Classification of ANA HEp-2 slide images using morphological features of stained patterns

Method for classification of the ANA HEp-2 medical test slide images is presented.To increase robustness of the method both stand-alone and overlapped cells are used.New method for a separation of overlapped cells introduced in the preliminary step.Cell-level classification is performed using two SVM models.Slide-level classification relies on a voting scheme with cell-source depended weights. Correct diagnostics of autoimmune disorders is important for a treatment planning as many of such diseases demonstrate similar symptoms. Owing to ANA HEp-2 medical test it is possible to distinguish among such autoimmune disease as lupus erythematosus, scleroderma and Sjogrens syndrome. It is known that manual disease classification performing based on analysis of indirect immunofluorescent images obtained in the course of this test is error-prone. Here, we present an automatic method for classification of ANA HEp-2 images that performs separation of the individual cell on pre-segmented slide images and subsequent cell and slide image classification. The method uses morphological properties of the stained patterns located inside the cell nucleus for an individual cell classification and a voting scheme for a classification of the whole ANA HEp-2 slide image.