Skip to main content
SpringerLink
Log in

Left ventricle analysis in echocardiographic images using transfer learning

  • Scientific Paper
  • Published:
Physical and Engineering Sciences in Medicine Aims and scope Submit manuscript

Abstract

The segmentation of cardiac boundaries, specifically Left Ventricle (LV) segmentation in 2D echocardiographic images, is a critical step in LV segmentation and cardiac function assessment. These images are generally of poor quality and present low contrast, making daily clinical delineation difficult, time-consuming, and often inaccurate. Thus, it is necessary to design an intelligent automatic endocardium segmentation system. The present work aims to examine and assess the performance of some deep learning-based architectures such as U-Net1, U-Net2, LinkNet, Attention U-Net, and TransUNet using the public CAMUS (Cardiac Acquisitions for Multi-structure Ultrasound Segmentation) dataset. The adopted approach emphasizes the advantage of using transfer learning and resorting to pre-trained backbones in the encoder part of a segmentation network for echocardiographic image analysis. The experimental findings indicated that the proposed framework with the \(\text {U}\)-\(\text {Net1}_{\text {VGG19}}\) is quite promising; it outperforms other more recent approaches with a Dice similarity coefficient of 93.30% and a Hausdorff Distance of 4.01 mm. In addition, a good agreement between the clinical indices calculated from the automatic segmentation and those calculated from the ground truth segmentation. For instance, the mean absolute errors for the left ventricular end-diastolic volume, end-systolic volume, and ejection fraction are equal to 7.9 ml, 5.4 ml, and 6.6%, respectively. These results are encouraging and point out additional perspectives for further improvement.

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
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Data availability

The dataset used in this study includes 2D echocardiographic images and is publicly accessible. The dataset used in this study can be accessed from: https://camus.creatis.insa-lyon.fr/challenge/.

Notes

  1. https://camus.creatis.insa-lyon.fr/challenge/

  2. https://image-net.org/

References

  1. Mc Namara K, Alzubaidi H, Jackson JK (2019) Cardiovascular disease as a leading cause of death: how are pharmacists getting involved? Integr Pharm Res Pract 8:1–11. https://doi.org/10.2147/IPRP.S133088

    Article  Google Scholar 

  2. Sadeghpour A, Alizadehasl A (2022) Practical cardiology. Elsevier, Amsterdam, pp 67–110. https://doi.org/10.1016/B978-0-323-80915-3.00008-9

    Book  Google Scholar 

  3. Carneiro G, Nascimento JC, Freitas A (2012) The segmentation of the left ventricle of the heart from ultrasound data using deep learning architectures and derivative-based search methods. IEEE Trans Image Process 21(3):968–982. https://doi.org/10.1109/TIP.2011.2169273

    Article  Google Scholar 

  4. Dietenbeck T, Alessandrini M, Barbosa D, D’hooge J, Friboulet D, Bernard O (2012) Detection of the whole myocardium in 2d-echocardiography for multiple orientations using a geometrically constrained level-set. Med Image Anal 16(2):386–401. https://doi.org/10.1016/j.media.2011.10.003

    Article  CAS  Google Scholar 

  5. Kim T, Hedayat M, Vaitkus VV, Belohlavek M, Krishnamurthy V, Borazjani I (2021) Automatic segmentation of the left ventricle in echocardiographic images using convolutional neural networks. Quant Imaging Med Surg 11(5):1763–1781

    Article  Google Scholar 

  6. Noble JA, Boukerroui D (2006) Ultrasound image segmentation: a survey. IEEE Trans Med Imaging 25(8):987–1010. https://doi.org/10.1109/TMI.2006.877092

    Article  Google Scholar 

  7. Yan J, Zhuang T (2003) Applying improved fast marching method to endocardial boundary detection in echocardiographic images. Pattern Recognit Lett 24(15):2777–2784. https://doi.org/10.1016/S0167-8655(03)00121-1

    Article  Google Scholar 

  8. Paragios N (2003) A level set approach for shape-driven segmentation and tracking of the left ventricle. IEEE Trans Med Imaging 22(6):773–776. https://doi.org/10.1109/TMI.2003.814785

    Article  Google Scholar 

  9. Bosch JG, Mitchell SC, Lelieveldt BPF, Nijland F, Kamp O, Sonka M, Reiber JHC (2002) Automatic segmentation of echocardiographic sequences by active appearance motion models. IEEE Trans Med Imaging 21(11):1374–1383. https://doi.org/10.1109/TMI.2002.806427

