Fuzzy-Based Analysis of Microscopic Color Cervical Pap Smear Images: Nuclei Detection

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.

[1]  L. Koss.  Cervical (pap) smear: New directions , 1993, Cancer.

[2]  S. Selvaggi.  Implications of low diagnostic reproducibility of cervical cytologic and histologic diagnoses. , 2001, JAMA.

[3]  Liu Jian-Xin,et al.  Automatic Color Image Segmentation Based on Anisotropic Diffusion and the Application in Cancer Cell Segmentation , 2007, 2007 1st International Conference on Bioinformatics and Biomedical Engineering.

[4]  Slawomir Wesolkowski,et al.  Comparison of color image edge detectors in multiple color spaces , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[5]  J. Arseneau,et al.  Atypical squamous cells of undetermined significance. A cytohistologic study of 52 cases. , 1997, Acta cytologica.

[6]  J Prat,et al.  Rescreening of atypical cervicovaginal smears using PAPNET , 1998, Cancer.

[7]  A. Maitra,et al.  Molecular Papanicolaou tests in the twenty-first century: molecular analyses with fluid-based Papanicolaou technology. , 2000, American journal of obstetrics and gynecology.

[8]  Nor Ashidi Mat Isa,et al.  An automated cervical pre-cancerous diagnostic system , 2008, Artif. Intell. Medicine.

[9]  D. I. Fotiadis,et al.  Automated segmentation of cell nuclei in PAP smear images , 2006 .

[10]  Jing Li Wang,et al.  Color image segmentation: advances and prospects , 2001, Pattern Recognit..

[11]  E. Montseny,et al.  An approach to a fuzzy color detection method, robust with regard to variable illuminant level conditions , 2002, 2002 Annual Meeting of the North American Fuzzy Information Processing Society Proceedings. NAFIPS-FLINT 2002 (Cat. No. 02TH8622).

[12]  Libo Zeng,et al.  Fast Segmentation of Cervical Cells by Using Spectral Imaging Analysis Techniques , 2006, ICNC.

[13]  M. Schiffman,et al.  Interobserver reproducibility of cervical cytologic and histologic interpretations: realistic estimates from the ASCUS-LSIL Triage Study. , 2001, JAMA.

[14]  Pornchai Phukpattaranont.  Segmentation ofCancerCells inMicroscopic Images using Neural Network andMathematical Morphology , 2006 .

[15]  Mark Sherman,et al.  The 2001 Bethesda System: terminology for reporting results of cervical cytology. , 2002, JAMA.

[16]  Alvy Ray Smith,et al.  Color gamut transform pairs , 1978, SIGGRAPH.

[17]  Jan Jantzen,et al.  Analysis of Pap-smear Image Data , 2006 .

[18]  George N. Papanicolaou Herbert F. Traut,et al.  Diagnosis of uterine cancer by the vaginal smear , 1943 .

[19]  J. Ferlay,et al.  Global Cancer Statistics, 2002 , 2005, CA: a cancer journal for clinicians.

[20]  A. Jemal,et al.  Global Cancer Statistics , 2011 .

[21]  A R Smith,et al.  Color Gamut Transformation Pairs , 1978 .

[22]  Eduard Montseny,et al.  A Fuzzy-based Automated Cells Detection System for Color Pap Smear Tests --FACSDS- , 2008, Fuzzy Sets and Their Extensions: Representation, Aggregation and Models.

[23]  J. Cuzick,et al.  Benefit of cervical screening at different ages: evidence from the UK audit of screening histories , 2003, British Journal of Cancer.

[24]  Ehud Rivlin,et al.  Cell nuclei segmentation using fuzzy logic engine , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[25]  Diane Solomon,et al.  The Bethesda System for Reporting Cervical/Vaginal Cytologic Diagnoses , 1994, Springer US.

[26]  P Barton,et al.  Cervical screening programmes: can automation help? Evidence from systematic reviews, an economic analysis and a simulation modelling exercise applied to the UK. , 2005, Health technology assessment.

[27]  Olivier Lezoray,et al.  SUPERVISED AUTOMATIC HISTOGRAM CLUSTERING AND WATERSHED SEGMENTATION. APPLICATION TO MICROSCOPIC MEDICAL COLOR IMAGES , 2011 .

[28]  M.Y. Mashor,et al.  Improvement of contrast enhancement technique for cervical cell of Pap smear images by reducing the effect of unwanted background information , 2006, 2006 International Conference on Computing & Informatics.

[29]  C. Destouni,et al.  Experience with a Thin-Layer, Liquid-Based Cervical Cytologic Screening Method , 2003, Acta Cytologica.

[30]  A. Washington,et al.  Clinical practice. Current approaches to cervical-cancer screening. , 2001, The New England journal of medicine.

[31]  B. S. Manjunath,et al.  Color image segmentation , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[32]  Pilar Sobrevilla Frisón,et al.  Application of fuzzy techniques to the design of algorithms in computer vision , 1998 .

[33]  Eduard Montseny,et al.  An approach to a Fuzzy-based Automatic Pap Screening System-FAPSS-addressed to cytology cells detection , 2003, 22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003.

[34]  Adalsteinn D. Brown,et al.  Current Approaches to Cervical-Cancer Screening , 2001 .

[35]  W J Frable,et al.  Cervical screening by neural networks , 2001, Cancer.

[36]  Zhong Li,et al.  Automated classification of Pap smear tests using neural networks , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[37]  P. Phukpattaranont,et al.  Segmentation of Cancer Cells in Microscopic Images using Neural Network and Mathematical Morphology , 2006, 2006 SICE-ICASE International Joint Conference.