Advertisement

Multi-estimator Full Left Ventricle Quantification Through Ensemble Learning

  • Jiasha Liu
  • Xiang LiEmail author
  • Hui Ren
  • Quanzheng Li
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11395)

Abstract

Cardiovascular disease accounts for 1 in every 4 deaths in United States. Accurate estimation of structural and functional cardiac parameters is crucial for both diagnosis and disease management. In this work, we develop an ensemble learning framework for more accurate and robust left ventricle (LV) quantification. The framework combines two 1st-level modules: direct estimation module and a segmentation module. The direct estimation module utilizes Convolutional Neural Network (CNN) to achieve end-to-end quantification. The CNN is trained by taking 2D cardiac images as input and cardiac parameters as output. The segmentation module utilizes a U-Net architecture for obtaining pixel-wise prediction of the epicardium and endocardium of LV from the background. The binary U-Net output is then analyzed by a separate CNN for estimating the cardiac parameters. We then employ linear regression between the 1st-level predictor and ground truth to learn a 2nd-level predictor that ensembles the results from 1st-level modules for the final estimation. Preliminary results by testing the proposed framework on the LVQuan18 dataset show superior performance of the ensemble learning model over the two base modules.

Keywords

Semantic segmentation Direct estimation Ensemble learning 

References

  1. 1.
    Hundley, W.G., et al.: Society for Cardiovascular Magnetic Resonance guidelines for reporting cardiovascular magnetic resonance examinations. J. Cardiovasc. Magn. Reson. 11, 5 (2009)CrossRefGoogle Scholar
  2. 2.
    Peng, P., Lekadir, K., Gooya, A., Shao, L., Petersen, S.E., Frangi, A.F.: A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging. Magn. Reson. Mater. Phys. Biol. Med. 29, 155–195 (2016)CrossRefGoogle Scholar
  3. 3.
    Ben Ayed, I., Chen, H.-M., Punithakumar, K., Ross, I., Li, S.: Max-flow segmentation of the left ventricle by recovering subject-specific distributions via a bound of the Bhattacharyya measure. Med. Image Anal. 16, 87–100 (2012)CrossRefGoogle Scholar
  4. 4.
    Petitjean, C., Dacher, J.-N.: A review of segmentation methods in short axis cardiac MR images. Med. Image Anal. 15, 169–184 (2011)CrossRefGoogle Scholar
  5. 5.
    Afshin, M., et al.: Regional assessment of cardiac left ventricular myocardial function via MRI statistical features. IEEE Trans. Med. Imaging 33, 481–494 (2014)CrossRefGoogle Scholar
  6. 6.
    Wang, Z., Salah, M.B., Gu, B., Islam, A., Goela, A., Li, S.: Direct estimation of cardiac biventricular volumes with an adapted Bayesian formulation. IEEE Trans. Biomed. Eng. 61, 1251–1260 (2014)CrossRefGoogle Scholar
  7. 7.
    Xue, W., Lum, A., Mercado, A., Landis, M., Warrington, J., Li, S.: Full quantification of left ventricle via deep multitask learning network respecting intra- and inter-task relatedness. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 276–284. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66179-7_32CrossRefGoogle Scholar
  8. 8.
    Xue, W., Islam, A., Bhaduri, M., Li, S.: Direct multitype cardiac indices estimation via joint representation and regression learning. IEEE Trans. Med. Imaging 36, 2057–2067 (2017)CrossRefGoogle Scholar
  9. 9.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, William M., Frangi, Alejandro F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Jiasha Liu
    • 1
  • Xiang Li
    • 2
    Email author
  • Hui Ren
    • 2
    • 4
  • Quanzheng Li
    • 1
    • 2
    • 3
  1. 1.Peking UniversityBeijingChina
  2. 2.MGH/BWH Center for Clinical Data ScienceBostonUSA
  3. 3.Laboratory for Biomedical Image AnalysisBeijing Institute of Big Data ResearchBeijingChina
  4. 4.Heart CenterPeking University People’s HospitalBeijingChina

Personalised recommendations