Advertisement

Histopathological Image Analysis Using Model-Based Intermediate Representations and Color Texture: Follicular Lymphoma Grading

  • Olcay Sertel
  • Jun Kong
  • Umit V. Catalyurek
  • Gerard Lozanski
  • Joel H. Saltz
  • Metin N. Gurcan
Article

Abstract

Follicular lymphoma (FL) is a cancer of lymph system and it is the second most common lymphoid malignancy in the western world. Currently, the risk stratification of FL relies on histological grading method, where pathologists evaluate hematoxilin and eosin (H&E) stained tissue sections under a microscope as recommended by the World Health Organization. This manual method requires intensive labor in nature. Due to the sampling bias, it also suffers from inter- and intra-reader variability and poor reproducibility. We are developing a computer-assisted system to provide quantitative assessment of FL images for more consistent evaluation of FL. In this study, we proposed a statistical framework to classify FL images based on their histological grades. We introduced model-based intermediate representation (MBIR) of cytological components that enables higher level semantic description of tissue characteristics. Moreover, we introduced a novel color-texture analysis approach that combines the MBIR with low level texture features, which capture tissue characteristics at pixel level. Experimental results on real follicular lymphoma images demonstrate that the combined feature space improved the accuracy of the system significantly. The implemented system can identify the most aggressive FL (grade III) with 98.9% sensitivity and 98.7% specificity and the overall classification accuracy of the system is 85.5%.

Keywords

Histopathological image analysis Model-based intermediate representation Color texture analysis Follicular lymphoma 

Notes

Acknowledgements

This work is supported in part by the US National Science Foundation (#CNS-0643969, #CNS-0403342, #CNS-0615155, #CCF-0342615), by the NIH NIBIB BISTI (#P20EB000591), NCI caBIG core middleware development (79077CBS10). The authors would like to thank Dr. Arwa Sha’naah, Dr. Amy Gewirtz, Dr. Frederick Racke, and Dr. John Zhao of The Ohio State University, Department of Pathology for providing the ground truth information and guidance, Dr. Pierluigi Porcu for useful discussions and Drs. Michael Pennell and Soledad Fernandez for the statistical design of the study.

