Skip to main content
SpringerLink
Log in

Automatic Left Ventricle Segmentation from Short-Axis MRI Images Using U-Net with Study of the Papillary Muscles’ Removal Effect

  • Original Article
  • Published:
Journal of Medical and Biological Engineering Aims and scope Submit manuscript

Abstract

Purpose

In clinical routines, the evaluation of cardiac wall motion is based on manual segmentation of ventricular contours. This task is time-consuming and leads to inter-observer variability. In this context, the aim of this paper is to propose a fully automatic method based on U-net architecture for left ventricle (LV) segmentation while studying the impact of papillary muscles presence and elimination on the segmentation accuracy.

Methods

In this work, we developed and evaluated an automatic approach based on U-Net architecture for LV segmentation. We started with a preprocessing pipeline which consists in cropping original images using convolutional neural network (CNN) and eliminating pillars using morphological operators. Regarding segmentation, our neural network was trained and validated using ACDC dataset composed of 150 patients. The performance of the proposed method was evaluated on an internal database composed of 100 patients (more than 2500 frames) using technical metrics including Hausdorff distance (HD), Jaccard coefficient (IoU), and Dice Similarity Coefficient (DSC).

Results

A comparative study demonstrated that the proposed architecture outperformed the original U-Net. Quantitative analysis of the obtained results confirmed the strength of our method that reveals the superlative segmentation performance as evaluated using the following indices including HD = 6.541 ± 1.6 mm, IoU = 94.85 ± 2%, and DSC = 93.27 ± 5% with p value < 0.0032. After the preprocessing application, the segmentation accuracy was improved. Thus, new mean HD, IoU, and DSC were 5.034 ± 2 mm, 98.83 ± 3.4%, and 98.04 ± 4%, respectively, with p value < 0.0018. Clinically, pillars’ exclusion facilitated middle and apical sections’ interpretation and helped in pathologies localization and clinical parameters’ estimation.

Conclusion

Experimental results demonstrate that the proposed approach offers a promising tool for LV segmentation and verifies its potential clinical applicability. In addition, pillars’ elimination using morphological operations proves its usefulness in improving segmentation accuracy.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

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

Similar content being viewed by others

Data availability

The data and the groundtruth used for neural network training are publicly available via the following link: https://www.creatis.insa-lyon.fr/Challenge/acdc/databases.html.

References

  1. Salerno, M., Sharif, B., & Arheden, H. (2017). Recent advances in cardiovascular magnetic resonance: Techniques and applications. Circulation: Cardiovascular Imaging, 10(6), e003951

    PubMed  Google Scholar 

  2. Vick, I. I. I. (2009). The gold standard for noninvasive imaging in coronary heart disease: Magnetic resonance imaging. Current Opinion in Cardiology, 24(6), 567–579.

    Article  PubMed  Google Scholar 

  3. Santiago, C., Nascimento, J. C., & Marques, J. S. (2018). Fast segmentation of the left ventricle in cardiac MRI using dynamic programming. Computer Methods and Programs in Biomedicine, 154, 9–23.

    Article  PubMed  Google Scholar 

  4. Budai, A., Suhai, F. I., Csorba, K., Toth, A., et al. (2020). Fully automatic segmentation of right and left ventricle on short-axis cardiac MRI images. Computerized Medical Imaging and Graphics, 85, 101786.

    Article  PubMed  Google Scholar 

  5. Xie, L., Song, Y., & Chen, Q. (2020). Automatic left ventricle segmentation in short-axis MRI using deep convolutional neural networks and central-line guided level set approach. Computers in Biology and Medicine, 122, 103877.

    Article  PubMed  Google Scholar 

  6. Bernard, O., Lalande, A., Zotti, C., et al. (2018). Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: Is the problem solved? IEEE Transactions on Medical Imaging, 37(11), 2514–2525.

    Article  PubMed  Google Scholar 

  7. Zhang, Y. (2021). Cascaded convolutional neural network for automatic myocardial infarction segmentation from delayed-enhancement cardiac MRI. Statistical atlases and computational models of the heart. M&Ms and EMIDEC challenges: 11th international workshop (pp. 328–333). Springer International Publishing.

    Chapter  Google Scholar 

  8. Bai, W., Sinclair, M., Tarroni, G., Oktay, O., Rajchl, M., Vaillant, G., & Rueckert, D. (2018). Automated cardiovascular magnetic resonance image analysis with fully convolutional networks. Journal of Cardiovascular Magnetic Resonance, 20(1), 1–12.

