Advertisement

Anatomical structure segmentation from early fetal ultrasound sequences using global pollination CAT swarm optimizer–based Chan–Vese model

  • M. A. FeminaEmail author
  • S. P. Raajagopalan
Original Article

Abstract

The structure of an early fetal heart provides essential information for the diagnosis of fetus defects. Accurate segmentation of anatomical structure is a major challenging task because of the small size, low signal-to-noise ratio, and rapid movement of the ultrasound images. In recent years, active contour methods have found applications to ultrasound image segmentation. The familiar region-based Chan–Vese (RCV) model is a strong and flexible technique that is able to segment many types of images compared to other active contours. However, the solution trapping in local minima is the main drawback determined on the RCV model with the exposure of improper initial contours. Also, the RCV model showed poor results with this situation. More probably, the images having large intensity differences between global and local structures usually suffered from this problem. To solve this issue, we develop an improved version of the RCV model which is expected to achieve satisfactory segmentation performance, irrespective of the initial selection of the contour. We have formulated a new and hybrid meta-heuristic optimization algorithm namely global pollination–based CAT swarm (GPCATS) optimizer to solve the fitting energy minimization problem. In the GPCATS method, the global pollination step of the flower pollination algorithm (FPA) is used for improving the distance averaging of the CATS algorithm. The performance of the proposed method was analyzed on different fetal heart ultrasound videos acquired from 12 subjects. Each frame of each video was manually annotated in order to provide labels for training and validating the model. Experimental results of the proposed model proved that the precision of locating boundaries is improved greatly and requires only a reduced number of iterations (75% less) for convergence compared to the traditional RCV model. This proposed method also proved that our model not only enhances the accuracy of locating boundaries but also works stronger robustness than some other active contour methods.

Graphical Abstract

Anatomical structure segmentation from early fetal ultrasound sequences using GPCATS based Chan-Vese Model

Keywords

Congenital heart defect Fetal heart Ultrasound Global pollination CAT swarm Chan–Vese Level set 

Notes

Acknowledgments

We thank our excellent radiological technician, Chennai, for his important input regarding the technical part of this study.

Compliance with ethical standards

This study was conducted with approval from the Ethics Committee of Thasiah Medical Centre, Tamilnadu, India. Written informed consent was obtained from all participants’ guardians.

Conflict of interest

The authors declare that they have no conflict of interest.