    Article  Google Scholar 

  10. Galicia E, Torres F, Escalante B, Olveres J, Arámbula F (2021) Full multi resolution active shape model for left ventricle segmentation. In: Walker A, Rittner L, Romero Castro E, Lepore N, Brieva J, Linguraru MG (eds) 17th international symposium on medical information processing and analysis, p. 41. SPIE, Campinas, Brazil. https://doi.org/10.1117/12.2606252

  11. Ali Y, Beheshti S, Janabi-Sharifi F (2021) Echocardiogram segmentation using active shape model and mean squared eigenvalue error. Biomed Signal Process Control 69:102807. https://doi.org/10.1016/j.bspc.2021.102807

    Article  Google Scholar 

  12. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444. https://doi.org/10.1038/nature14539

    Article  CAS  Google Scholar 

  13. Minaee S, Boykov YY, Porikli F, Plaza AJ, Kehtarnavaz N, Terzopoulos D (2021) Image segmentation using deep learning: a survey. IEEE Trans Pattern Anal Mach Intell. https://doi.org/10.1109/TPAMI.2021.3059968

    Article  Google Scholar 

  14. Smistad E, Ostvik A, Haugen BO, Lovstakken L (2017) 2D left ventricle segmentation using deep learning. In: 2017 IEEE international ultrasonics symposium (IUS), pp. 1–4. IEEE, Washington, DC. https://doi.org/10.1109/ULTSYM.2017.8092573

  15. Leclerc S, Smistad E, Pedrosa J, østvik A, Cervenansky F, Espinosa F, Espeland T, Berg EAR, Jodoin P-M, Grenier T, Lartizien C, D’hooge J, Lovstakken L, Bernard O (2019) Deep learning for segmentation using an open large-scale dataset in 2D echocardiography. IEEE Trans Med Imaging 38(9):2198–2210. https://doi.org/10.1109/TMI.2019.2900516

    Article  Google Scholar 

  16. Dahal L, Kafle A, Khanal B (2020) Uncertainty estimation in deep 2D echocardiography segmentation. arXiv:2005.09349 [cs]. arXiv:2005.09349

  17. Hesse LS, Namburete AIL (2020) Improving U-net segmentation with active contour based label correction. In: Papież BW, Namburete AIL, Yaqub M, Noble JA (eds) Medical image understanding and analysis, vol 1248. Springer, Cham. https://doi.org/10.1007/978-3-030-52791-4_6

    Chapter  Google Scholar 

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

  19. Zhao C, Xia B, Chen W, Guo L, Du J, Wang T, Lei B (2021) Multi-scale wavelet network algorithm for pediatric echocardiographic segmentation via hierarchical feature guided fusion. Appl Soft Comput 107:107386. https://doi.org/10.1016/j.asoc.2021.107386

    Article  Google Scholar 

  20. Yang Y, Sermesant M (2021) Shape constraints in deep learning for robust 2D echocardiography analysis. In: Ennis DB, Perotti LE, Wang VY (eds) Functional imaging and modeling of the heart, vol 12738. Springer, Cham, pp 22–34. https://doi.org/10.1007/978-3-030-78710-3_3

    Chapter  Google Scholar 

  21. Deng K, Meng Y, Gao D, Bridge J, Shen Y, Lip G, Zhao Y, Zheng Y (2021) TransBridge: a lightweight transformer for left ventricle segmentation in echocardiography. In: Noble JA, Aylward S, Grimwood A, Min Z, Lee S-L, Hu Y (eds) Simplifying medical ultrasound, vol 12967. Springer, Cham, pp 63–72. https://doi.org/10.1007/978-3-030-87583-1_7

    Chapter  Google Scholar 

  22. Jafari MH, Girgis H, Van Woudenberg N, Moulson N, Luong C, Fung A, Balthazaar S, Jue J, Tsang M, Nair P, Gin K, Rohling R, Abolmaesumi P, Tsang T (2020) Cardiac point-of-care to cart-based ultrasound translation using constrained CycleGAN. Int J Comput Assist Radiol Surg 15(5):877–886. https://doi.org/10.1007/s11548-020-02141-y

    Article  Google Scholar 

  23. Escobar M, Castillo A, Romero A, Arbeláez P (2020) UltraGAN: ultrasound enhancement through adversarial generation. In: Burgos N, Svoboda D, Wolterink JM, Zhao C (eds) Simulation and synthesis in medical imaging, vol 12417. Springer, Cham, pp 120–130. https://doi.org/10.1007/978-3-030-59520-3_13

