Special Issue on the International Conference on Intelligent Systems Design and Applications (Selected Papers from ISDA 2009); Guest Editors: H. Bustince (Public Univ. of Navarra, Spain) and B. Lazzerini (Univ. of Pisa, Italy)No Access

FUZZY-BASED ANALYSIS OF MICROSCOPIC COLOR CERVICAL PAP SMEAR IMAGES: NUCLEI DETECTION

PILAR SOBREVILLA

Applied Mathematics II Department, Universitat Politecnica de Catalunya, Jordi Girona 1-3, Barcelona 08034, Spain

MAII Department, Universitat Politecnica de Catalunya.

Search for more papers by this author

EDUARD MONTSENY

Automatic Control and Computer Engineering Department, Universitat Politecnica de Catalunya, Jordi Girona 1-3, Barcelona 08034, Spain

Search for more papers by this author

FABIO VASCHETTO

Dipartimento di Elettronica, Politecnico di Torino, Corso Duca degli Abruzzi, 24 Torino 10129, Italy

Search for more papers by this author

, and

ENRIQUE LERMA

Pathology Department, Sant Pau Hospital, Autonomous University of Barcelona, Sant Antoni Maria Claret, 167 Barcelona 08025, Spain

Search for more papers by this author

https://doi.org/10.1142/S1469026810002860Cited by:8 (Source: Crossref)

Abstract

The Pap Smear test, or cervico-vaginal cytology, is globally the most used and suitable method for screening cervical cancer precursor lesions, with a significant impact in reducing the incidence and mortality rates. However, Pap test suffers from subjective variability and no specificity, being the most controversial point the persistence of false negatives; i.e., normal cytological report for a woman with existing dysplasia, pre-malignant, or malignant lesions of the cervix. This is due in large part to the vast number of cells that must be reviewed by a technician for determining the possible existence of a small number of malignant or pre-malignant cells.

Automated systems that include technician knowledge and interpretation could not only reduce sample examination time but also avoid misclassification of samples because of human errors.

Here we present part of our ongoing work toward automation of cervical screening process. Specifically, since in cytological studies nuclei are considered the most informative regions, and an accurate segmentation is needed for extracting meaningful cell features, we propose an automated nuclei detection algorithm that integrates color information, cytopathologists knowledge, and fuzzy systems. Results have shown that besides a high performance and efficiency, the speed of the algorithm is very high.

Keywords:

Remember to check out the Most Cited Articles!
Check out these titles in artificial intelligence!

