Nothing Special   »   [go: up one dir, main page]
Skip to main content

Advertisement

Springer Nature Link
Log in

Automatic measurement plane placement for 4D Flow MRI of the great vessels using deep learning

  • Original Article
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Purpose

Despite the great potential and flexibility of 4D flow MRI for hemodynamic analysis, a major limitation is the need for time-consuming and user-dependent post-processing. We propose a fast four-step algorithm for rapid, robust, and repeatable flow measurements in the great vessels based on automatic placement of measurement planes and vessel segmentation.

Methods

Our algorithm works by (1) subsampling the 3D image into 3D patches, (2) predicting the probability of each patch containing individual vessels and location/orientation of the vessel within the patch via a convolutional neural network, (3) selecting the predicted planes with highest probabilities for each vessel, and (4) shifting the plane centers to the maximum velocity within each plane. The method was trained on 283 scans and evaluated on 40 unseen scans by comparing algorithm-derived processing times, plane locations, and flow measurements to those of two manual observers (graduate students) using t-tests, Pearson correlation, and Bland–Altman analysis.

Results

The average processing time for the algorithm (18 s) was shorter than observer 1 (362 s; P < 0.001) and observer 2 (317 s; P < 0.001). The distance between planes placed by the algorithm and those placed by manual observers was slightly greater (O1 vs. algorithm: 9.0 mm, O2 vs. algorithm: 10.3 mm) than the distance between planes placed by the two manual observers (8.3 mm). The correlation between flow values for planes placed by the algorithm and those placed by manual observers was slightly lower (O1 vs. algorithm: R = 0.68, O2 vs. algorithm: R = 0.72) than the flow correlation between the two manual observers (R = 0.81).

Conclusion

Our method is a feasible and accurate approach for fast, reproducible, and automated flow measurement and visualization in 4D flow MRI of the great vessels, with similar variability compared to a manual annotator as the variability between two manual observers. This approach could be applied in other anatomical regions.

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

Access this article

Log in via an institution

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

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
Fig. 8

Similar content being viewed by others

Data availability

Due to privacy concerns, we are unable to share the images used to train and test the algorithm publicly. However, a small number of deidentified images may be provided upon reasonable request.

Code availability

The code used to train the network, test the algorithm, and generate the figures and tables is available online at https://github.com/pcorrado/DL-Vessel-Localization.

References

  1. Markl M, Frydrychowicz A, Kozerke S, Hope M, Wieben O (2012) 4D flow MRI. J Magn Reson Imaging 36:1015–1036. https://doi.org/10.1002/jmri.23632

    Article  PubMed  Google Scholar 

  2. Hope MD, Meadows AK, Hope TA, Ordovas KG, Saloner D, Reddy GP, Alley MT, Higgins CB (2010) Clinical evaluation of aortic coarctation with 4D flow MR imaging. J Magn Reson Imaging 31:711–718. https://doi.org/10.1002/jmri.22083

    Article  PubMed  Google Scholar 

  3. Stalder AF, Russe MF, Frydrychowicz A, Bock J, Hennig J, Markl M (2008) Quantitative 2D and 3D phase contrast MRI: optimized analysis of blood flow and vessel wall parameters. Magn Reson Med 60:1218–1231. https://doi.org/10.1002/mrm.21778

    Article  CAS  PubMed  Google Scholar 

  4. Hope MD, Hope TA, Meadows AK, Ordovas KG, Urbania TH, Alley MT, Higgins CB (2010) Bicuspid aortic valve: four-dimensional MR evaluation of ascending aortic systolic flow patterns. Radiology 255:53–61. https://doi.org/10.1148/radiol.09091437

    Article  PubMed  Google Scholar 

  5. Frydrychowicz A, Wieben O, Niespodzany E, Reeder SB, Johnson KM, François CJ (2013) Quantification of thoracic blood flow using volumetric magnetic resonance imaging with radial velocity encoding: in vivo validation. Invest Radiol 48:819–825. https://doi.org/10.1097/RLI.0b013e31829a4f2f

