SciELO - Scientific Electronic Library Online

vol.9 issue2EDITORIALSearching for Qualitative and Quantitative Features for the Efficient Modification of Scale in Vector Layers author indexsubject indexsearch form
Home Pagealphabetic serial listing  

Services on Demand




Related links

  • Have no similar articlesSimilars in SciELO


Computación y Sistemas

Print version ISSN 1405-5546

Comp. y Sist. vol.9 n.2 México Oct./Dec. 2005




Segmentation of Blood Vessels Based on a Threshold that Combines Statistical and Scale Space Filters


Segmentación de Vasos Sanguíneos Basada en un Umbral que Combina Filtros Espaciales Estadísticos


Roberto Rodríguez


Institute of Cybernetics, Mathematics and Physics (ICIMAF)
Digital Signal Processing Group
Calle 15 no. 551 e/ C y D, CP 10 400, Ciudad de la Habana, CUBA




Article received on October 25, 2004; accepted on July 07, 2005



This paper presents a strategy for segmenting blood vessels based on the threshold, which–combines statistic and scale space filter. By incorporating statistical information, the strategy is capable of reducing over–segmentation. We propose a three stage strategy which involves: (1) optimal selection of window size; (2) optimal selection of scale and (3) segmentation process. We compared our strategy to two commonly used thresholding techniques. Experimental results showed that our method is much more robust and accurate. Our strategy suggested a modification to Otsu's method. In this application the important information to be extracted from images is only the number of blood vessels present in the images. The proposed strategy was tested on manual segmentation, where segmentation errors less than 3% for false positives and 0% for false negatives are observed. The work presented in this paper is a part of a global image analysis process. Therefore, these images will be subject to a further morphometrical analysis in order to diagnose and predict automatically malign tumors.

Keywords: Thresholding method, Scale–space filter, Image segmentation, Angiogenesis process.



Este artículo presenta una estrategia para la segmentación de vasos sanguíneos basada en el umbral, la cual combina estadística y filtro de espacio escala. Al incorporar información estadística la estrategia es capaz de reducir la sobre segmentación. Nosotros proponemos una estrategia consistente de tres estados, la cual involucra: (1) selección óptima del tamaño de ventana; (2) óptima selección de la escala y (3) el proceso de segmentación. Nuestra estrategia es comparada con dos técnicas comúnmente muy usadas las cuales hacen uso del umbral. Los resultados experimentales mostraron que nuestro método es mucho más robusto y exacto. Nuestra estrategia sugirió una modificación al método de Otsu. En esta aplicación la información importante a extraer de las imágenes es solamente el número de vasos sanguíneos presentes en ellas. Los resultados de la estrategia propuesta fueron comparados con aquellos obtenidos a través de la segmentación manual, donde el error de segmentación para los falsos positivos fue menor que el 3% y para los falsos negativos fue del 0%. El trabajo presentado en este artículo es parte de un proceso global de análisis de imágenes. Por tanto, estas imágenes serán sujetas a un adicional análisis morfométrico para diagnósticar y pronósticar automáticamente tumores malignos.

Palabras Clave: Método a través del umbral, Filtro espacio escala, Segmentación de imágenes, Proceso de angiogénesis.





The authors would like to thank Dr. Roberto Wong from "Dr. Carlos J. Finlay" hospital, Cuba, for facilitating the test images and accepting this project.