    Chapter  Google Scholar 

  24. Saeed M, Muhtaseb R, Yaqub M (2022) Is contrastive learning suitable for left ventricular segmentation in echocardiographic images? https://doi.org/10.48550/ARXIV.2201.07219. Publisher: arXiv Version Number: 1

  25. Zhu J-Y, Park T, Isola P, Efros AA (2020) Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv:1703.10593 [cs]

  26. Isola P, Zhu J-Y, Zhou T, Efros AA (2018) Image-to-image translation with conditional adversarial networks. arXiv:1611.07004 [cs]. arXiv: 1611.07004

  27. Chen L-C, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. arXiv:1706.05587 [cs]. arXiv: 1706.05587

  28. Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: International conference on machine learning. PMLR, pp 1597–1607

  29. Grill J-B, Strub F, Altché F, Tallec C, Richemond P, Buchatskaya E, Doersch C, Avila Pires B, Guo Z, Gheshlaghi Azar M et al (2020) Bootstrap your own latent-a new approach to self-supervised learning. Adv Neural Inf Process Syst 33:21271–21284

    Google Scholar 

  30. Li M, Wang C, Zhang H, Yang G (2020) MV-RAN: multiview recurrent aggregation network for echocardiographic sequences segmentation and full cardiac cycle analysis. Comput Biol Med 120:103728. https://doi.org/10.1016/j.compbiomed.2020.103728

    Article  Google Scholar 

  31. Wu H, Liu J, Xiao F, Wen Z, Cheng L, Qin J (2022) Semi-supervised segmentation of echocardiography videos via noise-resilient spatiotemporal semantic calibration and fusion. Med Image Anal 78:102397. https://doi.org/10.1016/j.media.2022.102397

    Article  Google Scholar 

  32. Moal O, Roger E, Lamouroux A, Younes C, Bonnet G, Moal B, Lafitte S (2022) Explicit and automatic ejection fraction assessment on 2D cardiac ultrasound with a deep learning-based approach. Comput Biol Med 146:105637. https://doi.org/10.1016/j.compbiomed.2022.105637

    Article  Google Scholar 

  33. Painchaud N, Duchateau N, Bernard O, Jodoin P-M (2022) Echocardiography segmentation with enforced temporal consistency. IEEE Trans Med Imaging. https://doi.org/10.1109/TMI.2022.3173669

    Article  Google Scholar 

  34. Sirjani N, Moradi S, Oghli MG, Hosseinsabet A, Alizadehasl A, Yadollahi M, Shiri I, Shabanzadeh A (2022) Automatic cardiac evaluations using a deep video object segmentation network. Insights Imaging 13(1):69. https://doi.org/10.1186/s13244-022-01212-9

    Article  Google Scholar 

  35. Ono S, Komatsu M, Sakai A, Arima H, Ochida M, Aoyama R, Yasutomi S, Asada K, Kaneko S, Sasano T, Hamamoto R (2022) Automated endocardial border detection and left ventricular functional assessment in echocardiography using deep learning. Biomedicines 10(5):1082. https://doi.org/10.3390/biomedicines10051082

    Article  Google Scholar 

  36. Li M, Dong S, Gao Z, Feng C, Xiong H, Zheng W, Ghista D, Zhang H, de Albuquerque VHC (2020) Unified model for interpreting multi-view echocardiographic sequences without temporal information. Appl Soft Comput 88:106049. https://doi.org/10.1016/j.asoc.2019.106049

    Article  Google Scholar 

  37. Shen Y, Zhang H, Fan Y, Lee AP, Xu L (2021) Smart health of ultrasound telemedicine based on deeply represented semantic segmentation. IEEE Internet Things J 8(23):16770–16778. https://doi.org/10.1109/JIOT.2020.3029957

    Article  Google Scholar 

  38. Zyuzin V, Mukhtarov A, Neustroev D, Chumarnaya T (2020) Segmentation of 2D echocardiography images using residual blocks in U-net architectures. In: 2020 ural symposium on biomedical engineering, radioelectronics and information technology (USBEREIT), pp 499–502. IEEE, Yekaterinburg, Russia. https://doi.org/10.1109/USBEREIT48449.2020.9117678

  39. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252. https://doi.org/10.1007/s11263-015-0816-y

