Artículos

 

Combined Hierarchical Watershed Segmentation and SVM Classification for Pap Smear Cell Nucleus Extraction

 

Extracción de núcleos de células en imágenes de la prueba de Papanicolaou usando watershed jerárquico y máquinas de vectores soporte

 

Maykel Orozco-Monteagudo¹, Cosmin Mihai², Hichem Sahli ^{2, 3}, and Alberto Taboada-Crispi ¹

 

¹ Centro de Estudios de Electrónica y Tecnologías de la Información (CEETI), Universidad Central de Las Villas, Santa Clara, Cuba morozco@uclv.edu.cu, ataboada@uclv.edu.cu.

² Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel, Brussels, Belgium cmihai@etro.vub.ac.be.

³ Interuniversity Microelectronics Centre (IMEC), Leuven, Belgium hsahli@etro.vub.ac.be.

 

Article received on 30/04/2011.
Accepted on 29/02/2012.

 

Abstract

In this paper, we propose a two-phase approach to nuclei segmentation/classification in Pap smear test images. The first phase, the segmentation phase, includes a morphological algorithm (watershed) and a hierarchical merging algorithm (waterfall). In the merging step, waterfall uses spectral and shape information as well as the class information. In the second phase, classification, the goal is to obtain nucleus regions and cytoplasm areas by classifying the regions resulting from the first phase based on their spectral and shape features, merging of the adjacent regions belonging to the same class. Between the two phases, three unsupervised segmentation quality criteria were tested in order to determine the best one selecting the best level after merging. The classification of individual regions is obtained using a Support Vector Machine (SVM) classifier. The segmentation and classification results are compared to the segmentation provided by expert pathologists and demonstrate the efficacy of the proposed method.

Keywords. Microscopic images, cell segmentation, watershed, SVM.

 

Resumen

En el presente trabajo se presenta un método en dos etapas para la segmentación y clasificación de núcleos de células en imágenes tomadas de la prueba de Papanicolaou. La primera etapa, la etapa de segmentación, está formada por un algoritmo morfológico (watershed o marcas de agua) y un algoritmo jerárquico de mezclado (waterfall o salto de agua). Para realizar el mezclado de regiones, waterfall usa información espectral, de forma y de las regiones que se separarán. En la segunda etapa, la etapa de clasificación, el objetivo es obtener los núcleos a partir de las clasificaciones de las regiones obtenidas en la primera etapa. Antes de realizar la clasificación, fueron probadas tres medidas no supervisadas de calidad de la segmentación para determinar el mejor resultado de la mezcla de regiones. La clasificación de las regiones se realizó usando Máquinas de Vector Soporte. Los resultados fueron comparados con las segmentaciones realizadas por patólogos demostrándose la eficacia del método propuesto.

Palabras clave. Segmentación, imágenes microscópicas, segmentación de células, marcas de agua, máquinas de vector soporte.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

References

1. Angulo, J. & Serra, J. (2005). Segmentación de imágenes en color utilizando histogramas bi-variables en espacios color polares luminancia/saturación/matiz. Computación y Sistemas, 8(4), 303–316.         [ Links ]

2. Bak, E., Najarian, K., & Brockway, J.P. (2004). Efficient segmentation framework of cell images in noise environments. 26th Annual International Conference of the IEEE Engineering in Medicineand Biology Society (IEMBS '04), San Francisco, California, USA, 1802–1805.         [ Links ]

3. Bergen, T., Steckhan, D., Wittenberg, T., & Zerfass, T. (2008). Segmentation of leukocytes and erythrocytes in blood smear images. 30th Annual International Conference of the IEEEEngineering in Medicine and Biology Society (EMBS 2008), Vancouver, Canada, 3075–3078.         [ Links ]

4. Beucher, S. & Meyer,F. (1993). The morphological approach to segmentation: the watershed transformation. Mathematical Morphology in Image Processing (433–482). New York: M. Dekker.         [ Links ]

5. Boland, M.V. & Murphy, R.F. (2001). A neural network classifier capable of recognizing the patterns of all major subcellular structures in fluorescence microscope images of HeLa cells. Bioinformatics, 17(12), 1213–1223.         [ Links ]

6. Borsotti, M., Campadelli, P., & Schettini, R. (1998). Quantitative evaluation of color image segmentation results. Pattern Recognition Letters, 19(8), 741–747.         [ Links ]

7. Calderero, F. & Marques, F. (2008). General region merging approaches based on information theory statistical measures. 15th IEEE International Conference on Image Processing (ICIP 2008), San Diego, CA, USA, 3016–3019.         [ Links ]