References

  1. 1.
    Jaffe, E. S., Harris, N. L., Stein, H., & Vardiman, J. W. (2001). Tumours of haematopoietic and lymphoid tissues. Lyon: IRAC Press.Google Scholar
  2. 2.
    Metter, G. E., Nathwani, B. N., Burke, J. S., Winberg, C. C., Mann, R. B., Barcos, M., et al. (1985). Morphological subclassification of follicular lymphoma: Variability of diagnoses among hematopathologists, a collaborative study between the repository center and pathology panel for lymphoma clinical studies. Journal of Clinical Oncology, 3, 25–38.Google Scholar
  3. 3.
    Dick, F., Van Lier, S., Banks, P., Frizzera, G., Witrak, G., Gibson, R., et al. (1987). Use of the working formulation for non-Hodgkin’s lymphoma in epidemiological studies: Agreement between reported diagnoses and a panel of experienced pathologists. Journal of National Cancer Institue, 78, 1137–1144.Google Scholar
  4. 4.
    The Non-Hodgkin Lymphoma Classification Project. (1997). A clinical evaluation of the International Lymphoma Study Group classification of non-Hodgkin lymphoma. Blood, 89, 3909–3918.Google Scholar
  5. 5.
    Meijer, G. A., Belien, J. A. M., Diest, P. J., & Baak, J. P. A. (1997). Image analysis in clinical pathology. Journal of Clinical Pathology, 50, 365–370.CrossRefGoogle Scholar
  6. 6.
    Tabesh, A., Teverovskiy, M., Pang, H., Kumar, V. P., Verbel, D., Kotsianti, A., et al. (2007). Multifeature prostate cancer diagnosis and Gleason grading of histological images. IEEE Transaction on Medical Imaging, 26, 1366–1378.CrossRefGoogle Scholar
  7. 7.
    Petushi, S., Garcia, F. U., Haber, M. H., Katsinis, C., & Tozeren, A. (2006). Large-scale computations on histology images reveal grade-differentiating parameters for breast cancer. BMC Medical Imaging, 6, 14.CrossRefGoogle Scholar
  8. 8.
    Demir, C., Gultekin, S. H., & Yener, B. (2005). Augmented cell-graphs for automated cancer diagnosis. Bioinformatics, 21, 7–12.CrossRefGoogle Scholar
  9. 9.
    Gurcan, M. N., Pan, T., Shimada, H., & Saltz, J. H. (2006). Image analysis for neuroblastoma classification: Segmentation of cell nuclei. In Int. conf. of the IEEE engineering in medicine and biology society (EMBC). New York, NY.Google Scholar
  10. 10.
    Kong, J., Sertel, O., Shimada, H., Boyer, K. L., Saltz, J. H., & Gurcan, M. N. (2007). Computer-aided grading of neuroblastic differentiation: Muti-resolution and multi-classifier approach. In Proc. of the int. conf. on image processing (ICIP). (pp. 525–528). San Antonio, TX.Google Scholar
  11. 11.
    Haralick, R. M., Shanmugam, K., & Dinstein, I. (1973). Textural features for image classification. IEEE Transaction on Systems, Man, and Cybernetics, 3, 610–621.CrossRefGoogle Scholar
  12. 12.
    Sertel, O., Kong, J., Lozanski, G., Shanaah, A., Catalyurek, U., Saltz, J., et al. (2008). Texture classification using non-linear color quantization: Application to histopathological image analysis. In Proc. of the IEEE int. conf. on acoustics, speech, and signal processing (ICASSP) (pp. 597–600). Las Vegas, NV.Google Scholar
  13. 13.
    Paschos, G. (2001). Perceptually uniform color spaces for color texture analysis: an empirical evaluation. IEEE Transaction on Image Processing, 10, 932–937.zbMATHCrossRefGoogle Scholar
  14. 14.
    MacQueen, J. B. (1967). Some Methods for classification and Analysis of Multivariate Observations. In Proc. of 5 th Berkeley symp. on mathematical statistics and probability. (vol. 1, pp. 281–297) Berkeley, Univ. of California Press.Google Scholar
  15. 15.
    Aksoy, S., Koperski, K., Tusk, C., Marchisio, G., & Tilton, J. C. (2005). Learning Bayesian classifiers for scene classification with a visual grammar. IEEE Transactions on Geoscience and Remote Sensing, 43, 581–589.CrossRefGoogle Scholar
  16. 16.
    Aksoy, S. (2006). Modeling of remote sensing image content using attributed relational graphs. Lecture Notes in Computer Science, 4109, 475–483.CrossRefGoogle Scholar
  17. 17.
    Tang, H. L., Hanka, R., & Ip, H. H. S. (2003). Histological image retrieval based on semantic content analysis. IEEE Transaction on Information Technology in Biomedicine, 7, 26–36.CrossRefGoogle Scholar
  18. 18.
    Meyer, F. (1994). Topographic distance and watershed lines. Signal Processing, 38, 113–125.zbMATHCrossRefGoogle Scholar
  19. 19.
    Halir, R., & Flusser, J. (1998). Numerically stable direct least squares fitting of ellipses. In Proc. int. conf. in central Europe on computer graphics, visualization and interactive digital media (pp. 125–132).Google Scholar
  20. 20.
    Shim, S., & Choi, T. (2003). Image indexing by modified color co-occurrence matrix. In Proc. of IEEE int. conf. on acoustics, speech, and signal processing (ICASSP).Google Scholar
  21. 21.
    Arvis, V., Debain, C., Berducat, M., & Benassi, A. (2004). Generalization of the co-occurrence matrix for color images: Application to color texture classification. Image Analysis and Stereology, 23(1), 63–72.Google Scholar
  22. 22.
    Kohonen, T. (1997). Self-organizing maps. Heidelberg: Springer.zbMATHGoogle Scholar
  23. 23.
    Fukunaga, K. (1990). Introduction to statistical pattern recognition. Academic.Google Scholar
  24. 24.
    Duda, R. O., Hart, P. E., Stork, G. (2001). Pattern classification. Wiley.Google Scholar
  25. 25.
    Martinez, A. M., & Kak, A. C. (2001). PCA versus LDA. IEEE Transaction on Pattern Analysis and Machine Intelligence, 23, 228–233.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Olcay Sertel
    • 1
    • 2
  • Jun Kong
    • 1
    • 2
  • Umit V. Catalyurek
    • 1
    • 2
  • Gerard Lozanski
    • 3
  • Joel H. Saltz
    • 2
  • Metin N. Gurcan
    • 2
  1. 1.Department of Electrical and Computer EngineeringThe Ohio State UniversityColumbusUSA
  2. 2.Department of Biomedical InformaticsThe Ohio State UniversityColumbusUSA
  3. 3.Department of PathologyThe Ohio State UniversityColumbusUSA

Personalised recommendations