    Article  Google Scholar 

  40. Yakubovskiy P (2019) Segmentation models. GitHub

  41. Sha Y (2021) Keras-unet-collection. GitHub. https://doi.org/10.5281/zenodo.5449801

    Article  Google Scholar 

  42. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980

  43. Wang J, Zhu H, Wang S-H, Zhang Y-D (2021) A review of deep learning on medical image analysis. Mob Netw Appl 26(1):351–380. https://doi.org/10.1007/s11036-020-01672-7

    Article  Google Scholar 

  44. Qin Z, Yu F, Liu C, Chen X (2018) How convolutional neural network see the world-a survey of convolutional neural network visualization methods. arXiv preprint arXiv:1804.11191

  45. Chaurasia A, Culurciello E (2017) LinkNet: exploiting encoder representations for efficient semantic segmentation. 2017 IEEE visual communications and image processing (VCIP), pp 1–4. https://doi.org/10.1109/VCIP.2017.8305148. arXiv: 1707.03718

  46. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  47. Oktay O, Schlemper J, Folgoc LL, Lee M, Heinrich M, Misawa K, Mori K, McDonagh S, Hammerla NY, Kainz B, Glocker B, Rueckert D (2018) Attention U-Net: learning where to look for the pancreas. arXiv:1804.03999 [cs]. arXiv: 1804.03999

  48. Abraham N, Khan NM (2019) A novel focal tversky loss function with improved attention u-net for lesion segmentation. In: 2019 IEEE 16th international symposium on biomedical imaging (ISBI 2019). IEEE, pp 683–687

  49. Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y, Lu L, Yuille AL, Zhou Y (2021) TransUNet: transformers make strong encoders for medical image segmentation. arXiv:2102.04306 [cs]. arXiv: 2102.04306

  50. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556

  51. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700–4708

  52. Dice LR (1945) Measures of the amount of ecologic association between species. Ecology 26(3):297–302

    Article  Google Scholar 

  53. Real R, Vargas JM (1996) The probabilistic basis of Jaccard’s index of similarity. Syst Biol 45(3):380–385

    Article  Google Scholar 

  54. Folland ED, Parisi AF, Moynihan PF, Jones DR, Feldman CL, Tow DE (1979) Assessment of left ventricular ejection fraction and volumes by real-time, two-dimensional echocardiography. A comparison of cineangiographic and radionuclide techniques. Circulation 60(4):760–766. https://doi.org/10.1161/01.CIR.60.4.760

    Article  CAS  Google Scholar 

  55. Bland JM, Altman DG (2010) Statistical methods for assessing agreement between two methods of clinical measurement. Int J Nurs Stud 47(8):931–936. https://doi.org/10.1016/j.ijnurstu.2009.10.001

    Article  Google Scholar 

  56. Chen Z, Zeng Z, Shen H, Zheng X, Dai P, Ouyang P (2020) DN-GAN: denoising generative adversarial networks for speckle noise reduction in optical coherence tomography images. Biomed Signal Process Control 55:101632. https://doi.org/10.1016/j.bspc.2019.101632

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to thank the Directorate General of Scientific Research and Technological Development (Direction Générale de la Recherche Scientifique et du Développement Technologique, DGRSDT, Algeria www.dgrsdt.dz) for the financial assistance towards this research.

Funding

The authors declare that no funds, grants, or other support were received during the preparation of this manuscript.

Author information

Authors and Affiliations

  1. Laboratory of Biomedical Engineering, Faculty of technology, University of Tlemcen, 13000, Tlemcen, Algeria

    Hafida Belfilali & Mahammed Messadi

  2. Laboratoire de Conception, Optimisation et Modélisation des Systèmes, LCOMS EA 7306, Université de Lorraine, 57000, Metz, France

    Frédéric Bousefsaf

Authors
  1. Hafida Belfilali
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Frédéric Bousefsaf
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mahammed Messadi
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the study conception and design. Material preparation and analysis were performed by Hafida Belfilali and Frédéric Bousefsaf. The first draft of the manuscript was written by Hafida Belfilali and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.

Corresponding authors

Correspondence to Hafida Belfilali or Frédéric Bousefsaf.

Ethics declarations

Conflict of interest

The authors have no relevant financial or non-financial interests to disclose.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Consent to participate

Not applicable.

Consent for publication

Not applicable

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 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

Belfilali, H., Bousefsaf, F. & Messadi, M. Left ventricle analysis in echocardiographic images using transfer learning. Phys Eng Sci Med 45, 1123–1138 (2022). https://doi.org/10.1007/s13246-022-01179-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13246-022-01179-3

Keywords

Search

Navigation