Automated Diagnosis and Classification of Cervical Cancer from pap-smear Images

Globally, cervical cancer ranks as the fourth most prevalent cancer affecting women. However, cervical cancer can be treated if detected at an early stage. Pap-smear is a good tool for screening of cervical cancer but the manual analysis is error-prone, tedious and time-consuming. The objective of this study was to rule out these limitations by automating the process of cervical cancer classification from pap-smear images by using an enhanced fuzzy c-means algorithm. Simulated annealing coupled with a wrapper filter was used for feature selection. The evaluation results showed that our method outperforms many of previous algorithms in classification accuracy (99.35%), specificity (97.93%) and sensitivity (99.85%), when applied to the Herlev benchmark pap-smear dataset. The overall accuracy, sensitivity and specificity of the classifier on prepared pap-smear slides was 95.00%, 100% and 90.00% respectively. False Negative Rate (FNR), False Positive Rate (FPR) and classification error of 0.00%, 10.00% and 5.00% respectively were obtained. The major contribution of this tool in a cervical cancer screening workflow is that it reduces on the time required by the cytotechnician to screen very many pap-smears by eliminating the obvious normal ones, hence more time can be put on the suspicious slides. The proposed tool has the capability of analyzing 1-2 smears per minute as opposed to the 5-10 minutes per slide in the manual analysis.

[1]  Garrison W. Cottrell,et al.  Color-to-Grayscale: Does the Method Matter in Image Recognition? , 2012, PloS one.

[2]  Karel J. Zuiderveld,et al.  Contrast Limited Adaptive Histogram Equalization , 1994, Graphics Gems.

[3]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[4]  N Tanaka,et al.  CYBEST model 3 automated cytologic screening system for uterine cancer utilizing image analysis processing. , 1982, Analytical and quantitative cytology.

[5]  Dr. Rahman Tashakkori.  Image Enhancement , 2009, Encyclopedia of Biometrics.

[6]  Rajesh Kumar,et al.  Debris removal in Pap-smear images , 2013, Comput. Methods Programs Biomed..

[7]  T J O'Leary,et al.  PAPNET-assisted rescreening of cervical smears: cost and accuracy compared with a 100% manual rescreening strategy. , 1998, JAMA.

[8]  Ernesto Bribiesca,et al.  State of the Art of Compactness and Circularity Measures 1 , 2009 .

[9]  Saso Dzeroski,et al.  Decision trees for hierarchical multi-label classification , 2008, Machine Learning.

[10]  John F. Canny,et al.  Canny Edge Detection , 2009 .

[11]  Zhiguo Jiang,et al.  Graph Convolutional Networks for Cervical Cell Classification , 2019 .

[12]  Richard Lee Hall,et al.  Canny Edge Detection , 2005 .

[13]  Hamid Hassanpour,et al.  Edge Detection Techniques: Evaluations and Comparison , 2008 .

[14]  Ewert Bengtsson,et al.  Screening for Cervical Cancer Using Automated Analysis of PAP-Smears , 2014, Comput. Math. Methods Medicine.

[15]  W. Tolles,et al.  AUTOMATIC SCREENING OF CYTOLOGICAL SMEARS FOR CANCER: THE INSTRUMENTATION , 1956, Annals of the New York Academy of Sciences.

[16]  Emile H. L. Aarts,et al.  Global optimization and simulated annealing , 1991, Math. Program..

[17]  Whoi-Yul Kim,et al.  A region-based shape descriptor using Zernike moments , 2000, Signal Process. Image Commun..

[18]  Malay Kumar Kundu,et al.  Automated classification of Pap smear images to detect cervical dysplasia , 2017, Comput. Methods Programs Biomed..

[19]  Georgios Dounias,et al.  Pap-smear Benchmark Data For Pattern Classification , 2005 .

[20]  R M Richart,et al.  The AutoPap 300 QC system multicenter clinical trials for use in quality control rescreening of cervical smears , 1997, Cancer.

[21]  R Erhardt,et al.  FAZYTAN: a system for fast automated cell segmentation, cell image analysis and feature extraction based on TV-image pickup and parallel processing. , 1980, Analytical and quantitative cytology.

[22]  Wayne Niblack,et al.  An introduction to digital image processing , 1986 .

[23]  Ronald M. Summers,et al.  DeepPap: Deep Convolutional Networks for Cervical Cell Classification , 2017, IEEE Journal of Biomedical and Health Informatics.

[24]  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.

[25]  J. A. Ware,et al.  A review of image analysis and machine learning techniques for automated cervical cancer screening from pap-smear images , 2018, Comput. Methods Programs Biomed..

[26]  G. P. Vooys,et al.  Field test results using the BioPEPR cervical smear prescreening system. , 1980, Cytometry.

[27]  A. Jemal,et al.  Global cancer statistics , 2011, CA: a cancer journal for clinicians.

[28]  Carolyn Nakisige,et al.  Cervical cancer screening and treatment in Uganda , 2017, Gynecologic oncology reports.

[29]  O A Husain,et al.  Trials with the cerviscan experimental prescreening device on polylysine-prepared slides. , 1981, Analytical and quantitative cytology.

[30]  Xinhua Zhuang,et al.  Image Analysis Using Mathematical Morphology , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Jing Qin,et al.  Application of Deep Learning in Automated Analysis of Molecular Images in Cancer: A Survey , 2017, Contrast media & molecular imaging.