Semi-Automatic Segmentation and Classification of Pap Smear Cells

Cytologic screening has been widely used for detecting the cervical cancers. In this study, a semiautomatic PC-based cellular image analysis system was developed for segmenting nuclear and cytoplasmic contours and for computing morphometric and textual features to train support vector machine (SVM) classifiers to classify four different types of cells and to discriminate dysplastic from normal cells. A software program incorporating function, including image reviewing and standardized denomination of file names, was also designed to facilitate and standardize the workflow of cell analyses. Two experiments were conducted to verify the classification performance. The cross-validation results of the first experiment showed that average accuracies of 97.16% and 98.83%, respectively, for differentiating four different types of cells and in discriminating dysplastic from normal cells have been achieved using salient features (8 for four-cluster and 7 for two-cluster classifiers) selected with SVM recursive feature addition. In the second experiment, 70% (837) of the cell images were used for training and 30% (361) for testing, achieving an accuracy of 96.12% and 98.61% for four-cluster and two-cluster classifiers, respectively. The proposed system provides a feasible and effective tool in evaluating cytologic specimens.

[1]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[2]  Chih-Jen Lin,et al.  Combining SVMs with Various Feature Selection Strategies , 2006, Feature Extraction.

[3]  Y. T. van der Schouw,et al.  Observer variation in cytologic grading for cervical dysplasia of Papanicolaou smears with the PAPNET testing system , 1999, Cancer.

[4]  J H Tucker.  CERVISCAN: an image analysis system for experiments in automatic cervical smear prescreening. , 1976, Computers and biomedical research, an international journal.

[5]  H Benghuzzi,et al.  Cytomorphological assessment of benign and malignant dense hyperchromatic groups in cervicovaginal smears. , 2000, Biomedical sciences instrumentation.

[6]  Chih-Yi Chiu,et al.  Finding textures by textual descriptions, visual examples, and relevance feedbacks , 2003, Pattern Recognit. Lett..

[7]  Rung Ching Chen,et al.  Quantitative Assessment of Pap Smear Cells by PC-Based Cytopathologic Image Analysis System and Support Vector Machine , 2008, ICMB.

[8]  Chao-Ton Su,et al.  Feature selection for the SVM: An application to hypertension diagnosis , 2008, Expert Syst. Appl..

[9]  Alain Rakotomamonjy,et al.  Variable Selection Using SVM-based Criteria , 2003, J. Mach. Learn. Res..

[10]  R. Demay,et al.  Common problems in Papanicolaou smear interpretation. , 1997, Archives of pathology & laboratory medicine.

[11]  Leo Grady,et al.  Random Walks for Image Segmentation , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  L. Mango,et al.  Reducing false negatives in clinical practice: the role of neural network technology. , 1996, American journal of obstetrics and gynecology.

[13]  N. Ku,et al.  Automated Papanicolaou smear analysis as a screening tool for female lower genital tract malignancies. , 1999, Current opinion in obstetrics & gynecology.

[14]  Martin Wasser,et al.  Cell cycle phase classification in 3D in vivo microscopy of Drosophila embryogenesis , 2011, BMC Bioinformatics.

[15]  Selim Aksoy,et al.  Unsupervised segmentation and classification of cervical cell images , 2012, Pattern Recognit..

[16]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[17]  Thomas F Kardos,et al.  The FocalPoint system , 2004, Cancer.

[18]  C J Taylor,et al.  The magiscan image analyser as a diagnostic aid in cytology. , 1981, Analytical and quantitative cytology.

[19]  P.K Sahoo,et al.  A survey of thresholding techniques , 1988, Comput. Vis. Graph. Image Process..

[20]  Qingmao Hu,et al.  On minimum variance thresholding , 2006, Pattern Recognit. Lett..

[21]  Nikos Dimitropoulos,et al.  Mammographic masses characterization based on localized texture and dataset fractal analysis using linear, neural and support vector machine classifiers , 2006, Artif. Intell. Medicine.