    Article  Google Scholar 

  9. Shaaf, Z. F., Jamil, M. M. A., Ambar, R., Alattab, A. A., Yahya, A. A., & Asiri, Y. (2022). Automatic Left Ventricle Segmentation from Short-Axis Cardiac MRI images based on fully convolutional neural network. Diagnostics, 12(2), 414.

    Article  PubMed  PubMed Central  Google Scholar 

  10. Avendi, M. R., Kheradvar, A., & Jafarkhani, H. (2016). A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI. Medical Image Analysis, 30, 108–119.

    Article  CAS  PubMed  Google Scholar 

  11. Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. International conference on medical image computing and computer-assisted intervention (pp. 234–241). Springer.

    Google Scholar 

  12. Cui, H., Yuwen, C., Jiang, L., Xia, Y., & Zhang, Y. (2021). Multiscale attention guided U-Net architecture for cardiac segmentation in short-axis MRI images. Computer Methods and Programs in Biomedicine, 206, 106142.

    Article  PubMed  Google Scholar 

  13. Ren, J., Sun, H., Huang, Y., & Gao, H. (2020). Knowledge-based multi-sequence MR segmentation via deep learning with a hybrid U-Net + + model. Statistical atlases and computational models of the heart. Multi-sequence CMR segmentation, CRT-EPiggy and LV full quantification challenges: 10th international workshop. Springer International Publishing.

    Google Scholar 

  14. Riffel, J. H., Schmucker, K., Andre, F., Ochs, M., Hirschberg, K., Schaub, E., & Friedrich, M. G. (2019). Cardiovascular magnetic resonance of cardiac morphology and function: Impact of different strategies of contour drawing and indexing. Clinical Research in Cardiology, 108(4), 411–429.

    Article  PubMed  Google Scholar 

  15. Vogel-Claussen, J., Finn, J. P., Gomes, A. S., Hundley, G. W., Jerosch-Herold, M., Pearson, G., & Bluemke, D. A. (2006). Left ventricular papillary muscle mass: Relationship to left ventricular mass and volumes by magnetic resonance imaging. Journal of Computer Assisted Tomography, 30(3), 426–432.

    Article  PubMed  Google Scholar 

  16. Albawi, S., Mohammed, T. A., & Al-Zawi, S. (2017). Understanding of a convolutional neural network. 2017 international conference on engineering and technology (ICET) (pp. 1–6). IEEE.

    Google Scholar 

  17. Heijmans, H. J. A. M. (1995). Mathematical morphology: basic principles. In Proceedings of summer school on “morphological image and signal processing.

  18. Farahani, A., & Mohseni, H. (2021). Medical image segmentation using customized u-net with adaptive activation functions. Neural Computing and Applications, 33(11), 6307–6323.

    Article  Google Scholar 

  19. Mathews, C., & Mohamed, A. (2020). Review of automatic segmentation of MRI based brain tumour using U-net architecture. 2020 Fourth international conference on inventive systems and control (ICISC) (pp. 46–50). IEEE.

    Chapter  Google Scholar 

  20. Ibtehaz, N., & Rahman, M. S. (2020). MultiResUNet: Rethinking the U-net architecture for multimodal biomedical image segmentation. Neural Networks, 121, 74–87.

    Article  PubMed  Google Scholar 

  21. Zunair, H., & Hamza, A. B. (2021). Sharp U-Net: Depthwise convolutional network for biomedical image segmentation. Computers in Biology and Medicine, 136, 104699.

    Article  PubMed  Google Scholar 

  22. Abdeltawab, H., Khalifa, F., Taher, F., Alghamdi, N. S., Ghazal, M., Beache, G., & El-Baz, A. (2020). A deep learning-based approach for automatic segmentation and quantification of the left ventricle from cardiac cine MR images. Computerized Medical Imaging and Graphics, 81, 101717.

    Article  PubMed  PubMed Central  Google Scholar 

  23. Grinias, E., & Tziritas, G. (2018). Fast fully-automatic cardiac segmentation in MRI using MRF model optimization, substructures tracking and B-spline smoothing. Statistical atlases and computational models of the heart. ACDC and MMWHS Challenges: 8th international workshop (pp. 91–100). Springer International Publishing.

    Google Scholar 

  24. Patravali, J., Jain, S., & Chilamkurthy, S. (2018). 2D–3D fully convolutional neural networks for cardiac MR segmentation. Statistical atlases and computational models of the heart. ACDC and MMWHS challenges: 8th international workshop (pp. 130–139). Springer International Publishing.

    Google Scholar 

  25. Calisto, M. B., & Lai-Yuen, S. K. (2020). AdaEn-Net: An ensemble of adaptive 2D–3D fully Convolutional Networks for medical image segmentation. Neural Networks, 126, 76–94.

