Advertisement

European Archives of Oto-Rhino-Laryngology

, Volume 273, Issue 1, pp 159–168 | Cite as

Microscopy image analysis of p63 immunohistochemically stained laryngeal cancer lesions for predicting patient 5-year survival

  • Konstantinos Ninos
  • Spiros Kostopoulos
  • Ioannis Kalatzis
  • Konstantinos Sidiropoulos
  • Panagiota Ravazoula
  • George Sakellaropoulos
  • George Panayiotakis
  • George Economou
  • Dionisis Cavouras
Laryngology

Abstract

The aim of the present study was to design a microscopy image analysis (MIA) system for predicting the 5-year survival of patients with laryngeal squamous cell carcinoma, employing histopathology images of lesions, which had been immunohistochemically (IHC) stained for p63 expression. Biopsy materials from 42 patients, with verified laryngeal cancer and follow-up, were selected from the archives of the University Hospital of Patras, Greece. Twenty six patients had survived more than 5 years and 16 less than 5 years after the first diagnosis. Histopathology images were IHC stained for p63 expression. Images were first processed by a segmentation method for isolating the p63-expressed nuclei. Seventy-seven features were evaluated regarding texture, shape, and physical topology of nuclei, p63 staining, and patient-specific data. Those features, the probabilistic neural network classifier, the leave-one-out (LOO), and the bootstrap cross-validation methods, were used to design the MIA-system for assessing the 5-year survival of patients with laryngeal cancer. MIA-system accuracy was about 90 % and 85 %, employing the LOO and the Bootstrap methods, respectively. The image texture of p63-expressed nuclei appeared coarser and contained more edges in the 5-year non-survivor group. These differences were at a statistically significant level (p < 0.05). In conclusion, this study has proposed an MIA-system that may be of assistance to physicians, as a second opinion tool in assessing the 5-year survival of patients with laryngeal cancer, and it has revealed useful information regarding differences in nuclei texture between 5-year survivors and non-survivors.

Keywords

5-year survival Laryngeal cancer p63 expression Immunohistochemistry Image analysis 

Notes

Acknowledgments

We would like to thank the Department of Pathology of the University Hospital of Patras for assisting in the peer evaluation of the H&E and p63-stained histologic specimens. We gratefully acknowledge the support of NVIDIA Corporation for the donation of the Tesla K20 GPU used for this research.

