Introduction

The Competition on Cells Classification by Fluorescent Image Analysis is hosted by the 20th IEEE International Conference on Image Processing (ICIP) , which is the premier forum for the presentation of technological advances and research results in the fields of theoretical, experimental, and applied image and video processing. ICIP will be held during September 15-18, 2013 in Melbourne, Australia.

The contest focuses on the classification of cells extracted from Indirect Immunofluorescence (IIF) images. The IIF is a diagnostic methodology based on image analysis that reveals the presence of autoimmune diseases by searching for antibodies in the patient serum. IIF uses the human larynx carcinoma (HEp-2) substrate, which bonds with serum antibodies forming a molecular complex. This complex then reacts with human immunoglobulin conjugated with a fluorochrome and becomes observable at the fluorescence microscope where it reveals the antigen-antibody reaction. Due to its effectiveness in the recent years we have assisted to a growing demand of diagnostic tests for systemic autoimmune diseases.

The interest toward the realization of Computer Aided Diagnosis is witnessed by the growing number of papers proposing algorithms for the analysis of IIF images. Thus, an important issue regards the definition of reliable classification algorithms, and the comparison of their performance on common datasets.

The competition, which is jointly organized by the University of Salerno (Italy), the University of Queensland (Australia) and Sullivan Nicolaides Pathology (SNP) - Queensland Medical Testing Laboratory, (Australia), has this aim. The involvement of the SNP, a relevant laboratory that offers high qualified pathology services for doctors, private hospitals and nursing homes in Queensland northern New South Wales and Darwin, allowed to obtain a significant and valuable dataset that will be used for the contest.

The competition is about the recognition of the staining pattern of the cells obtained by IIF images according to the following classes: Homogeneous, Speckled, Nucleolar, Centromere, Golgi and Nuclear Membrane.