Skip to main content
SpringerLink
Log in

Neural Network Vessel Lumen Regression for Automated Lumen Cross-Section Segmentation in Cardiovascular Image-Based Modeling

  • Original Article
  • Published:
Cardiovascular Engineering and Technology Aims and scope Submit manuscript

Abstract

Purpose

We accelerate a pathline-based cardiovascular model building method by training machine learning models to directly predict vessel lumen surface points from computed tomography (CT) and magnetic resonance (MR) medical image data.

Methods

We formulate vessel lumen detection as a regression task using a polar coordiantes representation.

Results

Neural networks trained with our regression formulation allow predictions to be made with significantly higher accuracy than existing methods that identify the vessel lumen through binary pixel classification. The regression formulation enables machine learning models to be trained end-to-end for vessel lumen detection without post-processing steps that reduce accuracy.

Conclusion

By employing our models in a pathline-based cardiovascular model building pipeline we substantially reduce the manual segmentation effort required to build accurate cardiovascular models, and reduce the overall time required to perform patient-specific cardiovascular simulations. While our method is applied here for cardiovascular model building it is generally applicable to segmentation of tree-like and tubular structures from image data.

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

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Figure 14
Figure 15
Figure 16
Figure 17
Figure 18
Figure 19
Figure 20
Figure 21
Figure 22
Figure 23

Similar content being viewed by others

Notes

  1. http://www.simvascular.org/.

  2. http://www.vascularmodel.com.

References

  1. Antiga, L., M. Piccinelli, and L. Botti. Ene-Iordache, B., Remuzzi, A., Steinman, D.A.: An image-based modeling framework for patient-specific computational hemodynamics. Med. Biol. Eng. Comput. 46:2008.

  2. Becker, C., R. Rigamonti, V. Lepetit, and P. Fua. Supervised Feature Learning for Curvilinear Structure Segmentation. Med. Image Comput. Comput. Assist. Interv. 2013.

  3. Benmansour, F., and L. Cohen. Tubular Structure Segmentation Based on Minimal Path Method and Anisotropic Enhancement. Int. J. Comput. Vis. 92:2011

  4. Chen, H., Q. Dou, L. Yu, J. Qin, and P.A. Heng. VoxResNet: deep voxelwise residual networks for brain segmentation from 3d MR images. NeuroImage 170:446–455, 2018. https://doi.org/10.1016/j.neuroimage.2017.04.041.

    Article  Google Scholar 

  5. Chen, L. C., G. Papandreou, I. Kokkinos, K. Murphy, and L., Y.A. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. arXiv 2016.

  6. Doost, S. N., D. Ghista, B. Su, L. Zhong, and Y. S. Morsi. Heart Blood Flow Simulation: a Perspective Review. Biomed. Eng. 15, 2016.

  7. Dou, Q., et al. 3d deeply supervised network for automated segmentation of volumetric medical images. Med. Image Anal. 41:40–54 2017. https://doi.org/10.1016/j.media.2017.05.001.

    Article  Google Scholar 

  8. Frangi, A., W. Niessen, K. Vincken, and M. Viergever. Multiscale vessel enhancement filtering. Medical Image Computing and Computer-Assisted Intervention 1998.

  9. Friman, O., M. Hindennach, C. Kuhnel, and H. O. Peitgen. Multiple Hypothesis Template Tracking of Small 3D Vessel Structures. Med. Image Anal. 14:2010.

  10. Grady, L. Multilabel Random Walker Image Segmentation Using Prior Models. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), vol. 1, pp. 763–770. IEEE, San Diego, CA, USA 2005. https://doi.org/10.1109/CVPR.2005.239.

  11. Gu, Z., J. Cheng, H. Fu, K. Zhou, H. Hao, Y. Zhao, T. Zhang, S. Gao, and J. Liu. Ce-net: Context encoder network for 2d medical image segmentation. arXiv 2019.

  12. He, K., X. Zhang, S. Ren, and J. Sun. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. International Conference on Computer Vision 2015.

  13. Heidenreich, P., et al. Forecasting the future of cardiovascular disease in the United States: A policy statement from the American Heart Association. Circulation 123:2011.

