Diagnosis of Vulvovaginal Candidiasis via Automatic Extraction of Candida Fungus from Pap Smear Images

Document Type : Original Article (s)

Authors

1 MSc Student, Department of Bioelectric and Biomedical Engineering, School of Advanced Medical Technology AND Student Research Committee, Isfahan University of Medical Sciences, Isfahan, Iran

2 Associate Professor, Department of Pathology, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran

3 Associate Professor, Department of Bioelectric and Biomedical Engineering, School of Advanced Medical Technology, Isfahan University of Medical Sciences, Isfahan, Iran

Abstract

Background: Vulvovaginal candidiasis (VVC) is a common clinical problem due to occurrence overgrowth of candida in genital system mucosa of females. The aim of this study was automatic diagnosis of vulvovaginal candidiasis via detection and extraction of candida fungus from microscopic images of Pap smear samples. We used image processing techniques to detect candida fungus.Methods: The sample space consisted of 200 microscopic images. Microscopic images were prepared from 49 Pap smear samples using Nikon1 V1 camera mounted on Nikon Eclipse 50i light microscope. For uniform illumination of the images, bottom-hat filtering was used. De-correlation stretching and linear contrast stretching were used for contrast enhancement. Different geometric features such as area, major axis, minor axis, eccentricity, perimeter, compactness, and decision tree classifier were used for extraction of mycelium and conidium of candida.Findings: The results of extraction of mycelium showed a specificity of 98.64% and a sensitivity of 96.88%. The corresponding values for conidium detection were 91.54% and 92.32%, respectively.Conclusion: According to our findings, this software would be helpful to pathologists in the diagnosis of vulvovaginal candidiasis in prevention of eyestrain. It could increase the accuracy of diagnosis, too.

Keywords

References

  1. Sobel JD. Epidemiology and pathogenesis of recurrent vulvovaginal candidiasis. Am J Obstet Gynecol 1985; 152(7 Pt 2): 924-35.
  2. Sobel JD. Candidal vulvovaginitis. Clin Obstet Gynecol 1993; 36(1): 153-65.
  3. Sobel JD. Vulvovaginal candidosis. Lancet 2007; 369(9577): 1961-71.
  4. White DJ, Vanthuyne A. Vulvovaginal candidiasis. Sex Transm Infect 2006; 82(Suppl 4): iv28-iv30.
  5. Fidel PL, Jr. History and new insights into host defense against vaginal candidiasis. Trends Microbiol 2004; 12(5): 220-7.
  6. Moreira D, Paula CR. Vulvovaginal candidiasis. Int J Gynaecol Obstet 2006; 92(3): 266-7.
  7. Garcia HM, Garcia SD, Copolillo EF, Cora EM, Barata AD, Vay CA, et al. Prevalence of vaginal candidiasis in pregnant women. Identification of yeasts and susceptibility to antifungal agents. Rev Argent Microbiol 2006; 38(1): 9-12.
  8. Vincent JL, Anaissie E, Bruining H, Demajo W, el-Ebiary M, Haber J, et al. Epidemiology, diagnosis and treatment of systemic Candida infection in surgical patients under intensive care. Intensive Care Med 1998; 24(3): 206-16.
  9. Barnett JA. A history of research on yeasts 12: medical yeasts part 1, Candida albicans. Yeast 2008; 25(6): 385-417.
  10. Kasiulevicius V, Sapoka V, Filipaviciute R. Sample size calculation in epidemiological studies. Gerontologija 2006; 7(4): 225-31.
  11. Akyuz AO, Reinhard E. Noise reduction in high dynamic range imaging. J Vis Commu Image R 2007; 18(5): 366-76.
  12. Ellenberger J. Noise reduction in digital imaging- an exploration of the state of the art. for CS525-Multimedia Computing and Communications. Colorado Springs, CO: University of Colorado; 2010.
  13. Jalba C, Wilkinson HF, Roerdink BTM. Morphological hat-transform scale spaces and their use in pattern classification. Pattern Recognition 2004; 37(5): 901-15.
  14. Gentav A, Aksoy S, Onder S. Unsupervised segmentation and classification of cervical cell images. Pattern Recognition 2012; 45(12): 4151-68.
  15. Saleh Al-amri SS, Kalyankar NV, Khamitkar SD. Linear and non-linear contrast enhancement image. International Journal of Computer Science and Network Security ed. 2010.
  16. Gillespie AR, Kahle AB, Walker RE. Color enhancement of highly correlated images. I. Decorrelation and HSI contrast stretches. Remote Sensing of Environment 1986; 20(3): 209-35.
  17. Siena I, Adi K, Gernowo R, Mirnasari N. Development of algorithm tuberculosis bacteria identification using color segmentation and neural networks. International Journal of Video and Image Processing and Network Security 2012; 12(4): 9-13.
  18. Costa MG, Costa Filho CF, Sena JF, Salem J, de Lima MO. Automatic identification of mycobacterium tuberculosis with conventional light microscopy. Conf Proc IEEE Eng Med Biol Soc 2008; 2008: 382-5.
  19. Otsu N. A threshold selection method from gray-level histograms. Systems, Man and Cybernetics, IEEE Transactions on 1979; 9(1): 62-6.
  20. Forero MG, Sroubek F, Cristbal G. Identification of tuberculosis bacteria based on shape and color. Real-Time Imaging 2004; 10(4): 251-62.
  21. Hiremath PS, Parashuram B. Automatic identification and classification of Bacilli bacterial cell growth phases. IJCA,Special Issue on RTIPPR 2010; 1: 48-52.
  22. Loh WY. Classification and regression trees. WIREs Data Mining Knowl Discov 2011; 1(1): 14-23.
  23. Sadaphal P, Rao J, Comstock GW, Beg MF. Image processing techniques for identifying Mycobacterium tuberculosis in Ziehl-Neelsen stains. Int J Tuberc Lung Dis 2008; 12(5): 579-82.
  24. Tadrous PJ. Computer-assisted screening of Ziehl-Neelsen-stained tissue for mycobacteria. Algorithm design and preliminary studies on 2,000 images. Am J Clin Pathol 2010; 133(6): 849-58.
  25. Glas AS, Lijmer JG, Prins MH, Bonsel GJ, Bossuyt PM. The diagnostic odds ratio: a single indicator of test performance. J Clin Epidemiol 2003; 56(11): 1129-35.
Journal of Isfahan Medical School
Volume 32, Issue 304 - Serial Number 304
September and October 2014
Pages 1659-1667

Files

History

  • Receive Date: 16 September 2014
  • Revise Date: 01 November 2024
  • Accept Date: 06 April 2022

Share

How to cite

Statistics