Skip to main content

Validation of a Whole Heart Segmentation from Computed Tomography Imaging Using a Deep-Learning Approach

Abstract

The aim of this study is to develop an automated deep-learning-based whole heart segmentation of ECG-gated computed tomography data. After 21 exclusions, CT acquired before transcatheter aortic valve implantation in 71 patients were reviewed and randomly split in a training (n = 55 patients), validation (n = 8 patients), and a test set (n = 8 patients). A fully automatic deep-learning method combining two convolutional neural networks performed segmentation of 10 cardiovascular structures, which was compared with the manually segmented reference by the Dice index. Correlations and agreement between myocardial volumes and mass were assessed. The algorithm demonstrated high accuracy (Dice score = 0.920; interquartile range: 0.906–0.925) and a low computing time (13.4 s, range 11.9–14.9). Correlations and agreement of volumes and mass were satisfactory for most structures. Six of ten structures were well segmented. Deep-learning-based method allowed automated WHS from ECG-gated CT data with a high accuracy. Challenges remain to improve right-sided structures segmentation and achieve daily clinical application.

Graphical abstract

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Abbreviations

3D:

Tridimensional

WHS:

Whole heart segmentation

CT:

Computed tomography

AI:

Artificial intelligence

TAVI:

Transcatheter aortic valve implantation

PV:

Pulmonary veins

LA:

Left atrium

LVC:

Left ventricular cavity

LVM:

Left ventricular myocardium

Ao:

Aorta

CS:

Coronary sinus

SVC:

Superior vena cava

RA:

Right atrium

RVC:

Right ventricular cavity

PA:

Pulmonary artery

ROI:

Region of interest

CNN:

Convolutional neural network

IQR:

Interquartile

References

  1. 1.

    Siontis, G. C. M., Praz, F., Pilgrim, T., et al. (2016). Transcatheter aortic valve implantation vs. surgical aortic valve replacement for treatment of severe aortic stenosis: A meta-analysis of randomized trials. European Heart Journal, 37(47), 3503–3512. https://doi.org/10.1093/eurheartj/ehw225

    Article  PubMed  Google Scholar 

  2. 2.

    Siontis, G. C. M., Overtchouk, P., Cahill, T. J., et al. (2019). Transcatheter aortic valve implantation vs. surgical aortic valve replacement for treatment of symptomatic severe aortic stenosis: An updated meta-analysis. European Heart Journal, 40(38), 3143–3153. https://doi.org/10.1093/eurheartj/ehz275

    Article  PubMed  Google Scholar 

  3. 3.

    Auffret, V., Lefevre, T., Van Belle, E., et al. (2017). Temporal trends in transcatheter aortic valve replacement in France: FRANCE 2 to FRANCE TAVI. Journal of the American College of Cardiology, 70(1), 42–55. https://doi.org/10.1016/j.jacc.2017.04.053

    Article  PubMed  Google Scholar 

  4. 4.

    Muller, D. W. M., Farivar, R. S., Jansz, P., et al. (2017). Transcatheter mitral valve replacement for patients with symptomatic mitral regurgitation: A global feasibility trial. Journal of the American College of Cardiology, 69(4), 381–391. https://doi.org/10.1016/j.jacc.2016.10.068 [published correction appears in J Am Coll Cardiol 2017;69(9):1213].

    Article  PubMed  Google Scholar 

  5. 5.

    Guerrero, M., Urena, M., Himbert, D., et al. (2018). 1-Year outcomes of transcatheter mitral valve replacement in patients with severe mitral annular calcification. Journal of the American College of Cardiology, 71(17), 1841–1853. https://doi.org/10.1016/j.jacc.2018.02.054

    Article  PubMed  Google Scholar 

  6. 6.

    Mas, J. L., Mas, J. L., Derumeaux, G., Guillon, B., et al. (2017). Patent foramen ovale closure or anticoagulation vs. antiplatelets after stroke. New England Journal of Medicine, 377(11), 1011–1021. https://doi.org/10.1056/NEJMoa1705915

    CAS  Article  Google Scholar 

  7. 7.

    Bishop, M., Rajani, R., Plank, G., et al. (2016). Three-dimensional atrial wall thickness maps to inform catheter ablation procedures for atrial fibrillation. Europace, 18(3), 376–383. https://doi.org/10.1093/europace/euv073

    Article  PubMed  Google Scholar 

  8. 8.

    Blanke, P., Weir-McCall, J. R., Achenbach, S., et al. (2019). Computed tomography imaging in the context of transcatheter aortic valve implantation (TAVI)/transcatheter aortic valve replacement (TAVR): An expert consensus document of the Society of Cardiovascular Computed Tomography. JACC: Cardiovascular Imaging, 12(1), 1–24. https://doi.org/10.1016/j.jcmg.2018.12.003

    Article  PubMed  Google Scholar 

  9. 9.

