Skip to main content
SpringerLink
Log in

PAT-CNN: Automatic Segmentation and Quantification of Pericardial Adipose Tissue from T2-Weighted Cardiac Magnetic Resonance Images

  • Conference paper
  • First Online:
Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers (STACOM 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13593))

Abstract

Background: Increased pericardial adipose tissue (PAT) is associated with many types of cardiovascular disease (CVD). Although cardiac magnetic resonance images (CMRI) are often acquired in patients with CVD, there are currently no tools to automatically identify and quantify PAT from CMRI. The aim of this study was to create a neural network to segment PAT from T2-weighted CMRI and explore the correlations between PAT volumes (PATV) and CVD outcomes and mortality.

Methods: We trained and tested a deep learning model, PAT-CNN, to segment PAT on T2-weighted cardiac MR images. Using the segmentations from PAT-CNN, we automatically calculated PATV on images from 391 patients. We analysed correlations between PATV and CVD diagnosis and 1-year mortality post-imaging.

Results: PAT-CNN was able to accurately segment PAT with Dice score/ Hausdorff distances of 0.74 ± 0.03/27.1 ± 10.9 mm, similar to the values obtained when comparing the segmentations of two independent human observers (0.76 ± 0.06/21.2 ± 10.3 mm). Regression models showed that, independently of sex and body-mass index, PATV is significantly positively correlated with a diagnosis of CVD and with 1-year all cause mortality (p-value < 0.01).

Conclusions: PAT-CNN can segment PAT from T2-weighted CMR images automatically and accurately. Increased PATV as measured automatically from CMRI is significantly associated with the presence of CVD and can independently predict 1-year mortality.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 79.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 99.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Benčević, M., Galić, I., Habijan, M., Pižurica, A.: Recent progress in epicardial and pericardial adipose tissue segmentation and quantification based on deep learning: a systematic review. Appl. Sci. 12(10), 5217 (2022). https://doi.org/10.3390/app12105217

    Article  Google Scholar 

  2. Britton, K.A., Massaro, J.M., Murabito, J.M., Kreger, B.E., Hoffmann, U., Fox, C.S.: Body fat distribution, incident cardiovascular disease, cancer, and all-cause mortality. J. Am. Coll. Cardiol. 62(10), 921–925 (2013). https://doi.org/10.1016/J.JACC.2013.06.027

    Article  Google Scholar 

  3. Cai, S., et al.: Cardiac MRI measurements of pericardial adipose tissue volumes in patients on in-centre nocturnal hemodialysis. J. Nephrol. 33(2), 355–363 (2019). https://doi.org/10.1007/s40620-019-00665-4

    Article  Google Scholar 

  4. Cheng, V.Y., et al.: Pericardial fat burden on ECG-gated noncontrast CT in asymptomatic patients who subsequently experience adverse cardiovascular events. JACC Cardiovasc. Imaging 3(4), 352–360 (2010). https://doi.org/10.1016/J.JCMG.2009.12.013

    Article  Google Scholar 

  5. Commandeur, F., et al.: Deep learning for quantification of epicardial and thoracic adipose tissue from non-contrast CT. IEEE Trans. Med. Imaging 37(8), 1835–1846 (2018). https://doi.org/10.1109/TMI.2018.2804799

    Article  Google Scholar 

  6. Davidovich, D., Gastaldelli, A., Sicari, R.: Imaging cardiac fat. Eur. Heart J. - Cardiovasc. Imaging 14(7), 625–630 (2013). https://doi.org/10.1093/EHJCI/JET045

    Article  Google Scholar 

  7. Ding, X., et al.: Automated pericardial fat quantification from coronary magnetic resonance angiography: feasibility study. J. Med. Imaging 3(1), 014002 (2016). https://doi.org/10.1117/1.jmi.3.1.014002

  8. Fitzgibbons, T.P., Czech, M.P.: Epicardial and perivascular adipose tissues and their influence on cardiovascular disease: basic mechanisms and clinical associations. J. Am. Heart Assoc. 3(2) (2014). https://doi.org/10.1161/JAHA.113.000582

  9. Grosgeorge, D., Petitjean, C., Dacher, J.N., Ruan, S.: Graph cut segmentation with a statistical shape model in cardiac MRI. Comput. Vis. Image Underst. 117(9), 1027–1035 (2013). https://doi.org/10.1016/j.cviu.2013.01.014

    Article  Google Scholar 

  10. Henningsson, M., Brundin, M., Scheffel, T., Edin, C., Viola, F., Carlhäll, C.J.: Quantification of epicardial fat using 3D cine Dixon MRI. BMC Med. Imaging 20(1), 1–9 (2020). https://doi.org/10.1186/s12880-020-00478-z

    Article  Google Scholar 

  11. Howard, J.P., et al.: Automated analysis and detection of abnormalities in transaxial anatomical cardiovascular magnetic resonance images: a proof of concept study with potential to optimize image acquisition. Int. J. Cardiovasc. Imaging 37(3), 1033–1042 (2020). https://doi.org/10.1007/s10554-020-02050-w

    Article  Google Scholar 

  12. Kellman, P., et al.: Multiecho dixon fat and water separation method for detecting fibrofatty infiltration in the myocardium. Magn. Reson. Med. 61(1), 215–221 (2009). https://doi.org/10.1002/mrm.21657

