Ismail Burak Parlak¹, Ahmet Ademoglu², Salih Murat Egi³, Costantino Balestra⁴, Peter Germonpre⁵, and Alessandro Marroni⁶

¹ Institute of Biomedical Engineering, Bogazici University and the Department of Computer Engineering, Galatasaray University, Ciragan Cad. No:36 34257 Istanbul, TURKEY e–mail: bparlak@gsu.edu.tr.

² Institute of Biomedical Engineering, Bogazici University, Istanbul, TURKEY.

³ Department of Computer Engineering, Galatasaray University, Istanbul, TURKEY.

⁴ Environmental & Occupational Physiology Lab., Haute Ecole Paul Henri Spaak, Brussels, BELGIUM.

⁵ Centre for Hyperbaric Oxygen Therapy, Military Hospital, Brussels, BELGIUM.

Manuscript received May 23, 2011.
Manuscript accepted for publication August 25, 2011.

Abstract

Bubble recognition is a challenging problem in a broad range from mechanics to medicine. These gas–filled structures whose pattern and morphology alter in their surrounding environment would be counted either manually or with computational recognition procedures. In cardiology, user dependent bubble detection and temporal counting in videos require special trainings and experience due to ultra fast movement, inherent noise and video quality. In this study, we propose an efficient recognition routine to increase the objectivity of emboli detection. Firstly, we started to compare five different methods on two synthetic data sets emulating cardiac chamber environment with increasing speckle noise levels. Secondly, real echocardiographic video records were segmented by variational active contours and Left Atria (LA) were extracted. Finally, three successful methods in simulation were applied to LAs in order to reveal candidate bubbles on video frames. Our detection rate of proposed method was 95.7% and the others were 86.2% and 88.3%. We conclude that our approach would be useful in long lasting video processing and would be applied in other disciplines.

Key words: Image thresholding, active contours, venous emboli, echocardiography.

DESCARGAR ARTÍCULO EN FORMATO PDF

REFERENCES

[1] M. Postema and O. H. Gilja, "Contrast–enhanced and targeted ultrasound," World J Gastroenterol, vol. 17, 2011, pp. 28–41.         [ Links ]

[2] K. Tufan, A. Ademoglu, E. Kurtaran, G. Yildiz, S. Aydin and S. M. Egi, "Automatic detection of bubbles in the subclavian vein using doppler ultrasound signals," Aviat Space Environ Med., vol. 77, 2006, pp. 957–962.         [ Links ]

[3] H. Nakamura, Y. Inoue, T. Kudo, N. Kurihara, N. Sugano and T. Iwai, "Detection of venous emboli using doppler ultrasound," European Journal of Vascular & Endovascular Surgery, vol. 35, 2008, pp. 96–101.         [ Links ]

[4] J. Wang, X. Huang and Y. Zou, "Bubble detection of railway castings based on snake model," Jisuanji Gongcheng / Computer Engineering, vol. 36, 2010, pp. 205–207.         [ Links ]

[5] K. H. Chung, M. J Simmons and M. Barigou, "Local gas and liquid phase velocity measurement in a miniature stirred vessel using PIV combined with a new image processing algorithm," Experimental Thermal and Fluid Science, vol. 33, 2009, pp. 743–753.         [ Links ]

[6] D. C. Cheng and H. Burkhardt, "Bubble recognition from image sequences," in Inverse Problems and Experimental Design in Thermal and Mechanical Engineering, Eurotherm Seminar N. 68, 2001.         [ Links ]

[7] D. C. Cheng and H. Burkhardt, "Bubble tracking in image sequences," International Journal of Thermal Sciences, vol. 42, 2003, pp. 647–655.         [ Links ]

[8] D. C. Cheng and H. Burkhardt, "Template–based bubble identification and tracking in image sequences," International Journal of Thermal Sciences, vol. 45, 2006, pp. 321–330.         [ Links ]

[9] M. Honkanen, H. Eloranta and P. Saarenrinne, "Digital imaging measurement of dense multiphase flows in industrial processes," Flow Measurement and Instrumentation, vol. 21, 2010, pp. 25–32.         [ Links ]

[10] M. Honkanen, P. Saarenrinne, T. Stoor and J. Niinimaki, "Recognition of highly overlapping ellipse–like bubble images," Measurement Science and Technology, vol. 16, 2005, pp. 1760–1770.         [ Links ]

[11] O. Eftedal and A. O. Brubakk, "Detecting intravascular gas bubbles in ultrasonic images," Med Biol Eng Comput. vol. 31, 1993, pp. 627–633.         [ Links ]

[12] M. S. Norton, A. J. Sims, D. Morris, T. Zaglavara, M. A. Kenny and A. Murray, "Quantification of echo contrast passage across a patent foramen ovale," in: Computers in Cardiology, IEEE Press, 1998, pp. 89–92.         [ Links ]

[13] P. Germonpre, P. Dendale, P. Unger and C. Balestra, "Patent foramen ovale and decompression sickness in sports divers," Journal of Applied Physiology, vol. 84, 1998, pp. 1622–1626.         [ Links ]

[14] V. Caselles, F. Catte, T. Coll and F. Dibos, "A geometric model for active contours and image processing," Numer. Math. vol. 66, 1993, pp. 1–31.         [ Links ]

[15] T. Chan and L. Vese, "Active contours without edges," IEEE Trans Image Process, vol. 10, 2001, pp. 266–277.         [ Links ]

[16] B. Vemuri and Y. Chen, "Joint image registration and segmentation," in: Geometric Level Set Methods in Imaging, Vision and Graphics, Springer, 2003, pp. 251–259.         [ Links ]

[17] M. Sezgin and B. Sankur, "Survey over image thresholding techniques and quantitative performance evaluation," in: Journal of Electronic Imaging, vol. 13, 2004, pp. 146–165.         [ Links ]

[18] N. Otsu, "A thresholding selection method from gray–level histogram," IEEE Transactions on Systems, Man and Cybernetics, vol. 9, 1979, pp. 62–66.         [ Links ]

[19] J. C. Yen, F. J. Chang and S. Chang, "A new criterion for automatic multilevel thresholding," IEEE Trans. Image Process. vol. 4, 1995, pp. 370–378.         [ Links ]

[20] N. Ramesh, J. H. Yoo and I. K. Sethi, "Thresholding based on histogram approximation," IEEE Proceedings Vision, Image and Signal Process. vol. 142, 1995, pp. 271–279.         [ Links ]

[21] A. Beghdadi, A. L. Negrate and P. V. De Lesegno, "Entropic thresholding using a block source model," Graphical Models in Image Processing vol. 57, 1995, pp. 197–205.         [ Links ]