    Blanke, P., Dvir, D., Cheung, A., et al. (2015). Mitral annular evaluation with CT in the context of transcatheter mitral valve replacement. JACC: Cardiovascular Imaging, 8(5), 612–615. https://doi.org/10.1016/j.jcmg.2014.07.028

    Article  PubMed  Google Scholar 

  10. 10.

    Blanke, P., Naoum, C., Dvir, D., et al. (2017). Predicting LVOT obstruction in transcatheter mitral valve implantation: Concept of the neo-LVOT. JACC: Cardiovascular Imaging, 10(4), 482–485. https://doi.org/10.1016/j.jcmg.2016.01.005

    Article  PubMed  Google Scholar 

  11. 11.

    Weir-McCall, J. R., Blanke, P., Naoum, C., Delgado, V., Bax, J. J., & Leipsic, J. (2018). Mitral valve imaging with CT: Relationship with transcatheter mitral valve interventions. Radiology, 288(3), 638–655. https://doi.org/10.1148/radiol.2018172758

    Article  PubMed  Google Scholar 

  12. 12.

    Zhuang, X., & Shen, J. (2016). Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI. Medical Image Analysis, 31, 77–87. https://doi.org/10.1016/j.media.2016.02.006

    Article  PubMed  Google Scholar 

  13. 13.

    Commandeur, F., Goeller, M., Betancur, J., Cadet, S., Doris, M., Chen, X., et al. (2018). Deep learning for quantification of epicardial and thoracic adipose tissue from non-contrast CT. IEEE Transactions on Medical Imaging, 37, 1835–1846.

    Article  Google Scholar 

  14. 14.

    Zreik, M., Lessmann, N., van Hamersvelt, R. W., et al. (2018). Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis. Medical Image Analysis, 44, 72–85. https://doi.org/10.1016/j.media.2017.11.008

    Article  PubMed  Google Scholar 

  15. 15.

    Itu, L., Rapaka, S., Passerini, T., et al. (2016). A machine-learning approach for computation of fractional flow reserve from coronary computed tomography. Journal of Applied Physiology1985, 121(1), 42–52. https://doi.org/10.1152/japplphysiol.00752.2015

    Article  Google Scholar 

  16. 16.

    Coenen, A., Kim, Y. H., Kruk, M., et al. (2018). Diagnostic accuracy of a machine-learning approach to coronary computed tomographic angiography-based fractional flow reserve: Result from the MACHINE consortium. Circulation: Cardiovascular Imaging, 11(6), e007217. https://doi.org/10.1161/CIRCIMAGING.117.007217

    Article  PubMed  Google Scholar 

  17. 17.

    Zhuang, X., Bai, W., Song, J., et al. (2015). Multiatlas whole heart segmentation of CT data using conditional entropy for atlas ranking and selection. Medical Physics, 42(7), 3822–3833. https://doi.org/10.1118/1.4921366

    Article  PubMed  Google Scholar 

  18. 18.

    Zhou, R., Liao, Z., Pan, T., et al. (2017). Cardiac atlas development and validation for automatic segmentation of cardiac substructures. Radiotherapy and Oncology, 122(1), 66–71. https://doi.org/10.1016/j.radonc.2016.11.016

    Article  PubMed  Google Scholar 

  19. 19.

    Cai, K., Yang, R., Chen, H., et al. (2017). A framework combining window width-level adjustment and Gaussian filter-based multi-resolution for automatic whole heart segmentation. Neurocomputing, 220, 138–150. https://doi.org/10.1016/j.neucom.2016.03.106

    Article  Google Scholar 

  20. 20.

    Zhuang, X., Li, L., Payer, C., et al. (2019). Evaluation of algorithms for multi-modality whole heart segmentation: An open-access grand challenge. Medical Image Analysis, 58, 101537. https://doi.org/10.1016/j.media.2019.101537

    Article  PubMed  PubMed Central  Google Scholar 

  21. 21.

    Baskaran, L., Maliakal, G., Al’Aref, S. J., et al. (2020). Identification and quantification of cardiovascular structures from CCTA: An end-to-end, rapid, pixel-wise, deep-learning method. JACC: Cardiovascular Imaging, 13(5), 1163–1171. https://doi.org/10.1016/j.jcmg.2019.08.025

    Article  PubMed  Google Scholar 

  22. 22.

    Kaladji, A., Lucas, A., Kervio, G., Haigron, P., & Cardon, A. (2010). Sizing for endovascular aneurysm repair: Clinical evaluation of a new automated three-dimensional software. Annals of Vascular Surgery, 24(7), 912–920. https://doi.org/10.1016/j.avsg.2010.03.018

    Article  PubMed  PubMed Central  Google Scholar 

  23. 23.