  14. Hoogi, A., A. Subramaniam, R. Veerapaneni, and D. L. Rubin. Adaptive Estimation of Active Contour Parameters Using Convolutional Neural Networks and Texture Analysis. IEEE Trans. Med. Imaging 36:2017.

  15. Hornik, K. Approximation capabilities of multilayer feedforward networks. Neural Netw. 4:1991.

  16. Kamnitsas, K., et al. Efficient multi-scale 3d cnn with fully connected crf for accurate brain lesion segmentation. Med. Image Anal. 2016.

  17. Kerrien, E., A. Yureidini, J. Dequidt, C. Duriez, R. Anxionnat, and S. Cotin. Blood vessel modeling for interactive simulation of interventional neuroradiology procedures. Med. Image Anal. 35:2017.

  18. Khlebnikov, R., and C. Figueroa. Crimson: Towards a software environment for patient-specific blood flow simulation for diagnosis and treatment. Clinical Image-Based Procedures. Transl. Res. Med. Imaging 2016.

  19. Kingma, D., and J. Ba. Adam: A method for stochastic optimization. International Conference on Learning Representations 2015.

  20. Kretschmer, J., C. Godenschwager, B. Preim, and M. Stamminger. Interactive patient-specific vascular modeling with sweep surfaces. IEEE Trans. Visualiz. Comput. Graph. 19:2013.

  21. Krissian, K., G. Malandain, and A. Nicholas. Model-Based Detection of Tubular Structures in 3D Images. Comput. Vis. Image Understand. 80:2000.

  22. Law, M. W. K., and A. C. S. Chung. Three Dimensional Curvilinear Structure Detection Using Optimally Oriented Flux. European Conference on Computer Vision 2008.

  23. Law, M. W. K., and A. C. S. Chung. An oriented flux symmetry based active contour model for three dimensional vessel segmentation. European Conference on Computer Vision 2010.

  24. LeCun, Y., Y. Bengio, and G. Hinton. Deep learning. Nature 521(7553):436–444 2015.

    Article  Google Scholar 

  25. Lesage, D., E. Angelini, I. Bloch, and G. Funka-Lea. A review of 3D vessel lumen segmentation techniques: Models, features and extraction schemes. Med. Image Anal. 13: 2009.

  26. Lorigo, L. M., et al. CURVES: Curve Evolution for Vessel Segmentation. Med. Image Anal. 5:2001.

  27. Maher, G. D., N. W. Wilson, and A. L. Marsden. Accelerating Cardiovascular Model Building with Convolutional Neural Networks. Medical and Biological Engineering and Computing 2019.

  28. Marsden, A. Simulation based planning of surgical interventions in pediatric cardiology. Phys. Fluids 25:2013.

  29. Merkow, J., A. Marsden, D. Kriegman, and Z. Tu. Dense volume-to-volume vascular boundary detection. In: Medical Image Computing and Computer-Assisted Intervention. Springer, Cham 2016.

  30. Merkow, J., Z. Tu, D. Kriegman, and A. Marsden. Structural edge detection for cardiovascular modeling. In: MICCAI 2015, pp. 735–742. Springer 2015.

  31. Moreno, R. and Ö. Smedby. Gradient-based enhancement of tubular structures in medical images. Med. Image Anal. 26:2015.

  32. Petersen, K., M. Schaap, D. Lesage, M. Lee, and L. Grady. Fast and Accurate Segmentation of Coronary Arteries for Improved Cardiovascular Care. GPU Technology Conference p. 55, 2017.

  33. Pezold, S., et al. Automatic, Robust, and Globally Optimal Segmentation of Tubular Structures. Medical Image Computing and Computer Assisted Intervention 2016.

  34. Ronneberger, O., P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer Assisted Intervention 2015.

  35. Rudyanto, R., et al. Comparing algorithms for automated vessel segmentation in computed tomography scans of the lung: the vessel 12 study. Med. Image Anal. 18:2014.

  36. Sankaran, S., H. Kim, G. Choi, and C. Taylor. Uncertainty quantification in coronary blood flow simulations: Impact of geometry, boundary conditions and blood viscosity. J. Biomech. 49:2016.

  37. Schaap, M., et al. Standardized Evaluation Methodology and Reference Database for Evaluating Coronary Artery Centerline Extraction Algorithms. Med. Image Anal. 13:2009.