    Article  Google Scholar 

  13. Kerfoot, E., Clough, J., Oksuz, I., Lee, J., King, A.P., Schnabel, J.A.: Left-ventricle quantification using residual U-net. In: Pop, M., et al. (eds.) STACOM 2018. LNCS, vol. 11395, pp. 371–380. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-12029-0_40

    Chapter  Google Scholar 

  14. Kerfoot, E., Puyol Anton, E., Ruijsink, B., Clough, J., King, A.P., Schnabel, J.A.: Automated CNN-based reconstruction of short-axis cardiac MR sequence from real-time image data. In: Stoyanov, D., et al. (eds.) RAMBO/BIA/TIA -2018. LNCS, vol. 11040, pp. 32–41. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00946-5_4

    Chapter  Google Scholar 

  15. Kingma, D., Ba, J.: Adam: a method for stochastic optimization. Comput. Sci. (2014)

    Google Scholar 

  16. Lavie, C.J., Pandey, A., Lau, D.H., Alpert, M.A., Sanders, P.: The present and future obesity and atrial fibrillation prevalence, pathogenesis, and prognosis effects of weight loss and exercise. Technical report (2017). https://doi.org/10.1016/J.JACC.2017.09.002

  17. Liu, J., et al.: Pericardial adipose tissue, atherosclerosis, and cardiovascular disease risk factors the Jackson heart study. Diabetes Care 33(7), 1635–1639 (2010). https://doi.org/10.2337/DC10-0245

    Article  Google Scholar 

  18. Lourenço, A., et al.: Left atrial ejection fraction estimation using SEGANet for fully automated segmentation of CINE MRI. In: Puyol Anton, E., et al. (eds.) STACOM 2020. LNCS, vol. 12592, pp. 137–145. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-68107-4_14

    Chapter  Google Scholar 

  19. Mancas, M., Gosselin, B., Macq, B.: Segmentation using a region-growing thresholding. In: Dougherty, E.R., Astola, J.T., Egiazarian, K.O. (eds.) Image Processing: Algorithms and Systems IV, vol. 5672, pp. 388–398. International Society for Optics and Photonics, SPIE (2005). https://doi.org/10.1117/12.587995

  20. Norouzi, A., et al.: Medical image segmentation methods, algorithms, and applications. IETE Tech. Rev. 31(3), 199–213 (2014). https://doi.org/10.1080/02564602.2014.906861

    Article  Google Scholar 

  21. Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979). https://doi.org/10.1109/TSMC.1979.4310076

    Article  Google Scholar 

  22. Rodrigues, O., Morais, F.F., Morais, N.A., Conci, L.S., Neto, L.V., Conci, A.: A novel approach for the automated segmentation and volume quantification of cardiac fats on computed tomography. Comput. Methods Program. Biomed. 123, 109–128 (2016). https://doi.org/10.1016/J.CMPB.2015.09.017

    Article  Google Scholar 

  23. Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28

    Chapter  Google Scholar 

  24. Weschenfelder, C., Quadros, A., Santos, J., Garofallo, S.B., Marcadenti, A.: Adipokines and adipose tissue-related metabolites, nuts and cardiovascular disease. Metabolites 10(1), 32 (2020)

    Article  Google Scholar 

  25. Yaniv, Z., Lowekamp, B.C., Johnson, H.J., Beare, R.: SimpleITK image-analysis notebooks: a collaborative environment for education and reproducible research. J. Digit. Imaging 31(3), 290–303 (2017). https://doi.org/10.1007/s10278-017-0037-8

    Article  Google Scholar 

  26. Yeung, M., Sala, E., Schönlieb, C.B., Rundo, L.: Unified focal loss: generalising dice and cross entropy-based losses to handle class imbalanced medical image segmentation. Comput. Med. Imaging Graphics 95, 102026 (2022). https://doi.org/10.1016/J.COMPMEDIMAG.2021.102026

Download references

Acknowledgements

This work was supported by the British Heart Foundation Centre of Research Excellence at Imperial College London (RE/18/4/34215).

Author information

Authors and Affiliations

  1. Department of Metabolism, Digestion and Reproduction, Imperial College London, London, UK

    Zhuoyu Li

  2. Department of Computing, Imperial College London, London, UK

    Camille Petri

  3. National Heart and Lung Institute, Imperial College London, London, UK

    Camille Petri, James Howard, Graham Cole & Marta Varela

Authors
  1. Zhuoyu Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Camille Petri
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. James Howard
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Graham Cole
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Marta Varela
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Marta Varela .

Editor information

Editors and Affiliations

  1. Pompeu Fabra University, Barcelona, Spain

    Oscar Camara

  2. King’s College London, London, UK

    Esther Puyol-Antón

  3. Imperial College London, London, UK

    Chen Qin

  4. Inria, Sophia Antipolis, France

    Maxime Sermesant

  5. King’s College London, London, UK

    Avan Suinesiaputra

  6. Fudan University, Shanghai, China

    Shuo Wang

  7. King’s College London, London, UK

    Alistair Young

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Li, Z., Petri, C., Howard, J., Cole, G., Varela, M. (2022). PAT-CNN: Automatic Segmentation and Quantification of Pericardial Adipose Tissue from T2-Weighted Cardiac Magnetic Resonance Images. In: Camara, O., et al. Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers. STACOM 2022. Lecture Notes in Computer Science, vol 13593. Springer, Cham. https://doi.org/10.1007/978-3-031-23443-9_33

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-23443-9_33

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-23442-2

  • Online ISBN: 978-3-031-23443-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Societies and partnerships

Search

Navigation