    Lang, R. M., Badano, L. P., Mor-Avi, V., et al. (2015). Recommendations for cardiac chamber quantification by echocardiography in adults: an update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging. European Heart Journal – Cardiovascular Imaging, 16(3), 233–270. https://doi.org/10.1093/ehjci/jev014 [published correction appears in Eur Heart J Cardiovasc Imaging. 2016 Apr;17(4):412] [published correction appears in Eur Heart J Cardiovasc Imaging. 2016 Sep;17 (9):969].

    Article  PubMed  Google Scholar 

  24. 24.

    Petersen, S. E., Khanji, M. Y., Plein, S., Lancellotti, P., & Bucciarelli-Ducci, C. (2019). European Association of Cardiovascular Imaging expert consensus paper: A comprehensive review of cardiovascular magnetic resonance normal values of cardiac chamber size and aortic root in adults and recommendations for grading severity. European Heart Journal - Cardiovascular Imaging, 20(12), 1321–1331. https://doi.org/10.1093/ehjci/jez232 [published correction appears in Eur Heart J Cardiovasc Imaging. 2019 Dec 1;20(12):1331].

    Article  PubMed  Google Scholar 

  25. 25.

    Tobon-Gomez, C., Geers, A. J., Peters, J., et al. (2015). Benchmark for algorithms segmenting the left atrium from 3D CT and MRI datasets. IEEE Transactions on Medical Imaging, 34(7), 1460–1473. https://doi.org/10.1109/TMI.2015.2398818

    Article  PubMed  Google Scholar 

  26. 26.

    Fuchs, A., Mejdahl, M. R., Kühl, J. T., et al. (2016). Normal values of left ventricular mass and cardiac chamber volumes assessed by 320-detector computed tomography angiography in the Copenhagen general population study. European Heart Journal Cardiovascular Imaging, 17(9), 1009–1017. https://doi.org/10.1093/ehjci/jev337

    Article  PubMed  Google Scholar 

  27. 27.

    Forrest N. Landola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer. SqueezeNet: AlexNet-level accuracy with 50× fewer parameters and < 0.50 MB model size. https://arxiv.org/abs/1602.07360. Accessed 18 April 2021

  28. 28.

    Karen Simonyan, Andrew Zisserman. Very deep convolutional network for large-scale image recognition. https://arxiv.org/abs/1409.1556. Accessed 18 April 2021

  29. 29.

    Gibson, E., Giganti, F., Hu, Y., et al. (2018). Automatic multi-organ segmentation on abdominal CT with dense V-networks. IEEE Transactions on Medical Imaging, 37(8), 1822–1834. https://doi.org/10.1109/TMI.2018.2806309

    Article  PubMed  PubMed Central  Google Scholar 

  30. 30.

    Eelbode, T., Bertels, J., Berman, M., et al. (2020). Optimization for medical image segmentation: Theory and practice when evaluating with dice score or Jaccard index. IEEE Transactions on Medical Imaging, 39(11), 3679–3690. https://doi.org/10.1109/TMI.2020.3002417

    Article  PubMed  Google Scholar 

  31. 31.

    Chen, J., Yang, Z. G., Xu, H. Y., Shi, K., Long, Q. H., & Guo, Y. K. (2017). Assessments of pulmonary vein and left atrial anatomical variants in atrial fibrillation patients for catheter ablation with cardiac CT. European Radiology, 27(2), 660–670. https://doi.org/10.1007/s00330-016-4411-6

    Article  PubMed  Google Scholar 

  32. 32.

    Cho J, Lee K, Shin E, Choy G, Do S. (2015) How much data is needed to train a medical image deep learning system to achieve necessary high accuracy? http://arxiv.org/abs/151106348. Accessed 18 April 2021 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Vincent Auffret.

Ethics declarations

Animal Studies

No animal studies were carried out by the authors for this article.

Conflict of Interest

Dr. Vincent Auffret and Dr. Le Breton received lecture fees from Edwards Lifescience. Mr. Florent Lalys is one of the employees of Therenva®. The other authors have nothing to disclose. All the authors take responsibility for all aspects of the reliability and freedom from bias of the data presented and their discussed interpretation.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Associate Editor Jozine ter Maaten oversaw the review of this article

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 1380 KB)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Sharobeem, S., Le Breton, H., Lalys, F. et al. Validation of a Whole Heart Segmentation from Computed Tomography Imaging Using a Deep-Learning Approach. J. of Cardiovasc. Trans. Res. (2021). https://doi.org/10.1007/s12265-021-10166-0

Download citation

Keywords

  • Whole heart segmentation
  • Deep learning
  • Computed tomography
  • Procedural planning