    Article  Google Scholar 

  26. Khened, M., Kollerathu, V. A., & Krishnamurthi, G. (2019). Fully convolutional multi-scale residual DenseNets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiers. Medical Image Analysis, 51, 21–45.

    Article  PubMed  Google Scholar 

  27. Zotti, C., Luo, Z., Lalande, A., et al. (2018). Convolutional neural network with shape prior applied to cardiac MRI segmentation. IEEE Journal of Biomedical and Health Informatics, 23(3), 1119–1128.

    Article  PubMed  Google Scholar 

  28. Isensee, F., Jaeger, P. F., & Full, P. M. (2018). Automatic cardiac disease assessment on cine-MRI via time-series segmentation and domain specific features. Statistical atlases and computational models of the heart. ACDC and MMWHS challenges: 8th international workshop (pp. 120–129). Springer International Publishing.

    Google Scholar 

  29. Zhang, H., Zhang, W., Shen, W., et al. (2021). Automatic segmentation of the cardiac MR images based on nested fully convolutional dense network with dilated convolution. Biomedical Signal Processing and Control, 68, 102684.

    Article  Google Scholar 

  30. Li, Z., Lou, Y., & Yan, Z. (2019). Fully automatic segmentation of short-axis cardiac MRI using modified deep layer aggregation. 2019 IEEE 16th international symposium on biomedical imaging (ISBI 2019) (pp. 793–797). IEEE.

    Chapter  Google Scholar 

  31. Penso, M., Moccia, S., Scafuri, S., et al. (2021). Automated left and right ventricular chamber segmentation in cardiac magnetic resonance images using dense fully convolutional neural network. Computer Methods and Programs in Biomedicine, 204, 106059

    Article  PubMed  Google Scholar 

  32. Guo, F., Ng, M., & Wright, G. (2019). Cardiac MRI left ventricle segmentation and quantification: A framework combining U-Net and continuous max-flow. Statistical atlases and computational models of the heart. Atrial segmentation and LV quantification challenges: 9th international workshop (pp. 450–458). Springer International Publishing.

    Chapter  Google Scholar 

Download references

Funding

No funds, grants, or other support was received.

Author information

Authors and Affiliations

  1. Research laboratory of Biophysics and Medical Technologies LR13ES07, Higher institute of Medical Technologies of Tunis, University of Tunis El Manar, 1006, Tunis, Tunisia

    Wafa Baccouch, Sameh Oueslati & Salam Labidi

  2. Image & Information Processing Department (iTi), IMT-Atlantique, Technopôle Brest Iroise CS 83818, 29238, Brest Cedex, France

    Basel Solaiman

  3. Faculty of Medicine of Tunis, University of Tunis El Manar, Tunis, Tunisia

    Dhaker Lahidheb

  4. Department of Cardiology, Military Hospital of Tunis, Tunis, Tunisia

    Dhaker Lahidheb

Authors
  1. Wafa Baccouch
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sameh Oueslati
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Basel Solaiman
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Dhaker Lahidheb
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Salam Labidi
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the study conception and design. WB: Conceptualization, Methodology, implementation, and first Writing—original draft and data collection. SO: contribution to the design of the study, monitored, validated, and discussed the proposed algorithm during the implementation phase. BS: Discussed, checked, and validated the implementation and optimization phase of the proposed algorithm as well as the obtained results. DL: evaluation of the obtained results, clinical validation. SL Supervised development of the research work and manuscript correction. All authors commented, evaluated, and validated the previous versions of the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Wafa Baccouch.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical Approval

The authors confirm that all procedures performed in our study involving human participants were in accordance with ethical standards of the institutional research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards. “For this type of study formal consent is not required.” We did not use either names, identifiers, or any personal data it was quite simply a collection of data relating to abnormalities that affect the contractile function of the myocardium. In addition, we do not have access to the identity or medical field of any patient except the age and the disease from which they suffer.

Consent to participate

For this type of study formal consent is not required. We did not use patients' names, identifiers or any personal data. It was quite simply a collection of anonymous data relating to abnormalities that affect the contractile function of the myocardium. It is worth noting that we haven't access to the identity or medical field of any patient except the age and the disease from which they suffer.

Additional information

Publisher’s Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Baccouch, W., Oueslati, S., Solaiman, B. et al. Automatic Left Ventricle Segmentation from Short-Axis MRI Images Using U-Net with Study of the Papillary Muscles’ Removal Effect. J. Med. Biol. Eng. 43, 278–290 (2023). https://doi.org/10.1007/s40846-023-00794-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s40846-023-00794-z

Keywords

Search

Navigation