1. Fu, K. S.; and Mui, J. K., "A survey on image segmentation," Pattern Recognition, 13: 3–16 (1981).        [ Links ]

2. Pratikakis, I., "Watershed–driven image segmentation," Ph.D thesis, (Vrije Universiteit Brussel, 1998).        [ Links ]

3. Sijbers, J. et al., "Watershed based segmentation of 3d MR Data for Volume Ouantization, " Magnetic Resonance Imaging, 15(6) (1997)        [ Links ]

4. Lim, Young W.; and Lee, Sang U., "On the color image segmentation algorithm based on the thresholding and the fuzzy c–means techniques," Pattern Recognition, 21(9): 935–952 (1990)        [ Links ]

5. Shareef, N.; and Wang, D. L., "Segmentation of medical images using Legion," IEEE Trans. on Medical Imaging, 18 (1) (1999).        [ Links ]

6. Sahoo, P. K. et al., "A survey of thresholding techniques," Computer Vision, Graphics, and Image Processing, 41: 233–260 (1988).        [ Links ]

7. Rodríguez, Roberto M. et al., "Color segmentation applied to study of the angiogenesis Part I, "Journal of Intelligent and Robotic System, 34 (1): 83–97 (2002).        [ Links ]

8. Rodríguez, Roberto; Teresa, E. A.; and Ingrid, C. B., "A strategy for reduction of noise in segmented images. Its use in the study of angiogenesis," Journal of Intelligent and Robotic System, 33 (1): 99–112 (2002).        [ Links ]

9. Otsu, N., "A threshold selection method from grey level histogram", IEEE Trans. Systems Man Cybernet, SMC–8: 62–66 (1978).        [ Links ]

10. Weickert, J.; Ishikawa, S.; and Imiya, A., "On the History of Gaussian Scale–Space Axiomatic", in Gaussian Scale–space theory, edited by J. Sporring et. al., (Netherlands: Kluwer Academic Publishers, 1997) 45–59.        [ Links ]

11. Boschner, B. H. et al., "Angiogenesis in bladder cancer: relationship between microvessel density and tumor prognosis," J. Natl. Cancer Inst., 87, 21 (1): 1603–1612 (1995).        [ Links ]

12. Díaz–Flores, L.; Gutiérrez, R.; and Varela, H., " Angiogenesis: an update," Histol Histopath 9: 807–843 (1992).        [ Links ]

13. León, S. P.; Folkerth, R. D.; and Black, P. M., " Microvessel density is a prognostic indicator for patients with astroglial brain tumors," Cancer, 77, 2, (15): 362–372 (1996).        [ Links ]

14. Semple, J. P.; Welch, W. R.; and Folkman, J., "Tumor angiogenesis and metastasis – correlation in invasive breast carcinoma," N. Engl. J. Med,. 324: 1–8 (1991).        [ Links ]

15. Weidner, N. et al., "Tumor angiogenesis correlates with metastasis in invasive prostate carcinoma," American Journal of Pathology, 143 (2) (1993).        [ Links ]

16. Wu, K.; Gauthier, D.; and Levine, M. D., "Live Cell Image Segmentation," IEEE Transactions on Biomedical Engineering, 42 (1) (1995).        [ Links ]

17. Sharon, A. S., "ANGY: A rule–Based Expert System for Automatic Segmentation of Coronary Vessels From Digital Substrated Angiograms", IEEE Transactions on pattern Analysis and Machine Intelligence, PAMI 8 (2): 188–199 (1986).        [ Links ]

18. Rodríguez, Roberto M., "The interaction and heuristic knowledge in digital image restoration and enhancement. An intelligent system (SIPDI)," Ph.D. Thesis, (Havana: Institute of Technology, 1995).        [ Links ]

19. Rodríguez, R.; Alarcón, T.; and Sánchez, L., "MADIP: Morphometrical Analysis by Digital Image Processing," Proceedings of the IX Spanish Symposium on Pattern Recognition and Image Analysis, (Spain, 2001), I: 291–298. ISBN 84–8021–349–3.        [ Links ]

20. Koenderink, J. J., "The structure of images," Biological Cybernetics, 50: 363–370 (1984).        [ Links ]

21. Lifshitz, L. M.; and Pizer, S. M., "A multiresolution hierarchical approach to image segmentation based on intensity extreme," IEEE Transaction on Pattern Analysis and Machine Intelligence, 12 (6): 529–541 (1990).        [ Links ]

Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License