References

D. M. Parkinet al., CA Cancer J. Clin. 55(2), 74 (2005), DOI: 10.3322/canjclin.55.2.74. Crossref, Google Scholar
G. F. Sawayaet al., N. Engi. J. Med. 344, 1603 (2001), DOI: 10.1056/NEJM200105243442107. Crossref, Google Scholar
P. Sasieni, J. Adams and J. Cuzick, Br. J. Cancer 89, 88 (2003), DOI: 10.1038/sj.bjc.6600974. Crossref, Google Scholar
G. N. Papanicolaou and N. F. Traut , Diagnosis of Uterine Cancer by the Vaginal Smear ( Commonwealth Fund , New York , 1943 ) . Crossref, Google Scholar
L. G. Koss, Cancer 71(), 1406 (1993). Crossref, Google Scholar
S. M. Selvaggi, JAMA 285, 1506 (2001), DOI: 10.1001/jama.285.11.1506. Crossref, Google Scholar
D. Malleet al., Acta Cytology 47, 129 (2003). Crossref, Google Scholar
M. H. Stoler and M. Schiffman, JAMA 285, 1500 (2001), DOI: 10.1001/jama.285.11.1500. Crossref, Google Scholar
W. M. Linet al., Am. J. Obstet. Gynecol. 183, 39 (2000). Google Scholar
B. H. Williset al., Health Technol. Assess. 9(13), 1 (2005). Google Scholar
H. D. Chenget al., Patt. Recogn. 34(12), 2259 (2001), DOI: 10.1016/S0031-3203(00)00149-7. Crossref, Google Scholar
O. Lezoray, Image Anal. Stereol. 22, 113 (2003). Crossref, Google Scholar
L. Zeng and Q. Wu, Lect. Notes Comput. Sci. 4222 (Springer-Verlag, 2006) pp. 734–741. Google Scholar
N. Isa et al. , Improvement of contrast enhancement technique for cervical cell of Pap smear images by reducing the effect of unwanted background information , Proc. Int. Conf. Computing & Informatics, ICOCI '06 ( 2006 ) . Google Scholar
Y. Marinakis and G. Dounias , Nearest neighbor based pap-smear cell classification using tabu search for feature selection , Proc. Nature Inspired Smart Information Systems NiSIS ( 2006 ) . Google Scholar
L. Zhong and K. Najarian, Automated classification of Pap Smear tests using neural networks, Proc. IJCNN '014 (2001) pp. 2899–2901. Google Scholar
P. Phukpattaranont and P. Boonyaphiphat, Segmentation of cancer cells in microscopic images using neural network and mathematical morphology, Proc. SICE-ICASE Int. Joint Conf. (2006) pp. 18–21. Google Scholar
W. J. Frable, Cancer Cytopathol. 93(3), 171 (2001). Crossref, Google Scholar
N. Mat-Isa, M. Mashorb and N. Othman, Artif. Intell. Med. 42(1), 1 (2008). Crossref, Google Scholar
G. Begelmanet al., Cell nuclei segmentation using fuzzy logic engine, Proc. Int. Conf. Image Processing5 (2004) pp. 2937–2940. Google Scholar
D. Murashov , Method for segmentation of low contrast cytological images based on the active contour model , Proc. ACIT — Signal and Image Processing 450 ( 2005 ) . Google Scholar
M. E. Plissitiet al., Automated segmentation of cell nuclei in PAP smear images, Proc. IEEE Int. Special Topic Conference on Information Technology in Biomedicine (2006) pp. 26–28. Google Scholar
P. Sobrevilla, E. Lerma and E. Montseny, An approach to a fuzzy-based automatic pap screening system — FAPSS addressed to cytology cells detection, Proc. 22nd NAFIPS Int. Conf. (2003) pp. 138–142. Google Scholar
P. Sobrevilla, E. Montseny and E. Lerma, Fuzzy Sets and Their Extensions: Representation, Aggregation and Models, eds. H. Bustinceet al. (Springer, Berlin/Heidelberg, 2008) pp. 657–674. Crossref, Google Scholar
R. J. Kurman and D. Solomon , The Bethesda System for Reporting Cervical/Vaginal Cytologic Diagnoses ( Springer-Verlag , New York , 1994 ) . Crossref, Google Scholar
D. Solomoet al., JAMA 287, 2114 (2001). Crossref, Google Scholar
E. Lermaet al., Cancer Cytopathol. 84, 361 (1998). Crossref, Google Scholar
S. Romani, E. Montseny and P. Sobrevilla, Proc. NAFIPS 2002 Conf. (2002) pp. 69–74. Google Scholar
S. Wesolkowski, M. Jernigan and R. Dony, Comparison of color image edge detectors in multiple color spaces, Proc. 2000 Int. Conf. on Image Processing2 (2000) pp. 796–799. Google Scholar
A. R. Robertson, Phys. Today 24 (1992), DOI: 10.1063/1.881324. Google Scholar
L. Na and L. J. Xin, Automatic color image segmentation based on anisotropic diffusion and the application in cancer cell segmentation, Proc. 1st Int. Conf. on Bioinformatics and Biomedical Engineering (2007) pp. 992–994. Google Scholar
A. R. Smith, IEEE Trans. Comput. Graph. 12, 12 (1978). Crossref, Google Scholar
J. Jantzen and G. Dounias , Analysis of Pap-smear image data , Proc. 2nd Annual Symposium of the Nature-Inspired Smart Information Systems NISIS ( 2006 ) . Google Scholar
Y. Marinakis and G. Dounias , Pap Smear diagnosis using a hybrid intelligent scheme focusing on Genetic Algorithm based feature selection , Proc. Nature Inspired Smart Information Systems NiSIS ( 2006 ) . Google Scholar
E. Montseny and P. Sobrevilla, Math. Soft Comput. 2(3), 223 (1998). Google Scholar