  38. Schmidhuber, J. Deep learning in neural networks: an overview. Neural Netw. 61:85–117, 2015. https://doi.org/10.1016/j.neunet.2014.09.003.

    Article  Google Scholar 

  39. Schumann, C., M. Neugebauer, R. Bade, B. Preim, and H. Peitgen. Implicit vessel surface reconstruction for visualization and CFD simulation. Int. J. Comput. Assist. Radiol. Surg. 2:2008.

  40. Szegedy, C., et al. Going Deepr with Convolutions. Conf. Comput. Vis. Pattern Recogn. 2015.

  41. Taha, A. A., and A. Hanbury. Metrics for Evaluating 3D Medical Image Segmentation: Analysis, Selection and Tool. BMC Med. Imaging 15:2015.

  42. Taylor, C., and C. Figueroa. Patient-specific Modeling of Cardiovascular Mechanics. Ann. Rev. Biomed. Eng. 11:2009.

  43. Updegrove, A., N. Wilson, J. Merkow, H. Lan, A. Marsden, and S. Shadden. SimVascular: An Open Source Pipeline for Cardiovascular Simulation. Ann. Biomed. Eng. 61:2013.

  44. Updegrove, A., N. Wilson, and S. Shadden. Boolean and smoothing of discrete surfaces. Adv. Eng. Softw. 95:2016.

  45. Urick, B., M., S.T., S.S. Hossain, Y.J. Zhang, and T. J. R. Hughes. Review of patient-specific vascular modeling: Template-based isogeometric framework and the case for cad. Arch. Comput. Methods Eng. 26:2019.

  46. Wang, K.C.Y. Level set methods for computational prototyping with application to hemodynamic modeling. Ph.D. thesis, Stanford University 2001.

  47. Wilson, N., A. Ortiz, and A. Johnson. The Vascular Model Repository: A Public Resource of Medical Imaging Data and Blood Flow Simulation Results. J. Med. Dev. 7:2013.

  48. Wolterink, J. M., T. Leriner, and I. Isgum. Graph convolutional networks for coronary artery segmentation in cardiac CT angiography. arXiv 2020.

  49. Xie, E., P. Sun, X. Song, W. Wang, D. Liang, C. Shen, and P. Luo. Polarmask: Single shot instance segmentation with polar representation. arXiv 2020.

  50. Zhang, Y., Y. Bazilevs, S. Goswami, C. Bajaj, and T. Hughes. Patient-specific vascular NURBS modeling for isogeometric analysis of blood flow. Comput. Methods Appl. Mech. Eng. 196:2007.

Download references

Funding

This research was funded by the National Science Foundation Software Infrastructure for Sustained Innovation (SSI) Grants 1663671 and 1562450, National Institute of Health Grants R01HL123689 and R01EB018302 and the American Heart Association Precision Medicine Platform.

Data Availability

The used datasets can be found at the Vascular Model Repository (www.vascularmodel.com).

Author information

Authors and Affiliations

  1. Institute for Computational and Mathematical Engineering, Stanford University, Stanford, CA, USA

    Gabriel Maher

  2. Research Computing, Stanford University, Stanford, CA, USA

    David Parker

  3. Open Source Medical Software Corporation, Los Angeles, CA, USA

    Nathan Wilson

  4. Pediatric Cardiology, Bioengineering, Stanford University, Stanford, CA, USA

    Alison Marsden

Authors
  1. Gabriel Maher
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. David Parker
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Nathan Wilson
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Alison Marsden
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Alison Marsden.

Ethics declarations

Code Availability

The trained neural networks and application code are available through the SimVascular software (www.simvascular.org).

Conflict of interest

Gabriel Maher, David Parker, Nathan Wilson and Alison Marsden declare that they have no conflict of interest.

Additional information

Associate Editor Wei Sun oversaw the review of this article.

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Maher, G., Parker, D., Wilson, N. et al. Neural Network Vessel Lumen Regression for Automated Lumen Cross-Section Segmentation in Cardiovascular Image-Based Modeling. Cardiovasc Eng Tech 11, 621–635 (2020). https://doi.org/10.1007/s13239-020-00497-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13239-020-00497-5

Keywords

Search

Navigation