References

  1. 1.
    Rueda S, Knight CL, Papageorghiou AT, Noble JA (2015) Feature-based fuzzy connectedness segmentation of ultrasound images with an object completion step. Med Image Anal 26:30–46Google Scholar
  2. 2.
    Mitchell SC, Korones SB, Berendes HW (Mar 1971) Congenital heart disease in 56,109 births: incidence and natural history. Circulation 43(3):323–332Google Scholar
  3. 3.
    Hoffman KL, Kaplan S (2002) The incidence of congenital heart disease. J Am Coll Cardiol 39:1890–1900Google Scholar
  4. 4.
    Allan LD, Chita SK, Sharland GK, Fagg NL, Anderson RH, Crawford DC (1989) The accuracy of fetal echocardiography in the diagnosis of congenital heart disease. Int J Cardiol 25:279–288Google Scholar
  5. 5.
    Maraci MA, Bridge CP, Napolitano R, Papageorghiou A, Noble JA (2017) A framework for analysis of linear ultrasound videos to detect fetal presentation and heartbeat. Med Image Anal 37:22–36Google Scholar
  6. 6.
    Vijayalakshmi S, Sriraam N, Suresh S, Muttan S (2013) Automated region mask for four-chamber fetal heart biometry. J Clin Monit Comput 27(2):205–209Google Scholar
  7. 7.
    Becher R, Wegner RD (2006) Detailed screening for fetal anomalies and cardiac defects at the 11–13 week scan. Ultrasound Obstet Gynecol 27:613–618Google Scholar
  8. 8.
    Osher S, Sethian JA (1988) Fronts propagating with curvature-dependent speed: algorithms based on Hamilton–Jacobi formulation. J Comput Phys 79:12–49Google Scholar
  9. 9.
    Sarti A, Malladi R (1999) A geometric level set model for ultrasound image analysis, in Computing Sciences Directorate Mathematics Department. University of California, Berkeley, CAGoogle Scholar
  10. 10.
    Lin N, Yu W, Duncan JS (2003) Combinative multi-scale level set framework for echocardiographic image segmentation. Med Image Anal 7(4):529–537Google Scholar
  11. 11.
    Paragios N (2003) A level set approach for shape-driven segmentation and tracking of the left ventricle. IEEE Trans Med Imaging 22(6):773–776Google Scholar
  12. 12.
    Chen Y, Huang F, Tagare HD, Murali R, Wilson D, Geiser EA (2003) Using prior shape and intensity profile in medical image segmentation, ICCV, pp. 1117–1124Google Scholar
  13. 13.
    Sarti A, Malladi R, Sethian JA (2000) Subjective surfaces: a method for completion of missing boundaries. PNAS 12(97):6258–6263Google Scholar
  14. 14.
    Corsi C, Borsari M, Sarti A, Lamberti C, Travaglini A, Shiota T, Thomas JD (2001) Left ventricular endocardial surface detection based on real time 3D echocardiographic data. Eur J Ultrasound 13:41–51Google Scholar
  15. 15.
    Corsi C, Saracino G, Sarti A, Lamberti C (2002) Left ventricular volume estimation for real-time-dimensional echocardiography. IEEE Trans Med Imaging 21:1202–1208Google Scholar
  16. 16.
    Chan T, Vese LA (2001) Active contours without edges. IEEE Trans Image Process 10(2):266–277Google Scholar
  17. 17.
    Chunming L, Chiu-Yen K, Gore JC, Zhaohua D (2008) Minimization of region-scalable fitting energy for image segmentation. IEEE Trans Image Process 17(10):1940–1949Google Scholar
  18. 18.
    Chunming L, Chenyang X, Changfeng G, Fox MD (2010) Distance regularized level set evolution and its application to image segmentation. IEEE Trans Image Process 19(12):3243–3254Google Scholar
  19. 19.
    Paragios N, Deriche R (2000) Geodesic active contours and level sets for the detection and tracking of moving objects. IEEE Trans Pattern Anal Mach Intell 22(3):266–280Google Scholar
  20. 20.
    Cremers D, Sochen N, Schnorr C (2003) Towards recognition-based variational segmentation using shape priors and dynamic labeling. In L. Griffith, (ed) Int. Conf. on Scale Space Theories in Computer Vision, volume 2695 of LNCS:388–400, Isle of Skye. SpringerGoogle Scholar
  21. 21.
    Piccoli L, Dahmer A, Scharcanski J, Navaux P (1999) Fetal echocardiographic image segmentation using neural networks, In 7th Int Conf on Imag Proc Appl, volume 2, pages 507–511, ManchesterGoogle Scholar
