International Conference on Medical Image Computing and Computer-Assisted Intervention

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 pp 493-500 | Cite as

Prospective Identification of CRT Super Responders Using a Motion Atlas and Random Projection Ensemble Learning

  • Devis Peressutti
  • Wenjia Bai
  • Thomas Jackson
  • Manav Sohal
  • Aldo Rinaldi
  • Daniel Rueckert
  • Andrew King
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9351)

Abstract

Cardiac Resynchronisation Therapy (CRT) treats patients with heart failure and electrical dyssynchrony. However, many patients do not respond to therapy. We propose a novel framework for the prospective characterisation of CRT ‘super-responders’ based on motion analysis of the Left Ventricle (LV). A spatio-temporal motion atlas for the comparison of the LV motions of different subjects is built using cardiac MR imaging. Patients likely to present a super-response to the therapy are identified using a novel ensemble learning classification method based on random projections of the motion data. Preliminary results on a cohort of 23 patients show a sensitivity and specificity of 70% and 85%.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Abraham, W.T., et al.: Cardiac resynchronization in chronic heart failure. The New England Journal of Medicine 346(24), 1845–1853 (2002)CrossRefGoogle Scholar
  2. 2.
    António, N., et al.: Identification of ‘super-responders’ to cardiac resynchronization therapy: the importance of symptom duration and left ventricular geometry. Europace 11(3), 343–349 (2009)CrossRefGoogle Scholar
  3. 3.
    Cerqueira, M.D., et al.: Standardized Myocardial Segmentation and Nomenclature for Tomographic Imaging of the Heart. Circulation 105(4), 539–542 (2002)MathSciNetCrossRefGoogle Scholar
  4. 4.
    De Craene, M., et al.: SPM to the heart: Mapping of 4D continuous velocities for motion abnormality quantification. In: 2012 IEEE ISBI, pp. 454–457 (2012)Google Scholar
  5. 5.
    Duchateau, N., et al.: A spatiotemporal statistical atlas of motion for the quantification of abnormal myocardial tissue velocities. Medical Image Analysis 15(3), 316–328 (2011)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Durrant, R., et al.: Random projections as regularizers: learning a linear discriminant from fewer observations than dimensions. Machine Learning, 1–16 (2014)Google Scholar
  7. 7.
    Hoogendoorn, C., et al.: A High-Resolution Atlas and Statistical Model of the Human Heart From Multislice CT. IEEE Transactions on Medical Imaging 32(1), 28–44 (2013)CrossRefGoogle Scholar
  8. 8.
    Jackson, T., et al.: A U-shaped type II contraction pattern in patients with strict left bundle branch block predicts super-response to cardiac resynchronization therapy. Heart Rhythm 11(10), 1790–1797 (2014)CrossRefGoogle Scholar
  9. 9.
    Kim, H., et al.: A weight-adjusted voting algorithm for ensembles of classifiers. Journal of the Korean Statistical Society 40(4), 437–449 (2011)MathSciNetCrossRefMATHGoogle Scholar
  10. 10.
    Shi, W., et al.: Temporal sparse free-form deformations. Medical Image Analysis 17(7), 779–789 (2013)CrossRefGoogle Scholar
  11. 11.
    Tian, Y., et al.: True complete left bundle branch block morphology strongly predicts good response to cardiac resynchronization therapy. Europace 15(10), 1499–1506 (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Devis Peressutti
    • 1
  • Wenjia Bai
    • 2
  • Thomas Jackson
    • 1
  • Manav Sohal
    • 1
  • Aldo Rinaldi
    • 1
  • Daniel Rueckert
    • 2
  • Andrew King
    • 1
  1. 1.Division of Imaging Sciences & Biomedical EngineeringKing’s College LondonLondonUK
  2. 2.Biomedical Image Analysis GroupImperial College LondonLondonUK

Personalised recommendations