Skip to main content

Detection of Aortic Cusp Landmarks in Computed Tomography Images with Deep Learning

  • Conference paper
  • First Online:
Functional Imaging and Modeling of the Heart (FIMH 2023)

Abstract

To perform aortic valve morphology for the assessment of the valvular heart disease in cardiovascular medicine, an accurate identification of specific anatomical points, i.e. landmarks, which define the aortic cusps, is required. In this study, we investigate the application of a deep learning framework, namely the spatial configuration network, for aortic cusp landmark detection in 120 contrast-enhanced end-diastolic coronary computed tomography images of normal patients. By performing three-fold cross-validation experiments, we obtained a mean detection error of \(1.45\,{\pm }\,0.82\) mm for six landmarks located at the nadirs and commissures of the aortic valve sinuses, which dropped to \(1.15\,{\pm }\,0.62\) mm when landmarks were detected in images that were cropped around the aortic valve by applying atlas-based segmentation. The obtained accuracy is comparable to existing methods, however, additional improvements in the form of image pre- or post-processing, or by applying advanced methodological concepts, may improve the landmark detection performance.

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

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://github.com/christianpayer/MedicalDataAugmentationTool-HeatmapRegression.

  2. 2.

    https://simpleelastix.github.io.

References

  1. Al, W.A., Jung, H.Y., Yun, I.D., Jang, Y., Park, H.B., Chang, H.J.: Automatic aortic valve landmark localization in coronary CT angiography using colonial walk. PLoS ONE 13(7), e0200317 (2018). https://doi.org/10.1371/journal.pone.0200317

    Article  Google Scholar 

  2. Aoyama, G., et al.: Automatic aortic valve cusps segmentation from CT images based on the cascading multiple deep neural networks. J. Imaging 8(1), 11 (2022). https://doi.org/10.3390/jimaging8010011

    Article  Google Scholar 

  3. Bekkouch, I.E.I., Maksudov, B., Kiselev, S., Mustafaev, T., Vrtovec, T., Ibragimov, B.: Multi-landmark environment analysis with reinforcement learning for pelvic abnormality detection and quantification. Med. Image Anal. 78, 102417 (2022). https://doi.org/10.1016/j.media.2022.102417

    Article  Google Scholar 

  4. Calleja, A., et al.: Automated quantitative 3-dimensional modeling of the aortic valve and root by 3-dimensional transesophageal echocardiography in normals, aortic regurgitation, and aortic stenosis. Circ. Cardiovasc. Imaging 6(1), 99–108 (2013). https://doi.org/10.1161/CIRCIMAGING.112.976993

    Article  Google Scholar 

  5. Chen, C., et al.: Deep learning for cardiac image segmentation: a review. Front. Cardiovasc. Med. 7, 25 (2020). https://doi.org/10.3389/fcvm.2020.00025

    Article  Google Scholar 

  6. Coffey, S., et al.: Global epidemiology of valvular heart disease. Nat. Rev. Cardiol. 18, 853–864 (2021). https://doi.org/10.1038/s41569-021-00570-z

    Article  Google Scholar 

  7. Klein, S., Staring, M., Murphy, K., Viergever, M.A., Pluim, J.P.W.: elastix: a toolbox for intensity-based medical image registration. IEEE Trans. Med. Imaging 29(1), 196–205 (2010). https://doi.org/10.1109/TMI.2009.2035616

    Article  Google Scholar 

  8. Krittanawong, C., et al.: Deep learning for cardiovascular medicine: a practical primer. Eur. Heart J. 40(25), 2058–2073 (2019). https://doi.org/10.1093/eurheartj/ehz056

    Article  Google Scholar 

  9. Noothout, J.M.H., et al.: Deep learning-based regression and classification for automatic landmark localization in medical images. IEEE Trans. Med. Imaging 39(12), 4011–4022 (2020). https://doi.org/10.1109/TMI.2020.3009002

    Article  Google Scholar 

  10. Payer, C., Štern, D., Bischof, H., Urschler, M.: Integrating spatial configuration into heatmap regression based CNNs for landmark localization. Med. Image Anal. 54, 207–219 (2019). https://doi.org/10.1016/j.media.2019.03.007

    Article  Google Scholar 

  11. 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 

  12. Tahoces, P.G., et al.: Automatic detection of anatomical landmarks of the aorta in CTA images. Med. Biol. Eng. Comput. 58(5), 903–919 (2020). https://doi.org/10.1007/s11517-019-02110-x

    Article  Google Scholar 

  13. Tretter, J.T., et al.: Understanding the aortic root using computed tomographic assessment: a potential pathway to improved customized surgical repair. Circ. Cardiovasc. Imaging 14(11), e013134 (2021). https://doi.org/10.1161/CIRCIMAGING.121.013134

    Article  Google Scholar 

  14. Yu, H., Yang, L.T., Zhang, Q., Armstrong, D., Deen, M.J.: Convolutional neural networks for medical image analysis: state-of-the art, comparisons, improvement and perspectives. Neurocomputing 444, 92–110 (2021). https://doi.org/10.1016/j.neucom.2020.04.157

    Article  Google Scholar 

  15. Zhou, S.K., Le, H.N., Luu, K., Nguyen, H.V., Ayache, N.: Deep reinforcement learning in medical imaging: a literature review. Med. Image Anal. 73, 102193 (2021). https://doi.org/10.1016/j.media.2021.102193

    Article  Google Scholar 

Download references

Acknowledgements

The study was approved by the Ethics Committee of the University Medical Center Ljubljana, Slovenia, under 0120-133/2021/3 and 0120-312/2022/3, and supported by the Slovenian Research Agency (ARRS) under grants J2-4453 and P2-0232, and by the University Medical Center Ljubljana, Slovenia, under grant 20190174.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Tomaž Vrtovec .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2023 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

Škrlj, L., Jelenc, M., Vrtovec, T. (2023). Detection of Aortic Cusp Landmarks in Computed Tomography Images with Deep Learning. In: Bernard, O., Clarysse, P., Duchateau, N., Ohayon, J., Viallon, M. (eds) Functional Imaging and Modeling of the Heart. FIMH 2023. Lecture Notes in Computer Science, vol 13958. Springer, Cham. https://doi.org/10.1007/978-3-031-35302-4_31

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-35302-4_31

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-35301-7

  • Online ISBN: 978-3-031-35302-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics