The Papanicolau (Pap) test is a routine cytological procedure for early detection of dysplastic lesions in cervical epithelium. A reliable screening method is crucial for triage of women at risk; however manual screening and interpretation are associated with relatively low sensitivity and substantial interobserver diagnostic variability. P16 and Ki67 biomarkers have been recently proposed as adjunctive tools in the diagnosis of high-risk human papillomavirus (hrHPV) associated dysplasias to supplement the morphological characteristics of cells by additional colorimetric features. In this study, an automated technique for the evaluation of dual p16/Ki67 immunoreactivity in cervical cell nuclei is introduced. Smears stained with p16 and Ki67 antibodies were digitized, and analyzed by algorithms we developed. Gradient-based radial symmetry operator and adaptive processing of symmetry image were employed to obtain the nuclear mask. This step was followed by the extraction of features including pixel data and immunoreactivity signature from each nucleus. The features were analyzed by two support vector machine classifiers to assign a nucleus into one of four types of immunoreactivity: p16 positive (p16+/Ki67−), Ki67 positive (p16−/Ki67+), dual p16/Ki67 positive (p16+/Ki67+) and negative (p16−/Ki67−), respectively. Results obtained by our method correlated well with readings by two cytopathologists (n = 18,068 cells); p16+/Ki67+ nuclei were classified with respective precisions of 77.1% and 82.6%. Specificity in identification of p16−/Ki67− nuclei was better than 99.5%, and the sensitivity in detection of all immunopositive nuclei was 86.3 and 89.4%, respectively. We found that the quantitative characterization of immunoreactivity provided by the additional highlighting of classified nuclei can positively impact the efficacy and screening outcome of the Pap test.
This is a preview of subscription content, access via your institution.
Buy single article
Instant access to the full article PDF.
Tax calculation will be finalised during checkout.
Bose, S., H. Evans, L. Lantzy, K. Scharre, and E. Youssef. p16(INK4A) is a surrogate biomarker for a subset of human papilloma virus-associated dysplasias of the uterine cervix as determined on the Pap smear. Diagn. Cytopathol. 32:21–24, 2005.
Botev, Z. I., J. F. Grotowski, and D. P. Kroese. Kernel density estimation via diffusion. Ann. Stat. 38:2916–2957, 2010.
Byers, T., J. Mouchawar, J. Marks, B. Cady, N. Lins, G. M. Swanson, D. G. Bal, and H. Eyre. The American Cancer Society challenge goals. How far can cancer rates decline in the U.S. by the year 2015? Cancer 86:715–727, 1999.
Dunton, C. J., K. H. van Hoeven, A. J. Kovatich, R. E. Oliver, R. Q. Scacheri, J. R. Cater, and J. A. Carlson, Jr. Ki-67 antigen staining as an adjunct to identifying cervical intraepithelial neoplasia. Gynecol. Oncol. 64:451–455, 1997.
Haralick, R. M., and L. G. Shapiro. Computer and Robot Vision. Reading, MA: Addison-Wesley, 1992.
Juric, D., V. Mahovlic, S. Rajhvajn, A. Ovanin-Rakic, L. Skopljanac-Macina, A. Barisic, I. S. Projic, D. Babic, M. Susa, A. Corusic, and S. Oreskovic. Liquid-based cytology—new possibilities in the diagnosis of cervical lesions. Coll. Antropol. 34:19–24, 2010.
Longatto Filho, A., M. L. Utagawa, N. K. Shirata, S. M. Pereira, G. M. Namiyama, C. T. Kanamura, C. Santos Gda, M. A. de Oliveira, A. Wakamatsu, S. Nonogaki, C. Roteli-Martins, C. di Loreto, G. de Mattosinho Castro Ferraz Mda, M. Y. Maeda, V. A. Alves, and K. Syrjanen. Immunocytochemical expression of p16INK4A and Ki-67 in cytologically negative and equivocal pap smears positive for oncogenic human papillomavirus. Int. J. Gynecol. Pathol. 24:118–124, 2005.
Loy, G., and A. Zelinsky. Fast radial symmetry for detecting points of interest. IEEE Trans. Pattern Anal. Mach. Intell. 25:959–973, 2003.
Mat-Isa, N. A. Automated edge detection technique for Pap smear images using moving K-means clustering and modified seed based region growing algorithm. Int. J. Comput. Internet Manag. 13:45–59, 2005.
Meyer, J. L., D. W. Hanlon, B. T. Andersen, O. F. Rasmussen, and K. Bisgaard. Evaluation of p16INK4a expression in ThinPrep cervical specimens with the CINtec p16INK4a assay: correlation with biopsy follow-up results. Cancer 111:83–92, 2007.
