Artículos

 

Segmentation of Breast Nodules on Ultrasonographic Images Based on Marke d–Controlled Watershed Transform

 

Segmentación de nódulos mamarios en imágenes ultrasonográficas basado en transformada Watershed controlada por marcadores

 

W. Gómez¹, L. Leija¹, W. C. A. Pereira² and A. F. C. Infantosi²

 

¹ Department of Electrical Engineering, CINVESTAV–IPN, Mexico City, Mexico. E–mail: wgomez@cinvestav.mx

² Biomedical Engineering Program – COPPE/UFRJ, Rio de Janeiro, Brazil. E–mail: wagner@peb.ufrj.br

 

Article received on January 07, 2009.
Accepted on October 01, 2009.

 

Abstract

In this article is presented a computerized segmentation method for breast nodules on ultrasonic images. With the goal of removing the speckle while preserving important information from the lesion boundaries, a Gabor filter followed by an anisotropic diffusion filtering are applied to the ultrasonic image. Furthermore, the marker–controlled Watershed transform defines potential boundaries that maximize the Average Radial Derivative function to get the final lesion contour. The segmentation procedure was applied on a database of 50 images and the computer–delineated margins were compared against manual outlines drawn by two radiologist. This comparison was performed by two metrics, which measure the similarity between two compared images: overlap ratio (OR) and normalized residual value (nrv). If there is perfect agreement between both images OR = 1 and nrv = 0. Then, the mean values results, for each metric, were for the first radiologist: OR = 0.87±0.04 and nrv = 0.14±0.06, and for the second radiologist: OR = 0.86±0.06 and nrv = 0.15±0.05.

Keywords: Breast ultrasound, Segmentation, Watershed transform, Average radial derivative.

 

Resumen

En este trabajo se presenta un método computacional para la segmentación de nódulos mamarios en imágenes ultrasónicas. Con el objetivo de remover el ruido multiplicativo (speckle) mientras se preservan los detalles importantes del contorno del tumor, se aplica un filtro de Gabor seguido de un filtro de difusión anisotrópico sobre la ultrasonografía de mama. Posteriormente, la transformada Watershed (línea divisora de aguas) controlada por marcadores define bordes potenciales que maximizan la Media Radial Derivativa para encontrar el contorno final de la lesión. El procedimiento de segmentación se aplicó en un banco de 50 ultrasonografías y la segmentación computarizada obtenida de cada imagen fue comparada contra las delineaciones manuales realizadas por dos radiólogos. Dicha comparación fue cuantificada a través de dos métricas, los cuales miden la similitud entre las imágenes comparadas: razón de superposición (OR) y valor residual normalizado (nrv). En el caso de coincidencia perfecta entre ambas imágenes OR = 1 y nrv = 0. Los valores promedio de cada métrica fueron para el primer radiólogo: OR = 0.87±0.04 y nrv = 0.14±0.06, y para el segundo radiólogo: OR = 0.86±0.06 y nrv = 0.15±0.05.

Palabras clave: Ultrasonido de mama, Segmentación, Transformada Watershed, Media radial derivativa.

 

DESCARGAR ARTÍCULO EN FORMATO PDF 

 

References

1. Alemán–Flores, M., Alemán–Flores, P., Álvarez–León, L., Santana–Montesdeoca, J. M., Fuentes–Pavón, P., & Trujillo–Pino, A. (2003). Computational techniques for the support of breast tumor diagnosis on ultrasound images. Cuadernos del Instituto Universitario de Ciencias y Tecnologías Cibernéticas, ULPGC 27, 1–12.         [ Links ]

2. Alemán–Flores, M., Álvarez, L., & Caselles, V. (2007). Texture–oriented anisotropic filtering and geodesic active contours in breast tumor ultrasound segmentation. Journal of Mathematical Imaging and Vision, 28(1), 81–97.         [ Links ]

3. Alemán–Flores, M., Álvarez, L., & Moreno, R. (2001). Modified Newton filters for edge orientation estimation and shape representation. IASTED International Conference on Signal Processing, Pattern Recognition & Applications. Rhodes, Greece, 27–32.         [ Links ]

4. Alvarenga, A. V., Infantosi, A. F. C., Azevedo, C. M., & Pereira, w. C. A. (2003). Application of morphological operators on the segmentation and contour detection of ultrasound breast images. Brazilian Journal on Biomedical Engineering, 19(2), 91–101.         [ Links ]

5. Bankman, I. N. (2000). Handbook of Medical Imaging: Processing and Analysis. San Diego: Academic Press.         [ Links ]

6. Chang, R. F., Wu, W. J., Moon, W. K., & Chen, D. R. (2005). Automatic ultrasound segmentation and morphology based diagnosis of solid breast tumors. Breast Cancer Research and Treatment, 89(2), 179–185.         [ Links ]