[22]  J N Turner,et al.  Advances in high-speed, three-dimensional imaging and automated segmentation algorithms for thick and overlapped clusters in cytologic preparations. Application to cervical smears. , 1998, Analytical and quantitative cytology and histology.

[23]  Bhaskar D. Kulkarni,et al.  A support vector machine-based method for predicting the propensity of a protein to be soluble or to form inclusion body on overexpression in Escherichia coli , 2006, Bioinform..

[24]  D. Cavouras,et al.  Development of a support vector machine-based image analysis system for assessing the thyroid nodule malignancy risk on ultrasound. , 2005, Ultrasound in medicine & biology.

[25]  Rassoul Amirfattahi,et al.  An Automated Method for Segmentation of Epithelial Cervical Cells in Images of ThinPrep , 2010, Journal of Medical Systems.

[26]  Ming-Hung Wang,et al.  An Adaptable Threshold Decision Method , 2009, 2009 Fifth International Conference on Information Assurance and Security.

[27]  Peter M. Kasson,et al.  A hybrid machine-learning approach for segmentation of protein localization data , 2005, Bioinform..

[28]  Edoardo Amaldi,et al.  On the Approximability of Minimizing Nonzero Variables or Unsatisfied Relations in Linear Systems , 1998, Theor. Comput. Sci..

[29]  Bharat Rekhi,et al.  Role of computerized morphometric analysis in diagnosis of effusion specimens , 2006, Diagnostic cytopathology.

[30]  S. You,et al.  Effectiveness of national cervical cancer screening programme in Taiwan: 12-year experiences , 2009, British Journal of Cancer.

[31]  Mehmet Fatih Akay,et al.  Support vector machines combined with feature selection for breast cancer diagnosis , 2009, Expert Syst. Appl..

[32]  J Linder.  Automation of the Papanicolaou smear: a technology assessment perspective. , 1997, Archives of pathology & laboratory medicine.

[33]  Andrea E Dawson.  Can we change the way we screen?: The ThinPrep Imaging System® , 2004, Cancer.

[34]  E. Myers,et al.  Technologic Advances for Evaluation of Cervical Cytology: Is Newer Better? , 2001, Obstetrical & gynecological survey.

[35]  J. F. Brenner,et al.  Contextual analysis and intermediate cell markers enhance high-resolution cell image analysis for automated cervical smear diagnosis. , 1991, Cytometry.

[36]  Meng-Hsiun Tsai,et al.  Nucleus and cytoplast contour detector of cervical smear image , 2008, Pattern Recognit. Lett..

[37]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[38]  Ming-Tsang Wu,et al.  Computerized nuclear morphometry in thyroid follicular neoplasms , 2005, Pathology international (Print).

[39]  Christophoros Nikou,et al.  Automated Detection of Cell Nuclei in Pap Smear Images Using Morphological Reconstruction and Clustering , 2011, IEEE Transactions on Information Technology in Biomedicine.

[40]  Farid Melgani,et al.  Toward an Optimal SVM Classification System for Hyperspectral Remote Sensing Images , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[41]  Xiaobo Zhou,et al.  Automated segmentation, classification, and tracking of cancer cell nuclei in time-lapse microscopy , 2006, IEEE Transactions on Biomedical Engineering.

[42]  Jing-Yu Yang,et al.  Automated Cell Phase Classification for Zebrafish Fluorescence Microscope Images , 2010, 2010 20th International Conference on Pattern Recognition.

[43]  Chih-Jen Lin,et al.  Manuscript Number: 2187 Training ν-Support Vector Classifiers: Theory and Algorithms , 2022 .

[44]  Mark H Stoler,et al.  Advances in Cervical Screening Technology , 2000, Modern Pathology.

[45]  L. Hao,et al.  Improving detection sensitivity for partial discharge monitoring of high voltage equipment , 2008 .

[46]  José Manuel Benítez,et al.  Segmentation of cervical cell nuclei in high-resolution microscopic images: A new algorithm and a web-based software framework , 2012, Comput. Methods Programs Biomed..

