Skip to main content
SpringerLink
Log in

Automated lung cancer detection by the analysis of glandular cells in sputum cytology images using scale space features

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Out of all various types of lung cancers, adenocarcinoma is increasing at an alarming rate mainly due to the increased rate of smoking. This work aims at developing a sputum cytology image analysis system which identifies benign and malignant glandular cells. In our proposed system, we develop an automated lung cancer detection system which segments the cell nuclei and classifies the glandular cells from the given sputum cytology image using a novel scale space catastrophe histogram (SSCH) feature. Catastrophe points occur when pairwise annihilation of extrema and saddle happens in scale space. Unusual nuclear texture shows the presence of malignancy in cells, and SSCH-based texture feature extraction from nuclear region is done. From the input high-resolution image, the cellular regions are localized using maximization of determinant of Hessian, nuclei regions are segmented using K-means clustering, and SSCH features are extracted and classified using support vector machine and color thresholding. The experimental results show that the proposed method obtained an accuracy of 87.53 % which is better than Gabor filter-based gray-level co-occurrence features, local binary pattern, and complex Daubechies wavelet-based features. The results obtained are in accordance with the dataset classified by medical experts.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

References

  1. Park, J.A., Park, H.J., Lee, J.S., Ha, J.O., Lee, G.K., Park, B.K., Ghim, T.T.: Adenocarcinoma of lung in never smoked children. Proc. Lung Cancer 61(1), 266–269 (2008)

    Article  Google Scholar 

  2. Oswald, N.C., Hinson, K.F.W., Canti, G., Miller, A.B.: The diagnosis of primary lung cancer with special reference to sputum cytology. Proc. Thorax 26(6), 623–631 (1971)

    Article  Google Scholar 

  3. Veena, V.S., Preethi, S.G., Jayasree, K., Sujathan, K.: Cytological analysis of sputum: the simplest and preliminary method of lung cancer diagnosis—a retrospective analysis of 8690 samples of symptomatic patients. Proc. Int. J. Sci. Res. Publ. 2(12), 1–6 (2012)

    Google Scholar 

  4. Palcic, B., Garner, D.M., Beveridge, J., Sun, X.R., Doudkine, A., MacAulay, C., Lam, S., Payne, P.W.: Increase of sensitivity of sputum cytology using high-resolution image cytometry: field study results. Proc. Cytom. 50(3), 168–176 (2002)

    Article  Google Scholar 

  5. Thunnisen, F.B.J.M.: Sputum examination for early detection of lung cancer. Proc. J. Clin. Pathol. 56(11), 805–810 (2003)

    Article  Google Scholar 

  6. Schreiber, G., McCrory, D.C.: Performance characteristics of different modalities for diagnosis of suspected lung cancer: summary of published evidence. Proc. Chest 123(1), 115S–128S (2003)

    Article  Google Scholar 

  7. Petty, L., Thomas, M.D.: The early Identification of lung carcinoma by sputum cytology. Proc. Cancer 89(11), 2461–2464 (2000)

    Article  Google Scholar 

  8. Hoda, R.S., Saccomanno, G., Schreiber, K., Decker, D., Koss, L.G.: Automated sputum screening with papnet system: a study of 122 cases. Proc. Hum. Pathol. 27(7), 656–659 (1996)

    Article  Google Scholar 

  9. Bernardis, E., Yu, S.X.: Pop out many small structures from a very large microscopic image. Proc. Med. Image Anal. 15(5), 690–707 (2011)

    Article  Google Scholar 

  10. Schnorrenberg, F., Pattichis, C.S., Kyriacou, K.C., Schizas, C.N.: Computer-aided detection of breast cancer nuclei. Proc. IEEE Trans. Inf. Technol. Biomed. 1(2), 128–140 (1997)

    Article  Google Scholar 

  11. Wang, H., Zeng, S., Yu, C., Wang, X., Xia, D.: The research of microscopic image segmentation and recognition on the cancer cells fallen into peritoneal effusion. In: Proceedings IEEE International Workshop on Medical Imaging and Augmented Reality, Shatin, Hong Kong, pp. 253–258 (2001)

  12. Begelman, G. , Gur, E., Rivlin, E., Rudzsky, M., Zalevsky, Z.: Cell nuclei segmentation using fuzzy logic engine. In: Proceedings IEEE Conference Image Processing pp. 2937–2940 (2004)