  22. 22.
    Lassige T, Benkeser P, Fyfe D, Sharma S (2000) Comparison of septal defects in 2d and 3d echocardiography using active contour models. Comput Med Imaging Graph 24(6):377–388Google Scholar
  23. 23.
    Siqueira M, Scharcanski J, Navaux P (2002) Echocardiographic image sequence segmentation and analysis using self-organizing maps. J VLSI Signal Proc SystSignal, Image, Video Technol 32:135–145Google Scholar
  24. 24.
    Dindoyal I, Lambrou T, Deng J, Todd-Pokropek A (2007) Level set snake algorithms on the fetal heart. IEEE International Symposium on Biomedical Imaging. p. 864–7Google Scholar
  25. 25.
    Chen Y, Tagare H, Thiruvenkadam S, Huang F, Wilson D, Gopinath K, Briggs R, Geiser E (2002) Using prior shapes in geometric active contours in a variational framework. Int J Comput Vis 50(3):315–328Google Scholar
  26. 26.
    Cremers D, Tischhauser F, Weickert J, Schnorr C (2002) Diffusion snakes: introducing statistical shape knowledge into the Mumford-Shah functional. Int J Comput Vis 50(3):295–313Google Scholar
  27. 27.
    Chen J, Zhang H, Zhang W, X D, Zhang Y, Li S (2018) Correlated regression feature learning for automated right ventricle segmentation. IEEE J Transl Eng Health Med 6:1–10Google Scholar
  28. 28.
    X D, Zhang W, Zhang H, Chen J, Zhang Y, JC Warrington G, Brahm SL (2018) Deep regression segmentation for cardiac bi-ventricle MR images. IEEE Access 6:3828–3838Google Scholar
  29. 29.
    Zhang H, Gao Z, Xu L, Yu X, Wong KCL, Liu H, Zhuang L, Shi P (2018) A Meshfree representation for cardiac medical image computing. IEEE J Transl Eng Health Med 6:1–12Google Scholar
  30. 30.
    Z Gao Y, Li Y, Sun J, Yang H, Xiong H, Zhang X, Liu WW, Liang D, Li S (2018) Motion tracking of the carotid artery wall from ultrasound image sequences: a nonlinear state-space approach. IEEE Trans Med Imaging 37:273–283Google Scholar
  31. 31.
    Fong KW, Toi A, Salem S, Hornberger LK, Chitayat D, Keating SJ, McAuliffe F, Johnson J-A (2004) Detection of fetal structural abnormalities with US during early pregnancy. Radio Graphics 24:157–174Google Scholar
  32. 32.
    Lin N, Weichuan Y, Duncan JS (2002) Combinative multi-scale level set framework for echocardiographic image segmentation. Springer-Verlag, Berlin, MICCAI 2488, pp 682–689Google Scholar
  33. 33.
    Leventon ME, Grimson WEL, Faugeras O (2002) Statistical shape influence in geodesic active contours. In 5th IEEE EMBS International Summer School on Biomedical Imaging, IEEE, p 8 Google Scholar
  34. 34.
    Li C, Xu C, Gui C, Fox MD (2010) Distance regularized level set evolution and its application to image segmentation. IEEE Trans Image Process, 19(12):3243-3254Google Scholar
  35. 35.
    Çataloluk H, Vehbi Çelebi F (2018) A novel hybrid model for two-phase image segmentation: GSA based Chan-Vese algorithm. Eng Appl Artif Intell 73:22–30Google Scholar
  36. 36.
    Santiago C, Marques JS, Nascimento JC (2013) A robust deformable model for 3D segmentation of the left ventricle from ultrasound data, mathematical methodologies in pattern recognition and machine learning. Springer Proc 30:163–178Google Scholar
  37. 37.
    Gupta D, Anand RS, Tyagi B (2015) A hybrid segmentation method based on Gaussian kernel fuzzy clustering and region based active contour model for ultrasound medical images. Biomed Signal Process Control 16:98–112Google Scholar
  38. 38.
    Yan JY, Zhuang T (Nov. 2003) Applying improved fast marching method to endocardial boundary detection in echocardiographic images. Pattern Recogn Lett 24(15):2777–2784Google Scholar
  39. 39.
    Mishra A, Dutta PK, Ghosh MK (2003) A GA based approach for boundary detection of left ventricle with echocardiographic image sequences. Image Vis Comput 21:967–976Google Scholar
  40. 40.