[47]  Georgios Dounias,et al.  Pap smear diagnosis using a hybrid intelligent scheme focusing on genetic algorithm based feature selection and nearest neighbor classification , 2009, Comput. Biol. Medicine.

[48]  Nor Ashidi Mat Isa,et al.  Semi-automated pseudo colour features extraction technique for cervical cancer's pap smear images , 2011, Int. J. Knowl. Based Intell. Eng. Syst..

[49]  Bülent Sankur,et al.  Survey over image thresholding techniques and quantitative performance evaluation , 2004, J. Electronic Imaging.

[50]  Tsukasa Ashihara,et al.  Morphological abstraction of thyroid tumor cell nuclei using morphometry with factor analysis , 2003, Microscopy research and technique.

[51]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[52]  R N Taylor,et al.  CytoView. A prototype computer image-based Papanicolaou smear proficiency test. , 1999, Acta cytologica.

[53]  Ichiro Mori,et al.  Color image analysis of cervical neoplasia using RGB computer color specification. , 2002, Analytical and quantitative cytology and histology.

[54]  Eduard Montseny,et al.  Fuzzy-Based Analysis of Microscopic Color Cervical Pap Smear Images: Nuclei Detection , 2010, Int. J. Comput. Intell. Appl..

[55]  Polina Golland,et al.  Scoring diverse cellular morphologies in image-based screens with iterative feedback and machine learning , 2009, Proceedings of the National Academy of Sciences.

[56]  Lilla Böröczky,et al.  Feature subset selection for improving the performance of false positive reduction in lung nodule CAD , 2006, 18th IEEE Symposium on Computer-Based Medical Systems (CBMS'05).

[57]  S. M.,et al.  Ghostscript wrapper for J:\PUB_ARCHIV\JOURNALS\ACY\ACY1998042_001\lockedpdfs\ACY1998042001165.PDF , 2013 .

[58]  Michalis E. Blazadonakis,et al.  Wrapper filtering criteria via linear neuron and kernel approaches , 2008, Comput. Biol. Medicine.

[59]  Nello Cristianini,et al.  An introduction to Support Vector Machines , 2000 .

[60]  Anne E Carpenter,et al.  CellProfiler: image analysis software for identifying and quantifying cell phenotypes , 2006, Genome Biology.

[61]  Naoki Sakai,et al.  Identification of Idealized Leaf Types Using Simple Dimensionless Shape Factors by Image Analysis , 1996 .

[62]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[63]  Stanislaw Osowski,et al.  Application of Support Vector Machine and Genetic Algorithm for Improved Blood Cell Recognition , 2009, IEEE Transactions on Instrumentation and Measurement.

[64]  Hideyuki Tamura,et al.  Textural Features Corresponding to Visual Perception , 1978, IEEE Transactions on Systems, Man, and Cybernetics.

[65]  Yen-Ping Chu,et al.  Edge Enhancement Nucleus and Cytoplast Contour Detector of Cervical Smear Images , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[66]  Mu-Chen Chen,et al.  Prediction model building and feature selection with support vector machines in breast cancer diagnosis , 2008, Expert Syst. Appl..

[67]  Vladimir Kirillov,et al.  A rapid method for diagnosing regional metastases of papillary thyroid cancer with morphometry , 2006, Microscopy research and technique.

[68]  V C Padaki,et al.  An interactive image analysis system for quantitative cytology & to classify cervical cells. , 1992, The Indian journal of medical research.

[69]  Babak Sokouti,et al.  A framework for diagnosing cervical cancer disease based on feedforward MLP neural network and ThinPrep histopathological cell image features , 2012, Neural Computing and Applications.

[70]  B Nordin,et al.  Image analysis in cytology: DNA-histogramming versus cervical smear prescreening. , 1993, Annales de biologie clinique.

[71]  Richard Weber,et al.  A wrapper method for feature selection using Support Vector Machines , 2009, Inf. Sci..

[72]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.