Advertisement

Learning Interpretable Anatomical Features Through Deep Generative Models: Application to Cardiac Remodeling

  • Carlo Biffi
  • Ozan Oktay
  • Giacomo Tarroni
  • Wenjia Bai
  • Antonio De Marvao
  • Georgia Doumou
  • Martin Rajchl
  • Reem Bedair
  • Sanjay Prasad
  • Stuart Cook
  • Declan O’Regan
  • Daniel Rueckert
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11071)

Abstract

Alterations in the geometry and function of the heart define well-established causes of cardiovascular disease. However, current approaches to the diagnosis of cardiovascular diseases often rely on subjective human assessment as well as manual analysis of medical images. Both factors limit the sensitivity in quantifying complex structural and functional phenotypes. Deep learning approaches have recently achieved success for tasks such as classification or segmentation of medical images, but lack interpretability in the feature extraction and decision processes, limiting their value in clinical diagnosis. In this work, we propose a 3D convolutional generative model for automatic classification of images from patients with cardiac diseases associated with structural remodeling. The model leverages interpretable task-specific anatomic patterns learned from 3D segmentations. It further allows to visualise and quantify the learned pathology-specific remodeling patterns in the original input space of the images. This approach yields high accuracy in the categorization of healthy and hypertrophic cardiomyopathy subjects when tested on unseen MR images from our own multi-centre dataset (100%) as well on the ACDC MICCAI 2017 dataset (90%). We believe that the proposed deep learning approach is a promising step towards the development of interpretable classifiers for the medical imaging domain, which may help clinicians to improve diagnostic accuracy and enhance patient risk-stratification.

References

  1. 1.
    Cohn, J.N., Ferrari, R., Sharpe, N.: Cardiac remodeling concepts and clinical implications: a consensus paper from an international forum on cardiac remodeling. J. Am. Coll. Cardiol. 35(3), 569–582 (2000)CrossRefGoogle Scholar
  2. 2.
    Yancy, C.W., et al.: 2013 ACCF/AHA guideline for the management of heart failure: a report of the American College of Cardiology Foundation/American Heart Association Task Force on Practice Guidelines. J. Am. Coll. Cardiol. 62(16), e147–239 (2013)CrossRefGoogle Scholar
  3. 3.
    Captur, G., et al.: The embryological basis of subclinical hypertrophic cardiomyopathy. Sci. Rep. 6, 27714 (2016)CrossRefGoogle Scholar
  4. 4.
    Authors/Task Force Members, Elliott, P.M., et al.: 2014 ESC Guidelines on diagnosis and management of hypertrophic cardiomyopathy: the Task Force for the Diagnosis and Management of Hypertrophic Cardiomyopathy of the European Society of Cardiology (ESC). Eur. Heart J. 35(39), 2733–79 (2014)Google Scholar
  5. 5.
    Petersen, S.E., et al.: Imaging in population science: cardiovascular magnetic resonance in 100,000 participants of UK Biobank-rationale, challenges and approaches. J. Cardiovasc. Magn. Reson. 15(1), 46 (2013)CrossRefGoogle Scholar
  6. 6.
    Narula, S., Shameer, K., Omar, A.M., Dudley, J.T., Sengupta, P.P.: Machine-learning algorithms to automate morphological and functional assessments in 2D echocardiography. J. Am. Coll. Cardiol. 68(21), 2287–2295 (2016)CrossRefGoogle Scholar
  7. 7.
    Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 20 December 2013
  8. 8.
    Medrano-Gracia, P., Cowan, B.R., Suinesiaputra, A., Young, A.A.: Atlas-based anatomical modeling and analysis of heart disease. Drug Discov. Today Dis. Models 1(14), 33–9 (2014)CrossRefGoogle Scholar
  9. 9.
    Bai, W., et al.: A bi-ventricular cardiac atlas built from 1000+ high resolution MR images of healthy subjects and an analysis of shape and motion. Med. Image Anal. 26(1), 133–45 (2015)CrossRefGoogle Scholar
  10. 10.
    Remme, E.W., Young, A.A., Augenstein, K.F., Cowan, B., Hunter, P.J.: Extraction and quantification of left ventricular deformation modes. IEEE Trans. Biomed. Eng. 51(11), 1923–1931 (2004)CrossRefGoogle Scholar
  11. 11.
    Ardekani, S., et al.: Computational method for identifying and quantifying shape features of human left ventricular remodeling. Ann. Biomed. Eng. 37(6), 1043–54 (2009)CrossRefGoogle Scholar
  12. 12.
    Zhang, X., et al.: Atlas-based quantification of cardiac remodeling due to myocardial infarction. PLoS One 9(10), e110243 (2014)CrossRefGoogle Scholar
  13. 13.
    Suinesiaputra, A., et al.: Statistical shape modeling of the left ventricle: myocardial infarct classification challenge. IEEE J. Biomed. Health Inform. 22(2), 503–515 (2017)CrossRefGoogle Scholar
  14. 14.
    Zhang, X., et al.: Orthogonal decomposition of left ventricular remodeling in myocardial infarction. GigaScience 6(3), 1–5 (2017)CrossRefGoogle Scholar
  15. 15.
    Shakeri, M., Lombaert, H., Tripathi, S., Kadoury, S.: Deep spectral-based shape features for Alzheimer’s disease classification. In: Reuter, M., Wachinger, C., Lombaert, H. (eds.) SeSAMI 2016. LNCS, vol. 10126, pp. 15–24. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-51237-2_2. Alzheimers Disease NeuroimagingCrossRefGoogle Scholar
  16. 16.
    Rueckert, D., Sonoda, L.I., Hayes, C., Hill, D.L.G., Leach, M.O., Hawkes, D.J.: Non-rigid registration using free-form deformations: application to breast MR images. IEEE Trans. Med. Imaging 18(8), 712–721 (1999)CrossRefGoogle Scholar
  17. 17.
    Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput. 15(6), 1373–96 (2003)CrossRefGoogle Scholar
  18. 18.
    Desai, M.Y., Ommen, S.R., McKenna, W.J., Lever, H.M., Elliott, P.M.: Imaging phenotype versus genotype in hypertrophic cardiomyopathy. Circ. Cardiovasc. Imaging 4(2), 156–168 (2011)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Carlo Biffi
    • 1
    • 2
  • Ozan Oktay
    • 1
  • Giacomo Tarroni
    • 1
  • Wenjia Bai
    • 1
  • Antonio De Marvao
    • 2
  • Georgia Doumou
    • 2
  • Martin Rajchl
    • 1
  • Reem Bedair
    • 2
  • Sanjay Prasad
    • 3
  • Stuart Cook
    • 3
    • 4
  • Declan O’Regan
    • 2
  • Daniel Rueckert
    • 1
  1. 1.Biomedical Image Analysis GroupImperial College LondonLondonUK
  2. 2.MRC London Clinical Sciences CentreImperial College LondonLondonUK
  3. 3.National Heart & Lung InstituteImperial College LondonLondonUK
  4. 4.Duke-NUS Graduate Medical SchoolSingaporeSingapore

Personalised recommendations