  13. Hu, M., Ping, X., Ding, Y.: Automated cell nucleus segmentation using improved snake. In: Proceedings International IEEE Conference on Image Processing, Oct. 24–27, pp. 2737–2740 (2004)

  14. Wittke, C., Mayer, J., Schweiggert, F.: On the classification of prostate carcinoma with methods from spatial statistics. Proc. IEEE Trans. Inf. Technol. Biomed. 11(4), 406–414 (2007)

    Article  Google Scholar 

  15. Kharna, N., Moghnieh, H., Yao, J., Guo, Y.P., Baker, A.A., Laganiere, J., Rouleau, G., Cheriet, M.: Automatic segmentation of cells from microscopic imagery using ellipse detection. Proc. IET Image Process. 1(1), 39–47 (2007)

    Article  Google Scholar 

  16. Ko, B., Seo, M., Nam, J.: Microscopic image segmentation for the clinical support system. In: Proceedings IEEE Computer Graphics, Imaging and Visualization, Bangkok. Thailand, Aug. 14–17, 489–494 (2007)

  17. Palacios, G., Beltran, J.R.: Cell nuclei segmentation combining multiresolution analysis, clustering methods and colour spaces. In: Proceedings IEEE International Conference Machine Vision and Image Processing, Kildare, Sept. 5–7, pp. 91–97 (2007)

  18. Taher, F., Sammouda, R.: Identification of lung cancer based on shape and color. In: Proceedings IEEE on 4th International Conference Innovations in Information Technology, Dubai, Nov. 18–20, pp. 481–485 (2007)

  19. Cheng, E.D., Challa, S., Chakravorty, R.: Microscopic cell detection based on multiple cell image segmentations and fusion algorithms. In: Proceedings 2nd IEEE International Conference Biomedical Engineering and Informatics, Oct. 17–19, pp. 1–7 (2009)

  20. Du, X., Dua, S.: Segmentation of fluorescence microscopy cell images using unsupervised mining. Proc. Open Med. Inform. 4, 41–49 (2010)

    Google Scholar 

  21. Bradbury, L., Wan, J.W.: A spectral k-means approach to bright-field cell image segmentation. In: Proceedings IEEE Annual International Conference Engineering in Medicine and Biology Society, pp. 4748–4751 (2010)

  22. Kazmar, T., Smid, M., Fuchs, M., Luber, B., Mattes, J.: Learning cellular texture features in microscopic cancer cell images for automated cell-detection. In: Proceedings IEEE Annual International Conference of Engineering in Medicine and Biology Society, Buenos Aires, Aug. 31, pp. 49–52 (2010)

  23. Plissiti, M.E., Nikou, C., Charchanti, A.: Automated detection of cell nuclei in pap smear images using morphological reconstruction and clustering. Proc. IEEE Trans. Inf. Technol. Biomed. 15(2), 233–241 (2011)

    Article  Google Scholar 

  24. Das, K., Majumdar, A., Siegenthaler, M., Keirstead, H., Gopi, M.: Automated cell classification and visualization for analyzing remyelination therapy. Proc. Vis. Comput. 27(12), 1055–1069 (2011)

    Article  Google Scholar 

  25. Rodenacker, K., Bengtsson, E.: A feature set for cytometry on digitized microscopic images. Proc. Anal. Cell. Pathol. 25(1), 1–36 (2003)

    Article  Google Scholar 

  26. Thiran, J., Macq, B.: Morphological feature extraction for the classification of digital images of cancerous tissues. Proc. IEEE Trans. Biomed. Eng. 43(10), 1011–1020 (1996)

    Article  Google Scholar 

  27. Zhang, L., Wang, Q., Qi, J.: Research based on fuzzy algorithm of cancer cells in pleural fluid microscopic images recognition. In: Proceedings IEEE International Conference Intelligent Information Hiding and Multimedia Signal Processing, Pasadena, California, pp. 211–214. Dec (2006)

  28. Niwas, S.I., Palanisamy, P., Chibbar, R., Zhang, W.J.: An expert support system for breast cancer diagnosis using color wavelet features. Proc. J. Med. Syst. 35(5), 3091–3102 (2011)

    Google Scholar 

  29. Altunbay, D., Cigir, C., Sokmensuer, C., Gunduz-Demir, C.: Color graphs for automated cancer diagnosis and grading. IEEE Trans. Biomed. Eng. 57(3), 665–674 (2010)