Nanda, K., D. C. McCrory, E. R. Myers, L. A. Bastian, V. Hasselblad, J. D. Hickey, and D. B. Matchar. Accuracy of the Papanicolaou test in screening for and follow-up of cervical cytologic abnormalities: a systematic review. Ann. Intern. Med. 132:810–819, 2000.
Nayar, R., and D. Solomon. Second edition of ‘The Bethesda System for reporting cervical cytology’—atlas, website, and Bethesda interobserver reproducibility project. Cytojournal 1:4, 2004.
Perona, P., and J. Malik. Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 12:629–639, 1990.
Plissiti, M. E., C. Nikou, and A. Charchanti. Automated detection of cell nuclei in pap smear images using morphological reconstruction and clustering. IEEE Trans. Inf. Technol. Biomed. 15:233–241, 2011.
Reagan, J. W., and M. J. Hamonic. The cellular pathology in carcinoma in situ; a cytohistopathological correlation. Cancer 9:385–402, 1956.
Sahebali, S., C. E. Depuydt, G. A. Boulet, M. Arbyn, L. M. Moeneclaey, A. J. Vereecken, E. A. Van Marck, and J. J. Bogers. Immunocytochemistry in liquid-based cervical cytology: analysis of clinical use following a cross-sectional study. Int. J. Cancer 118:1254–1260, 2006.
Sahebali, S., C. E. Depuydt, K. Segers, A. J. Vereecken, E. Van Marck, and J. J. Bogers. Ki-67 immunocytochemistry in liquid based cervical cytology: useful as an adjunctive tool? J. Clin. Pathol. 56:681–686, 2003.
Schölkopf, B., C. J. C. Burges, and A. J. Smola. Advances in Kernel Methods: Support Vector Learning. Cambridge, MA: MIT, 1999.
Scholzen, T., and J. Gerdes. The Ki-67 protein: from the known and the unknown. J. Cell. Physiol. 182:311–322, 2000.
Schubert, J. M., B. Bird, K. Papamarkakis, M. Miljkovic, K. Bedrossian, N. Laver, and M. Diem. Spectral cytopathology of cervical samples: detecting cellular abnormalities in cytologically normal cells. Lab. Invest. 90:1068–1077, 2010.
Siddiqi, A. M., H. Li, F. Faruque, W. Williams, K. Lai, M. Hughson, S. Bigler, J. Beach, and W. Johnson. Use of hyperspectral imaging to distinguish normal, precancerous, and cancerous cells. Cancer 114:13–21, 2008.
Sirovich, B. E., and H. G. Welch. The frequency of Pap smear screening in the United States. J. Gen. Intern. Med. 19:243–250, 2004.
Sobervilla, P., E. Montseny, F. Vaschetto, and E. Lerma. Fuzzy-based analysis of microscopic color cervical Pap smear images: nuclei detection. Int. J. Comput. Intell. Appl. 9:187–206, 2010.
Tsoumpou, I., M. Arbyn, M. Kyrgiou, N. Wentzensen, G. Koliopoulos, P. Martin-Hirsch, V. Malamou-Mitsi, and E. Paraskevaidis. p16(INK4a) immunostaining in cytological and histological specimens from the uterine cervix: a systematic review and meta-analysis. Cancer Treat. Rev. 35:210–220, 2009.
Walts, A. E., and S. Bose. p16, Ki-67, and BD ProExC immunostaining: a practical approach for diagnosis of cervical intraepithelial neoplasia. Hum. Pathol. 40:957–964, 2009.
Yang-Mao, S. F., Y. K. Chan, and Y. P. Chu. Edge enhancement nucleus and cytoplast contour detector of cervical smear images. IEEE Trans. Syst. Man. Cybern. B: Cybern. 38:353–366, 2008.
This work was supported in part by a grant from the Department of Surgery at Cedars-Sinai Medical Center, and in part by a NIH grant 5R21CA143618-02 (to AG). We also thank Dr Hunter Hardy M.D. for technical help in specimen imaging.
Conflict of interest
The authors declare that they have no conflict of interest.
Associate Editor James Tunnell oversaw the review of this article.
About this article
Cite this article
Gertych, A., Joseph, A.O., Walts, A.E. et al. Automated Detection of Dual p16/Ki67 Nuclear Immunoreactivity in Liquid-Based Pap Tests for Improved Cervical Cancer Risk Stratification. Ann Biomed Eng 40, 1192–1204 (2012). https://doi.org/10.1007/s10439-011-0498-8
- Pap test
- Cervical cancer screening
- Computer analysis
- Nuclei segmentation