Paolo Soda, Giulio Iannello



At the present, Indirect ImmunoFluorescence (IIF) imaging is the recommended method for the detection of antinuclear autoantibodies. IIF diagnosis requires to estimate the fluorescence intensity and to describe the staining pattern, but resources and adequately trained personnel are not always available. In this respect, an evident medical demand is the development of Computer Aided Diagnosis (CAD) tools that can offer a support to physician decision. In this paper we present a comprehensive system that supports the two sides of IIF tests classification. It is based on a cascade of two systems: the first labels the fluorescence intensity, whereas the second recognizes the staining pattern of positive wells. The analysis of its perspective performance shows the system potential in lowering the method variability, in increasing the level of standardization and in reducing the specialist workload by more than 80%.


  1. Allwein, E. L., Schapire, R. E., and Singer, Y. (2001). Reducing multiclass to binary: a unifying approach for margin classifiers. Journal of Machine Learning Research, 1:113-141.
  2. Bio-Rad Laboratories Inc. (2004). http://www.bio-rad.com.
  3. Center for Disease Control (1996). Quality assurance for the indirect immunofluorescence test for autoantibodies to nuclear antigen (IF-ANA): approved guideline. NCCLS I/LA2-A, 16(11).
  4. Crammer, K. and Singer, Y. (2002). On the algorithmic implementation of multiclass kernel-based vector machines. Journal of Machine Learning Research, 2:265-292.
  5. Das (2004). Service Manual AP16 IF Plus. Palombara Sabina (RI).
  6. Dietterich, T. G. and Bakiri, G. (1995). Solving multiclass learning problems via error-correcting output codes. Journal of Artificial Intelligence Research, 2:263-286.
  7. Fawcett, T. (2004). ROC graphs: Notes and practical considerations for researchers. Machine Learning, 31.
  8. Feltkamp, T. E. W., Klein, F., and Janssens, M. (1988). Standardisation of the quantitative determination of antinuclear antibodies (ANAs) with a homogeneous pattern. Annals of the Rheumatic Diseases, 47(11):906-909.
  9. Hastie, T. and Tibshirani, R. (1998). Classification by pairwise coupling. In NIPS 7897: Proceedings of the 1997 conference on Advances in neural information & processing systems 10, pages 507-513, Cambridge, MA, USA. MIT Press.
  10. Hiemann, R., Hilger, N., Michel, J., Nitscke, J., Bohm, A., Anderer, U., Weigert, M., and Sack, U. (2007). Automatic analysis of immunofluorescence patterns of HEp-2 cells. Annals of the New York Academy of Sciences, 1109(1):358-371.
  11. Jelonek, J. and Stefanowski, J. (1998). Experiments on solving multiclass learning problems by n2 classifier. In 10th European Conference on Machine Learning, pages 172-177. Springer-Verlag Lecture Notes in Artificial Intelligence.
  12. Kavanaugh, A., Tomar, R., Reveille, J., Solomon, D. H., and Homburger, H. A. (2000). Guidelines for clinical use of the antinuclear antibody test and tests for specific autoantibodies to nuclear antigens. American College of Pathologists, Archives of Pathology and Laboratory Medicine, 124(1):71-81.
  13. Kuncheva, L. I. (2005). Using diversity measures for generating error-correcting output codes in classifier ensembles. Pattern Recognition Letters, 26(1):83-90.
  14. Masulli, F. and Valentini, G. (2000). Comparing decomposition methods for classication. In KES'2000, Fourth International Conference on Knowledge-Based Intelligent Engineering Systems & Allied Technologies, pages 788-791.
  15. Mayoraz, E. and Moreira, M. (1997). On the decomposition of polychotomies into dichotomies. In ICML 7897: Proceedings of the Fourteenth International Conference on Machine Learning, pages 219-226.
  16. Perner, P., Perner, H., and Muller, B. (2002). Mining knowledge for HEp-2 cell image classification. Journal Artificial Intelligence in Medicine, 26:161-173.
  17. Piazza, A., Manoni, F., Ghirardello, A., Bassetti, D., Villalta, D., Pradella, M., and Rizzotti, P. (1998). Variability between methods to determine ANA, antidsDNA and anti-ENA autoantibodies: a collaborative study with the biomedical industry. Journal of Immunological Methods, 219:99-107.
  18. Rigon, A., Soda, P., Zennaro, D., Iannello, G., and Afeltra, A. (2007). Indirect immunofluorescence in autoimmune diseases: Assessment of digital images for diagnostic purpose. Cytometry B (Clinical Cytometry), 72:472-477.
  19. Sack, U., Knoechner, S., Warschkau, H., Pigla, U., Emmerich, F., and Kamprad, M. (2003). Computerassisted classification of HEp-2 immunofluorescence patterns in autoimmune diagnostics. Autoimmunity Reviews, 2:298-304.
  20. Soda, P. and Iannello, G. (2006). Experiences in ANNbased classification of immunofluorescence images. International Journal of Applied Science, Engineering and Technology, 2(2):102-107.
  21. Soda, P. and Iannello, G. (2008). Staining pattern classification in antinuclear autoantibodies testing. In HEALTHINF 2008, pages 231-236.
  22. Soda, P., Iannello, G., and Vento, M. (2008). A multiple experts system for classifying fluorescence intensity in antinuclear autoantibodies analysis. Pattern Analysis & Applications, doi: 10.1007/s10044-008-0116-z.
  23. Solomon, D. H., Kavanaugh, A. J., and Schur, P. H. (2002). Evidence-based guidelines for the use of immunologic tests: Antinuclear antibody testing. Arthritis Care & Research, 47(4):434-444.

Paper Citation

in Harvard Style

Soda P. and Iannello G. (2009). A CAD SYSTEM FOR IIF TESTS . In Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2009) ISBN 978-989-8111-63-0, pages 43-50. DOI: 10.5220/0001544800430050

in Bibtex Style

author={Paolo Soda and Giulio Iannello},
booktitle={Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2009)},

in EndNote Style

JO - Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2009)
SN - 978-989-8111-63-0
AU - Soda P.
AU - Iannello G.
PY - 2009
SP - 43
EP - 50
DO - 10.5220/0001544800430050