ANA HEp-2 cells image classification using number, size, shape and localization of targeted cell regions

• An automatic method for classification of ANA HEp-2 cells images is proposed.
• The proposed method utilizes for recognition a morphological properties of the targeted cell domains.
• The method applies both a binarization and threshold-less approaches for feature extraction.

The ANA HEp-2 medical test is a powerful tool in autoimmune disease diagnostics. The last step of this test, the interpretation of immunofluorescent images by trained experts, represents a potential source of errors and could theoretically be replaced by automated methods. Here we present a fully automatic method for recognition of types of immunofluorescent images produced by the ANA HEp-2 medical test. The proposed method makes use of the difference in number, size, shape and localization of cell regions that are targeted by the antinuclear antibodies – the humoral components of immune system that bind human antigens as a result of the immune system malfunction. The method extracts morphological properties of stained cell regions using a combination of thresholding-based and thresholding-less approaches and applies a conventional machine-learning algorithm for image classification.