Search

The indirect immunofluorescence (IIF) test with human epithelial type-2 (HEp-2) cells as substrates is the gold standard for anti-nuclear antibodies (ANA) test to diagnose autoimmune diseases. The specialists in the laboratory visually examine the specimen under microscope to recognise the staining patterns and generate the report. So ANA test is subjective and needs systemic automation for bioinformatics. In this view international benchmarking initiatives were organised by IAPR in the last six years. In this paper the state of the art on IIF HEp-2 cells classification task was analysed. This paper highlighted the original aspects with the detailed discussion of the published methods. Design choice verses performance was analysed.

ABSTRACTAntinuclear antibody (ANA) testing is best performed using the indirect immunofluorescence (IIF) method with human epithelial type-2 (HEp-2) cells as the substrate. IIF is a subjective procedure in which HEp-2 patterns are analyzed manually from the microscope. Therefore, ANA test results greatly rely on the experience and expertise of pathologists. Hence, complete automation of the ANA test is required to avoid incorrect diagnoses. This paper represents an algorithm for the complex HEp-2 cell classification problem. The proposed algorithm used a small hybrid feature set that characterizes the texture and morphology of the HEp-2 cells along with artificial neural network (ANN). The hybrid features were extracted by breaking up the image into eight binary images. The proposed hybrid descriptors were more efficient than the popular co-occurrence matrix descriptor and local binary pattern descriptors for texture analysis. The proposed algorithm was evaluated on the ICPR 2016 IIF HEp-2 cell image dataset. The results indicated that the hybrid descriptor with an ANN approach achieved improved performance, with “96.8%” mean class accuracy.