    Hunter I, Soraghan J, Christie J, Durrani T (1993) Detection of echocardiographic left ventricle boundaries using neural networks. Comput Cardiol 20:201–204Google Scholar
  41. 41.
    Malassiotis S, Strintzis MG (1999) Tracking the left ventricle in echocardiographic images by learning heart dynamics. IEEE Trans Med Imaging 18(3):282–290Google Scholar
  42. 42.
    Boukerroui D, Baskurt A, Noble JA, Basset O (2003) Segmentation of ultrasound images; multi-resolution 2D and 3D algorithm based on global and local statistics. Pattern Recogn Lett 24:779–790Google Scholar
  43. 43.
    Cremers D (2006) Dynamical statistical shape priors for level set based tracking. IEEE Trans Pattern Anal Mach Intell 28(8):1262–1273Google Scholar
  44. 44.
    Rousson M, Paragios N (2008) Prior knowledge, level set representations & visual grouping. Int J Comput Vis 76(3):231–243Google Scholar
  45. 45.
    Skalskia A, Turczaa P, Zieli skib T, Królczykc J, Grodzickic T (2012) Left ventricle USG image segmentation using active contour model. Procedia Comput Sci 1:2723–2732Google Scholar
  46. 46.
    Foulonneau, Charbonnier P, Heitz F (2009) Multi-reference shape priors for active contours. Int J Comput Vis 81(1):68–81Google Scholar
  47. 47.
    Zhang Y, Matuszewski BJ, Histace A, Precioso F (2011) Statistical shape model of Legendre moments with active contour evolution for shape detection and segmentation. In Computer analysis of images and patterns, vol. 6854, pp. 51–58Google Scholar
  48. 48.
    Wojak J, Angelini ED, Bloch I (2010) Introducing shape constraint via Legendre moments in a variational framework for cardiac segmentation on non-contrast CT images. In VISAPP, p 209–214Google Scholar
  49. 49.
    Mohammed NB, Chinnaiya A (2011) Evolution of foetal echocardiography as a screening tool for prenatal diagnosis of congenital heart defects. J Pak Med Assoc 61:904–909Google Scholar
  50. 50.
    Sridevi S, Nirmala S (2016) ANFIS based decision support system for prenatal detection of Truncus Arteriosus congenital heart defect. Appl Soft Comput 46:577-587Google Scholar
  51. 51.
    Mumford D, Shah J (1989) Optimal approximation by piecewise smooth functions and associated variational problems. Commun Pure Appl Math 42:577–685Google Scholar
  52. 52.
    Pavlyukevich I (2007) Lévy flights, non-local search and simulated annealing. J Comput Phys 226(2):1830–1844Google Scholar
  53. 53.
    Pappula L, Ghosh D (2017) Synthesis of linear aperiodic array using Cauchy mutated cat swarm optimization. Int J Electron Commun (AEÜ) 72:52–64Google Scholar
  54. 54.
    Skoullis VI, Tassopoulos IX, Beligiannis GN (2017) Solving the high school timetabling problem using a hybrid cat swarm optimization based algorithm. Applied Soft Computing 52:277–289Google Scholar
  55. 55.
    Sundararaj V (2016) An efficient threshold prediction scheme for wavelet based ECG signal noise reduction using variable step size firefly algorithm. International Journal of Intelligent Engineering and Systems 9(3):117–126Google Scholar
  56. 56.
    Sundararaj V, Muthukumar S, Kumar RS (2018) An optimal cluster formation based energy efficient dynamic scheduling hybrid MAC protocol for heavy traffic load in wireless sensor networks. Comput Secur & Security 77:277–288Google Scholar
  57. 57.
    Sundararaj V (2019) Optimal task assignment in mobile cloud computing by queue based Ant-Bee algorithm. Wirel Pers Commun 104(1):173–197Google Scholar
  58. 58.
    Bhadauria HS, Dewal ML (2014) Intracranial hemorrhage detection using spatial fuzzy c-mean and region-based active contour on brain CT imaging. SIViP 8(2):357–364Google Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2019

Authors and Affiliations

  1. 1.Electrical and Electronics EngineeringKCG College of TechnologyChennaiIndia
  2. 2.Computer Science and EngineeringGKM College of Engineering and TechnologyChennaiIndia

Personalised recommendations