    Article  Google Scholar 

  30. Pietikinen, M., Hadid, A., Zhao, G., Ahonen, T.: Computer Vision Using Local Binary Patterns, Springer, London. Ch. 2, 13–43 (2011)

  31. Nanni, L., Lumini, A., Brahnam, S.: Local binary patterns variants as texture descriptors for medical image analysis. Proc. J. Artif. Intell. Med. 49(2), 117–125 (2010)

    Article  Google Scholar 

  32. Kalkan, H., Nap, M., Duin, R.P., Loog, M.: Automated colorectal cancer diagnosis for whole-slice histopathology. In: Proceedings Medical Image Computing and Computer-Assisted Intervention -MICCAI-2012, Nice, France, Oct. 1–5, pp. 550–557 (2012)

  33. Niwas, S.I., Palanisamy, P., Sujathan, K., Bengtsson, E.: Analysis of nuclei textures of fine needle aspirated cytology images for breast cancer diagnosis using complex daubechies wavelets. In: Proceedings of Signal Processing Elsevier, Jul. (2012) (in press)

  34. Bejnordi, B.E., Moshavegh, R., Sujathan, K., Malm, P., Bengtsson, E.: Novel chromatin texture features for the classification of pap smears. In: Proceedings SPIE 8676, Medical Imaging 2013: Digital, Pathology, Mar. 29, pp. 867608-1 -867608-8 (2013)

  35. Sammouda, M., Niki, N., Niki, T., Yamaguchi, N.: Analysis of color images of tissues derived from patients with adenocarcinoma of the lung. In: Proceedings IEEE International Conference Image Processing, Vancouver, British Columbia, pp. 192–195 (2000)

  36. Phukpattaranont, P., Boonyaphiphat, P.: Segmentation of cancer cells in microscopic images using neural network and mathematical morphology. In: Proceedings IEEE International Joint Conference SICE-ICASE, Busan, Oct. 18–21, pp. 2312–2315 (2006)

  37. Theera-Umpon, N., Dhompongsa, S.: Morphological granulometric features of nucleus in automatic bone marrow white blood cell classification. Proc. IEEE Trans. Inf. Technol. Biomed 11(3), 353–359 (2007)

    Article  Google Scholar 

  38. Niwas, S.I., Palanisamy, P., Sujathan, K.: Complex wavelet as nucleus descriptors for automated cancer cytology classifier system using ANN. In: Proceedings IEEE International Conference Computational Intelligence and Computing Research, Coimbatore, India, Dec. 28–29, pp. 1–5 (2010)

  39. Doyle, S., Hwang, M., Shah, K., Madabhushi, A., Feldman, M., Tomaszeweski, J.: Automated grading of prostate cancer using architectural and textural image features. In: Proceedings 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Arlington, VA, Apr. 12–15, pp. 1284–1287 (2007)

  40. Niwas, S.I., Palanisamy, P., Zhang, W.J., Isa, N.A.M., Chibbar, R.: Log-gabor wavelets based breast carcinoma classification using least square support vector machine. In: Proceedings IEEE International Conference Imaging Systems and Techniques, Penang, May 17–18, pp. 219–223 (2011)

  41. Yu, L., Todd, N.W., Xing, L., Xie, Y., Zhang, H., Liu, Z., Fang, H., Zhang, J., Katz, Rl, Jiang, F.: Early detection of lung adenocarcinoma in sputum by a panel of microRNA markers. Proc. Int. J. Cancer 127(12), 2870–2878 (2010)

  42. Saccomano, G.: Sputum cytology: collection, fixation and concentration of sputum, bronchial aspirates and bronchial brushings. Lab Med. 10, 523–527 (1979)

    Google Scholar 

  43. Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: Speeded-up robust features (SURF). Proc. Comput. Vis. Image Underst. 110(3), 346–359 (2008)

    Article  Google Scholar 

  44. Viola, P.A., Jones, M.: Rapid object detection using a boosted cascade of simple features. Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. 1, 511–518 (2001)

    Google Scholar 

  45. Otsu, N.: A threshold selection method from gray-level histograms. Proc. IEEE Trans. Syst. Man Cybern. 9, 62–66 (1979)

    Article  Google Scholar 

  46. Rudin, L., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Proc. Phys. D 60, 259–268 (1992)

    MATH  Google Scholar 

  47. Vogel, C.R., Oman, M.E.: Iterative methods for total variation denoising. Proc. SIAM J. Sci. Comp. 17(1), 227–238 (1996)

