternative techniques based on chemical reactions, which have not the discrimination power of the ANA testing. An automatic system would pave the way for a wider use of ANA testing. An automatic inspection system for ANA testing can be divided into HEp-2 cell detection, fluorescence pattern classification and computer-aided diagnosis phases. This study focused on the first phase of cell detection that utilized the circle Hough transformation to separate connected cell in IIF images. The proposed method evaluated 7614 cells with six distinct fluorescence patterns from 113 images. Such a method provided a robust and fast automatic segmentation of HEp-2 fluorescent patterns in ANA testing.