Advertisement

Fully Automated Segmentation of Abnormal Heart in New Born Babies

  • Attifa Bilal
  • Aslam MuhammadEmail author
  • Martinez-Enriquez Ana Maria
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10633)

Abstract

We show an intuitive method to segment the heart chambers and epicardial surfaces, including the colossal vessel dividers, in pediatric cardiovascular in Machine Resonance Imaging (MRI) of inherent coronary illness. Exact entire heart division is important to make tolerant specific 3D heart models for surgical arranging within the sight of complex heart abandons. Anatomical changeability because of inborn deformities blocks completely programmed chart book based division. Our intelligent division technique abuses master segmentations of a little arrangement of short-hub cut locales to consequently delineate the rest of the volume utilizing patch-based division. We too research the capability of dynamic figuring out how to naturally request client contribution to zones where division blunder is probably going to be high. Approval is performed on four subjects with twofold outlet right ventricle, a severe inherent heart imperfection. We demonstrate that procedures asking the client to physically fragment districts of enthusiasm inside short-hub cuts yield higher exactness with less client contribution than those questioning whole short-axis cuts. The proposed system validates the technique of automatic segmentation of heart using the combination of Dice matrices and active appearance model techniques which help the doctors to recognize heart disease.

Keywords

Congenital heart disease Abnormal heart segmentation Automatic detection of disease in MRI images 

References

  1. 1.
    Gabriel Steg, P.: New developments in non-invasive cardiac imaging: critical assessment of the clinical role of cardiac magnetic resonance imaging. Eur. Heart J. 19(9), 1282–1286 (1998)CrossRefGoogle Scholar
  2. 2.
    World Health Organization of cardiovascular disease. www.who.int/cardiovascular_diseases/en
  3. 3.
    Schmauss, D., Haeberle, S., Hagl, C., Sodian, R.: Three-dimensional printing in cardiac surgery and interventional cardiology: a single-centre experience. Eur. J. Cardio. -Thorac. 47, 1044–1052 (2014)CrossRefGoogle Scholar
  4. 4.
    Jacobs, S., Grunert, R., Mohr, F.W., Falk, V.: 3D-Imaging of cardiac structures using 3D heart models for planning in heart surgery: a preliminary study. Interact. Cardiovasc. Thorac. Surg. 7(1), 6–9 (2008)CrossRefGoogle Scholar
  5. 5.
    Valverde, I., et al.: Three-dimensional patient specific cardiac model for surgical planning in Nikaidoh procedure. Cardiol. Young 25(4), 698–704 (2014)CrossRefGoogle Scholar
  6. 6.
    Zhuang, X.: Challenges and methodologies of fully automatic whole heart segmentation: a review. J. Healthc. Eng. 4(3), 371–408 (2013)CrossRefGoogle Scholar
  7. 7.
    Arrington, C.B., et al.: Exome analysis of a family with pleiotropic congenital heart disease. Circ Cardiovasc Genet. 5, 175–182 (2012)CrossRefGoogle Scholar
  8. 8.
    Mitchell, S., Lelieveldt, B., Geest, R., Schaap, J., Reiber, J., Sonka, M.: Segmentation of cardiac MR image: an active appearance model approach. In: Medical Imaging 2000: Image Processing, San Diego, CA. SPIE, vol. 1. SPIE (2000)Google Scholar
  9. 9.
    Yifrah, S., Zadicario, E., Ju, T., Cohen-Or, D.: An algorithm for suggesting delineation planes for interactive segmentation. In: IEEE International Symposium on Biomedical Imaging, pp. 361–364. IEEE Press, New York (2014)Google Scholar
  10. 10.
    Veeraraghavan, H., Miller, J.: Active learning guided interactions for consistent image segmentation with reduced user interactions. In: IEEE International Symposium on Biomedical Imaging, pp. 1645–1648. IEEE Press, New York (2011)Google Scholar
  11. 11.
    Veeraraghavan, H., Miller, J.: Active learning guided interactions for consistent image segmentation with reduced user interactions. In: Biomed Imaging, pp. 1645–1648. IEEE (2011)Google Scholar
  12. 12.
    Settles, B.: Active Learning. Morgan & Claypool Publishers, San Rafael (2012)zbMATHGoogle Scholar
  13. 13.
    Digilio, M.C., Marino, B., Giannotti, A., Dallapiccola, B., Opitz, J.M.: Specific congenital heart defects in RSH/Smith-lemli-opitz syndrome: postulated involvement of the sonic hedgehog pathway in syndromes with postaxial polydactyly or heterotaxia. Birth Defects Res. Part A: Clin. Mol. Teratol. 67, 149–153 (2003)CrossRefGoogle Scholar
  14. 14.
    Shi, W., et al.: Automatic segmentation of different pathologies from cardiac cine MRI using registration and multiple component EM estimation. In: Metaxas, D.N., Axel, L. (eds.) FIMH 2011. LNCS, vol. 6666, pp. 163–170. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-21028-0_21CrossRefGoogle Scholar
  15. 15.
    Wang, B., et al.: 4D active cut: an interactive tool for pathological anatomy modeling. In: IEEE International Symposium on Biomedical Imaging, pp. 529–532. IEEE Press, New York (2014)Google Scholar
  16. 16.
    Hirayama, Y.K., et al.: Phenotypes with GATA4/NKX2.5 mutations in familial atrial septal defect. Am. J. Med. Genet. A. 135(4), 47–52 (2005)CrossRefGoogle Scholar
  17. 17.
    Valverde, I., et al.: Three-dimensional patient-specific cardiac model for surgical planning in Nikaidoh procedure. Cardiol. Young 25(4), 698–704 (2014)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Attifa Bilal
    • 1
  • Aslam Muhammad
    • 2
    Email author
  • Martinez-Enriquez Ana Maria
    • 3
  1. 1.Department of CS and ITSuperior UniversityLahorePakistan
  2. 2.Department of CSUETLahorePakistan
  3. 3.Department of CSCINVESTAVD.F. MexicoMexico

Personalised recommendations