    Article  MATH  MathSciNet  Google Scholar 

  48. Soman, K.P., Ramanathan, R.: Digital Signal and Image Processing, The Sparse Way. ISA Publishers, India (2012)

    Google Scholar 

  49. MacQueen, J.B.: Some Methods for Classification and Analysis of Multivariate Observations. In: Proceedings 5th Berkeley Symposium on Mathematical Statistics and Probability, pp. 281–297 (1967)

  50. Platel, B., Kanters, F.M.W., Florack, L.M.J., Balmachnova, E.G.: Using multiscale top points in image matching. Proc. Int. Conf. Image Process. 1, 389–392 (2004)

    Google Scholar 

  51. Kanters, F., Lillholm, M., Duits, R., Janssen, B., Platel, B., Florack, L., Romeny, B.H.: On image reconstruction from multiscale top points. In: Proceedings 5th International Conference Scale-Space 2005, Hofgeismar. Germany, Apr. 7–9, 431–442 (2005)

  52. Lindeberg, T.: Scale-space theory: a basic tool for analysing structures at different scales. Proc. J. Appl. Stat. 21(2), 224–270 (1994)

    Google Scholar 

  53. Koenderink, J.: The structure of images. Proc. Biol. Cybern. 50(5), 363–370 (1984)

    Article  MATH  MathSciNet  Google Scholar 

  54. Florack, L.M.J., Romeny, B., Koenderink, J., Viergever, M.A.: Linear scale-space. Proc. Math. Imaging Vis. 4(4), 325–351 (1994)

    Article  Google Scholar 

  55. Duits, R., Florack, L., Graaf, J.D., Romeny, B.: On the axioms of scale space theory. Proc. Math. Imaging Vis. 20(3), 267–298 (2004)

    Article  Google Scholar 

  56. Lindeberg, T.: Feature detection with automatic scale selection. Proc. Int. J. Comput. Vision 30(2), 79–116 (1998)

    Article  Google Scholar 

  57. Romeny, B.: Front-End Vision and Multi-Scale Image Analysis: Multi-scale Computer Vision Theory and Applications. Kluwer, Netherlands (2002)

    Google Scholar 

  58. Florack, L.M.J., Kuijper, A.: The topological structure of scale-space images. Proc. Math. Imaging Vis. 12(1), 65–79 (2000)

    Article  MATH  MathSciNet  Google Scholar 

  59. Blom, J.: Topological and geometrical aspects of image structure, Ph.D. thesis, Utrecht University (1992)

  60. Kuijper, A.: On detecting all saddle points in 2D images. Proc. Pattern recognit. Lett. 25(15), 1665–1672 (2004)

    Article  Google Scholar 

  61. Chan, T.F., Vese, L.A.: Active contours without edges. Proc. IEEE Trans. Image Process. 12(2), 266–277 (2001)

    Article  Google Scholar 

  62. Witten, I.H., Frank, E.: Data Mining Practical Machine Learning Tools and Techniques, Morgan Kaufmann, San Francisco, California, Ch.5, pp. 143–173 (2005)

Download references

Acknowledgments

The authors would like to thank Nimi G. K. of Pathology lab, Regional Cancer Center, Thiruvananthapuram, India, for helping us in acquiring sputum cytology images. We would also like to thank Dr. C. Shunmugha Velayutham, Department of Computer Science and Engineering, Amrita Viswavidyapeetham, Coimbatore, India, for his valuable help and support.

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Amrita Viswa Vidyapeetham, Coimbatore, India

    S. Sajith Kecheril & D. Venkataraman

  2. Department of Computer Science and Engineering, Hindusthan College of Engineering and Technology, Coimbatore, India

    J. Suganthi

  3. Department of Pathology, Regional Cancer Center, Thiruvananathapuram, India

    K. Sujathan

Authors
  1. S. Sajith Kecheril
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. D. Venkataraman
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. J. Suganthi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. K. Sujathan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to D. Venkataraman.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kecheril, S.S., Venkataraman, D., Suganthi, J. et al. Automated lung cancer detection by the analysis of glandular cells in sputum cytology images using scale space features. SIViP 9, 851–863 (2015). https://doi.org/10.1007/s11760-013-0512-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-013-0512-8

Keywords

Search

Navigation