Motivations

Pattern Recognition techniques are widely used in the field of medical applications for the development of Computer-Aided Diagnosis (CAD) systems with the aim of supporting the physician with a second reader, thus allowing to reduce the number of mistaken decisions during the diagnosis process, or in the mass screening campaigns by determining a pre-selection of the cases to be examined, enabling the physician to focus his/her attention only on the most relevant cases, or as an aid for training and education of specialized medical personnel.

In the last years a certain interest has grown towards the realization of CAD systems for the analysis of Indirect Immuno-Fluorescence (IIF) images. Today IIF is the gold standard for a diagnostic methodology suitable to search for antibodies in the patient serum using the HEp-2 substrate, in order to reveal the presence of autoimmune diseases. Due to its effectiveness, we are witnessing a growing demand for diagnostic tests for systemic autoimmune diseases. Unfortunately, IIF is still a subjective method that requires manual microscopy reading; making it too dependent on the experience and expertise of the physicians. Henceforth, there is strong demand for the complete automation of the procedure. This would result in increased test repeatability and reliability, easier and faster result reporting and a reduction of cost for the Healthcare System.

To that end, an increasing number of research groups have provided innovative contributions to the different aspects of the analysis of IIF images: image acquisition, pre-processing, segmentation, and pattern classification.  However, research in the field of IIF image analysis is still in its infancy and has great potential for further growth. In fact, this research topic is gaining new enthusiasm and interest among scientists and the size of the community may now be considered significant. The large interest of the scientific community in these topics has been demonstrated by the increasing number of international benchmarking initiatives organized over the last few years hosted by the last two editions of the ICPR conference (in 2012 and 2014) and by ICIP 2013 which all attracted a very wide audience.

The aim of the HEP-2 CONTEST 2016 is to advance the development of algorithms and methods for HEp-2 image analysis through third party evaluation of the methods on common datasets.