7. Chen, C. M., Chou, Y. H., Chen, C. S., Cheng, J. Z., Ou, Y. F., Yeh, F. C., & Chen, K. W. (2005). Cell–competition algorithm: a new segmentation algorithm for multiple objects with irregular boundaries in ultrasound images. Ultrasound in Medicine & Biology, 31(12), 1647–1664.         [ Links ]

8. Chen, C. M., Lu, H. H., & Lin, Y. C. (2000). An early vision–based snake model for ultrasound image segmentation. Ultrasound in Medicine & Biology, 26(2), 273–285.         [ Links ]

9. Cheng, J. Z., Chen, C. M., Chou, Y. H., Chen, C. S., Tiu, C. M., & Chen, K. W. (2007). Cell–based two–region competition algorithm with a map framework for boundary delineation of a series of 2D ultrasound images. Ultrasound in Medicine & Biology, 33(10), 1640–1650.         [ Links ]

10. Drukker, K., Giger, M. L., Horsch, K., Kupinski, M. A., Vyborny, C. J., & Mendelson, E. B. (2002). Computerized lesion detection on breast ultrasound. Medical Physics, 29(7), 1438–1446.         [ Links ]

11. Gerig, G., Kubler, O., Kikinis, R., & Jolesz, F. A. (1992). Nonlinear anisotropic filtering of MRI data. IEEE Transactions on Medical Imaging, 11(2), 221–232.         [ Links ]

12. Giger, M. L. (2000). Computer–aided diagnosis of breast lesions in medical images. Computing in Science & Engineering, 2(5), 39–45.         [ Links ]

13. Horsch, K., Giger, M. L., Venta, L. A., & Vyborny, C. J. (2001). Automatic segmentation of breast lesions on ultrasound. Medical Physics, 28(8), 1652–1659.         [ Links ]

14. Huang, S. F., Chang, R. F., Chen, D. R., & Moon, W. K. (2004). Characterization of spiculation on ultrasound lesions. IEEE Transactions on Medical Imaging, 23(1), 111–121.         [ Links ]

15. Huang, Y. L. & Chen, D. R. (2004). watershed segmentation for breast tumor in 2–D sonography. Ultrasound in Medicine & Biology, 30(5), 625–632.         [ Links ]

16. Infantosi, A. F. C., Luz, L. M. S., Pereira, W. C. A., & Alvarenga, A. V. (2008). Breast ultrasound segmentation using morphologic operators and a Gaussian function constraint. 14th Nordic–Baltic Conference on Biomedical Engineering and Medical Physics, Riga, Latvia, 20, 520–523.         [ Links ]

17. Infantosi, A. F. C., Silva, J. L., Tierra–Criollo, C. J., & Simpson, D. M. (1998). Avaliação do desempenho de técnicas de interpolação no mapeamento cerebral utilizando simulação. RBE Caderno de Engenharia Biomédica, 14(2), 71–96.         [ Links ]

18. Oshiki, M., Shinomura, R., Mitake, T., Sakurai, T., Matsuura, S., & Harada, J. (2004). Boundary Detection Method for Ultrasound Diagnostic Images Using Region–Growing Approach, Japanese Journal of Applied Physics, 43(7A), 4411–4416.         [ Links ]

19. Parvati, K., Rao, B. S. P., & Das, M. M. (2008). Image segmentation using gray–scale morphology and marker–controlled watershed transformation. Discrete Dynamics in Nature and Society, 2008, 1–8.         [ Links ]

20. Perona, P. & Malik, J. (1990). Scale–space and edge detection using anisotropic diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(10), 629–639.         [ Links ]

21. Roerdink, J. & Meijster, A. (2001). The watershed transform: definitions, algorithms and parallelizations strategies. Fundamenta Informaticae, 41(1–2), 187–228.         [ Links ]

22. Soille, P. (2004). Morphological Image Analysis: Principles and Applications. 2nd ed. Berlin: Springer–Verlag.         [ Links ]

23. Vincent, L. & Soille, P. (1991). Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(6), 583–598        [ Links ]

24. Weldon, T., Higgins, W. E., & Dunn, D. F. (1996). Gabor filter design for multiple texture segmentation. Optical Engineering, 35(10), 2852–2863.         [ Links ]

25. Yu, Y. & Acton, S. T. (2002). Speckle reducing anisotropic diffusion. IEEE Transactions on Medical Imaging, 11(11), 1260–1270.         [ Links ]

26. Zonderland, H. M., Coerkamp, E. G., Hermans, J., Van de Vijver, M. J., & van Voorthuisen, A. E. (1999). Diagnosis of breast cancer: contribution of US as an adjunct to mammography. Radiology, 213(2), 413–422.         [ Links ]