Benchmarking HEp-2 Cells Classification Methods

In this paper we report on the first edit ion of the HEp-2 Cells Classificat ion contest , held at the 2012 edit ion of the Internat ional Conference on Pattern Recognit ion, and focused on Indirect Immunofluorescence (IIF) image analysis. The IIF methodology is used to detect autoimmune diseases by searching for ant ibodies in the pat ient serum but, unfortunately, it is st ill a subject ive method that depends too heavily on the experience and expert ise of the physician. This has been the mot ivat ion behind the recent init ial developments of computer aided diagnosis systems in this field. The contest aimed to bring together researchers interested in the performance evaluat ion of algorithms for IIF image analysis: 28 different recognit ion systems able to automat ically recognize the staining pattern of cells within IIF images were tested on the same undisclosed dataset. In part icular, the dataset takes into account the six staining patterns that occur most frequent ly in the daily diagnost ic pract ice: centromere, nucleolar, homogeneous, fine speckled, coarse speckled and cytoplasmic. In the paper we briefly describe all the submit ted methods, analyze the obtained results and discuss the design choices condit ioning the performance of each method. URL http://dx.doi.org/10.1109/TMI.2013.2268163 [6 ] DOI 10.1109/TMI.2013.2268163 [6 ] Short Tit le IEEE Trans Med Imaging Source URL: http://www.antibodychain.com/content/benchmarking_hep_2_cells_classification_methods Links: [1] http://www.antibodychain.com/content/benchmarking_hep_2_cells_classification_methods [2] http://www.antibodychain.com/biblio/author/142512 [3] http://www.antibodychain.com/biblio/author/142513 [4] http://www.antibodychain.com/biblio/author/55326 [5] http://www.antibodychain.com/biblio/author/142514 [6] http://dx.doi.org/10.1109/TMI.2013.2268163