References

  1. 1.
    Talamini R, Bosetti C, La Vecchia C, Dal Maso L, Levi F, Bidoli E, Negri E, Pasche C, Vaccarella S, Barzan L, Franceschi S (2002) Combined effect of tobacco and alcohol on laryngeal cancer risk: a case-control study. Cancer Causes Control 13(10):957–964PubMedCrossRefGoogle Scholar
  2. 2.
    Sant M, Allemani C, Santaquilani M, Knijn A, Marchesi F, Capocaccia R (2009) EUROCARE-4. Survival of cancer patients diagnosed in 1995–1999. Results and commentary. Eur J Cancer 45(6):931–991PubMedCrossRefGoogle Scholar
  3. 3.
    Pruneri G, Pignataro L, Manzotti M, Carboni N, Ronchetti D, Neri A, Cesana BM, Viale G (2002) p63 in laryngeal squamous cell carcinoma: evidence for a role of TA-p63 down-regulation in tumorigenesis and lack of prognostic implications of p63 immunoreactivity. Lab Invest 82(10):1327–1334PubMedCrossRefGoogle Scholar
  4. 4.
    Dong P, Li X, Zhu Z, Yu Z, Lu G, Sun Z, Wang S (2004) Application of tissue microarray: evaluation of the expression of S-100-positive dendritic cells, tumor suppressor gene p63 and tissue inhibitor of metalloproteinase-1 in laryngeal carcinoma. Acta Otolaryngol 124(10):1204–1207PubMedCrossRefGoogle Scholar
  5. 5.
    Takahashi Y, Noguchi T, Takeno S, Kimura Y, Okubo M, Kawahara K (2006) Reduced expression of p63 has prognostic implications for patients with esophageal squamous cell carcinoma. Oncol Rep 15(2):323–328PubMedGoogle Scholar
  6. 6.
    Borba M, Cernea C, Dias F, Faria P, Bacchi C, Brandao L, Costa A (2010) Expression profile of p63 in 127 patients with laryngeal squamous cell carcinoma. ORL J Otorhinolaryngol Relat Spec 72(6):319–324PubMedGoogle Scholar
  7. 7.
    Re M, Zizzi A, Ferrante L, Stramazzotti D, Goteri G, Gioacchini FM, Olivieri F, Magliulo G, Rubini C (2014) p63 and Ki-67 immunostainings in laryngeal squamous cell carcinoma are related to survival. Eur Arch Otorhinolaryngol 271(6):1641–1651PubMedCrossRefGoogle Scholar
  8. 8.
    Delides A, Panayiotides I, Alegakis A, Kyroudi A, Banis C, Pavlaki A, Helidonis E, Kittas C (2005) Fractal dimension as a prognostic factor for laryngeal carcinoma. Anticancer Res 25(3B):2141–2144Google Scholar
  9. 9.
    Dobroś W, Gil K, Chłap Z, Olszewski E (1999) The use of nuclear morphometry for the prediction of survival in patients with advanced cancer of the larynx. Eur Arch Otorhinolaryngol 256(5):257–261PubMedCrossRefGoogle Scholar
  10. 10.
    Bacauskiene M, Verikas A, Gelzinis A, Valincius D (2009) A feature selection technique for generation of classification committees and its application to categorization of laryngeal images. Pattern Recogn 42(5):645–654CrossRefGoogle Scholar
  11. 11.
    Verikas A, Gelzinis A, Valincius D, Bacauskiene M, Uloza V (2007) Multiple feature sets based categorization of laryngeal images. Comput Methods Programs Biomed 85(3):257–266PubMedCrossRefGoogle Scholar
  12. 12.
    Ninos K, Kostopoulos S, Sidiropoulos K, Kalatzis I, Glotsos D, Athanasiadis E, Ravazoula P, Panayiotakis G, Economou G, Cavouras D (2013) Computer-based image analysis system designed to differentiate between low-grade and high-grade laryngeal cancer cases. Anal Quant Cytol Histol 35(5):261–272Google Scholar
  13. 13.
    Egner JR (2010) AJcc cancer staging manual. JAMA 304(15):1726–1727CrossRefGoogle Scholar
  14. 14.
    Kostopoulos S, Cavouras D, Daskalakis A, Kagadis GC, Kalatzis I, Georgiadis P, Ravazoula P, Nikiforidis G (2008) Cascade pattern recognition structure for improving quantitative assessment of estrogen receptor status in breast tissue carcinomas. Anal Quant Cytol Histol 30(4):218–225PubMedGoogle Scholar
  15. 15.
    Cheng HD, Sun Y (2000) A hierarchical approach to color image segmentation using homogeneity. IEEE Trans Image Process 9(12):2071–2082PubMedCrossRefGoogle Scholar
  16. 16.
    Jain AK (1989) Fundamentals of digital image processing. Prentice-Hall Inc, USAGoogle Scholar
  17. 17.
    Haralick RM, Shanmugam K, Dinstein IH (1973) Textural features for image classification. IEEE Trans Sys Man Cyb 3:610–621CrossRefGoogle Scholar
  18. 18.
    Galloway MM (1975) Texture analysis using gray-level run lengths. Comput Graph Image Process 4:172–179CrossRefGoogle Scholar
  19. 19.
    Huang PW, Lai YH (2010) Effective segmentation and classification for HCC biopsy images. Pattern Recogn 43(4):1550–1563CrossRefGoogle Scholar
  20. 20.
    Bandyopadhyay S, Saha S (2013) Unsupervised classification: similarity measures, classical and metaheuristic approaches, and applications. Springer-Verlag, BerlinCrossRefGoogle Scholar
  21. 21.
    Le CT (2003) Introductory biostatistics. Wiley, New YorkGoogle Scholar
  22. 22.
    Specht DF (1990) Probabilistic neural networks. Neural Netw 3:109–118CrossRefGoogle Scholar
  23. 23.
    Kechman V (2001) Support vector machines. Learning and soft computing. MIT, Cambridge, pp 121–184Google Scholar
  24. 24.
    Theodoridis S, Koutroumbas K (2008) Pattern recognition, 4th edn. Academic Press, USAGoogle Scholar
  25. 25.
    Kirk DB, W-mW Hwu (2010) Programming massively parallel processors a hands-on approach. Morgan Kaufmann, AmsterdamGoogle Scholar
  26. 26.
    Sidiropoulos KP, Kostopoulos SA, Glotsos DT, Athanasiadis EI, Dimitropoulos ND, Stonham JT, Cavouras DA (2013) Multimodality GPU-based computer-assisted diagnosis of breast cancer using ultrasound and digital mammography images. Int J Comput Assist Radiol Surg 8(4):547–560PubMedCrossRefGoogle Scholar
  27. 27.
    Glotsos D, Spyridonos P, Cavouras D, Ravazoula P, Dadioti PA, Nikiforidis G (2004) Automated segmentation of routinely hematoxylin-eosin-stained microscopic images by combining support vector machine clustering and active contour models. Anal Quant Cytol Histol 26(6):331–340PubMedGoogle Scholar
  28. 28.
    Latson L, Sebek B, Powell KA (2003) Automated Cell Nuclear Segmentation in Color Images of Hematoxylin and Eosin-Stained Breast Biopsy. Anal Quant Cytol Histol 25(6):321–331PubMedGoogle Scholar
  29. 29.
    Spyridonos P, Cavouras D, Ravazoula P, Nikiforidis G (2002) A computer-based diagnostic and prognostic system for assessing urinary bladder tumour grade and predicting cancer recurrence. Med Inform Internet Med 27(2):111–122PubMedCrossRefGoogle Scholar
  30. 30.
    Shamir L, Delaney JD, Orlov N, Eckley DM, Goldberg IG (2010) Pattern recognition software and techniques for biological image analysis. PLoS Comput Biol 6(11):e1000974PubMedPubMedCentralCrossRefGoogle Scholar
  31. 31.
    Theodoridis S, Pikrakis A, Koutroumbas K, Cavouras D (2010) Introduction to pattern recognition: a matlab approach. Academic PressGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Konstantinos Ninos
    • 1
  • Spiros Kostopoulos
    • 2
  • Ioannis Kalatzis
    • 2
  • Konstantinos Sidiropoulos
    • 2
    • 3
  • Panagiota Ravazoula
    • 4
  • George Sakellaropoulos
    • 5
  • George Panayiotakis
    • 5
  • George Economou
    • 1
  • Dionisis Cavouras
    • 2
  1. 1.Department of Physics, School of Natural SciencesUniversity of PatrasRio, PatrasGreece
  2. 2.Medical Image and Signal Processing Laboratory, Department of Biomedical EngineeringTechnological Educational Institute of AthensAthensGreece
  3. 3.European Molecular Biology Laboratory, Wellcome Trust Genome CampusEuropean Bioinformatics Institute (EMBL-EBI)CambridgeUK
  4. 4.Department of PathologyUniversity Hospital of PatrasRioGreece
  5. 5.Department of Medical Physics, Faculty of Medicine, School of Health SciencesUniversity of PatrasRio, PatrasGreece

Personalised recommendations