8. Canu, S., Grandvalet, Y., & Rakotomamonjy, A. (2003). SVM and Kernel Methods MATLAB Toolbox. Perception de Systemes et Information, INSA de Rouen, France.         [ Links ]

9. Cohen, L., Vinet, L., Sander, P.T., & Gagalowicz, A. (1989). Hierarchical regional based stereo matching. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'89), San Diego, CA, USA, 416–421.         [ Links ]

10. Cristianini, N. & Shawe-Taylor, J.(2000). An Introduction to Support Vector Machines and other kernel-based learning methods. Cambridge; New York: Cambridge University Press.         [ Links ]

11. Geerinck, T., Mihai, C., Jabloun, M., Vanhamel, I., & Sahli, H. (2009). Multi-scale image analysis of satellite data using perceptual grouping. IEEE International Geoscience and Remote Sensing Symposium.         [ Links ]

12. Geerinck, T., Sahli, H., Henderickx, D., Vanhamel, I., & Enescu, V. (2009). Modeling Attention and Perceptual Grouping to Salient Objects. Attention in Cognitive. Lecture Notes in Computer Science, 5395, 166–182.         [ Links ]

13. Jantzen, J., Norup, J., Dounias, G., & Bjerregaard, B. (2005). Pap-smear Benchmark Data for Pattern Classification. Nature inspired Smart Information Systems (NiSIS 2005), Albufeira, Portugal, 1–9.         [ Links ]

14. Jennrich, R.I. & Sampson, P. (1960). Stepwise discriminant analysis. Mathematical methods for digital computers, 339-358.         [ Links ]

15. Kale, A. & Aksoy, S. (2010). Segmentation of Cervical Cell Images. 20th International Conference on Pattern Recognition (ICPR). Istanbul, Turkey, 2399–2402.         [ Links ]

16. Lezoray, O. & Cardot, H. (2002). Cooperation of color pixel classification schemes and color watershed: a study for microscopic images. IEEE Transactions on Image Processing, 11(7), 783–789.         [ Links ]

17. Liu, J. & Yang, Y.H. (1994). Multiresolution color image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(7), 689–700.         [ Links ]

18. Lucchi, A., Smith, K., Achanta, R., Lepetit, V., & Fua, P. (2010). A Fully Automated Approach to Segmentation of Irregularly Shaped Cellular Structures in EM Images. 13th International Conference on Medical Image Computing and Computer-Assisted Intervention, Part II (MICCAI'10), Beijing, China, 463–471.         [ Links ]

19. Munkres, J. (1957). Algorithms for the assignment and transportation problems. Journal of the Society for Industrial and Applied Mathematics, 5(1), 32–38.         [ Links ]

20. Pantanowitz, L., Hornish, M., & Goulart, R.A. (2010). The impact of digital imaging in the field of cytopathology. Cytojournal, 6(6).         [ Links ]

21. Papanicolaou, G.N. & Traut, H.F. (1943). Diagnosis of uterine cancer by the vaginal smear. Yale Journal of Biology and medicine, 15(6), 924.         [ Links ]

22. Platt, J.C. (2000). Probabilities for SV Machines. Advances in large margin classifiers (61–74), Cambridge, Mass.: MIT Press.         [ Links ]

23. Ricketts, I.W., Banda-Gamboa, H., Cairns, A.Y., & Hussein, K. (1992). Automatic classification of cervical cells-using the frequency domain. IEE Colloquium on Applications of Image Processing in Mass Health Screening, London, UK, 9/1–9/4.         [ Links ]

24. Roerdink, J.B.T.M. & Meijster, A. (2000). The watershed transform: Definitions, algorithms and parallelization strategies. Fundamenta Informaticae-Special issue on Mathematical morphology, 41(1-2), 187–228.         [ Links ]

25. Rosenberger, C.(1999). Mise en oeuvre d'un systeme adaptatif de segmentation d'images. Thèse de doctorat, Universite de Rennes 1, Rennes, Francia.         [ Links ]

26. Walker, R.F. & Jackway, P.T. (1996). Statistical geometric features-extensions for cytological texture analysis. 13th International Conference on Pattern Recognition, Vienna, Austria, 2, 790–794.         [ Links ]

27. Zenzo, S.D. (1986). A note on the gradient of a multi-image. Computer Vision, Graphics, Image Processing, 33(1), 116–125.         [ Links ]

28. Zijdenbos, A.P., Dawant, B.M., Margolin, R.A., & Palmer, A.C. (1994). Morphometric analysis of white matter lesions in MR images: method and validation. IEEE Transactions on Medical Imaging, 13(4), 716–724.         [ Links ]