    Article  PubMed  Google Scholar 

  6. Tariq U, Hsiao A, Alley M, Zhang T, Lustig M, Vasanawala SS (2013) Venous and arterial flow quantification are equally accurate and precise with parallel imaging compressed sensing 4D phase contrast MRI. J Magn Reson Imaging 37:1419–1426. https://doi.org/10.1002/jmri.23936

    Article  PubMed  Google Scholar 

  7. Dyverfeldt P, Bissell M, Barker AJ, Bolger AF, Carlhäll C-J, Ebbers T, Francios CJ, Frydrychowicz A, Geiger J, Giese D, Hope MD, Kilner PJ, Kozerke S, Myerson S, Neubauer S, Wieben O, Markl M (2015) 4D flow cardiovascular magnetic resonance consensus statement. J Cardiovasc Magn Reson 17:72. https://doi.org/10.1186/s12968-015-0174-5

    Article  PubMed  PubMed Central  Google Scholar 

  8. Geiger J, Hirtler D, Gottfried K, Rahman O, Bollache E, Barker AJ, Markl M, Stiller B (2017) Longitudinal evaluation of aortic hemodynamics in marfan syndrome: new insights from a 4D flow cardiovascular magnetic resonance multi-year follow-up study. J Cardiovasc Magn Reson 19:1–11. https://doi.org/10.1186/s12968-017-0347-5

    Article  Google Scholar 

  9. Bannas P, Roldán-alzate A, Johnson KM, Woods MA, Reeder SB, Ozkan O, Motosugi U, Wieben O, Reeder SB, Kramer H (2016) Longitudinal monitoring of hepatic blood flow before and after TIPS by using 4D-flow MR imaging. Radiology 281:574–582. https://doi.org/10.1148/radiol.2016152247

    Article  PubMed  Google Scholar 

  10. Suri JS, Liu K, Reden L, Laxminarayan S (2002) A review on MR vascular image processing algorithms: acquisition and prefiltering: Part I. IEEE Trans Inf Technol Biomed 6:324–337. https://doi.org/10.1109/TITB.2002.804139

    Article  PubMed  Google Scholar 

  11. Van Pelt R, Nguyen H, Ter Haar RB, Vilanova A (2012) Automated segmentation of blood-flow regions in large thoracic arteries using 3D-cine PC-MRI measurements. Int J Comput Assist Radiol Surg 7:217–224. https://doi.org/10.1007/s11548-011-0642-9

    Article  PubMed  Google Scholar 

  12. Bustamante M, Petersson S, Eriksson J, Alehagen U, Dyverfeldt P, Carlhäll CJ, Ebbers T (2015) Atlas-based analysis of 4D flow CMR: Automated vessel segmentation and flow quantification. J Cardiovasc Magn Reson 17:1–12. https://doi.org/10.1186/s12968-015-0190-5

    Article  Google Scholar 

  13. Berhane H, Scott M, Elbaz M, Jarvis K, McCarthy P, Carr J, Malaisrie C, Avery R, Barker AJ, Robinson JD, Rigsby CK, Markl M (2020) Fully automated 3D aortic segmentation of 4D flow MRI for hemodynamic analysis using deep learning. Magn Reson Med. https://doi.org/10.1002/mrm.28257

    Article  PubMed  PubMed Central  Google Scholar 

  14. Blansit K, Retson T, Masutani E, Bahrami N, Hsiao A (2019) Deep learning-based prescription of cardiac MRI Planes. Radiol Artif Intell 1:e180069. https://doi.org/10.1148/ryai.2019180069

    Article  PubMed  PubMed Central  Google Scholar 

  15. Gu T, Korosec FR, Block WF, Fain SB, Turk Q, Lum D, Zhou Y, Grist TM, Haughton V, Mistretta CA (2005) PC VIPR: a high-speed 3D phase-contrast method for flow quantification and high-resolution angiography. Am J Neuroradiol 26:743–749

    PubMed  PubMed Central  Google Scholar 

  16. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 2016:770–778. https://doi.org/10.1109/CVPR.2016.90

    Article  Google Scholar 

  17. Chollet F (2015) Keras. https://keras.io

  18. Jain AK, Dubes RC (1988) Algorithms for clustering data. Prentice Hall, Engle-wood Cliffs, NJ

    Google Scholar 

  19. Schrauben E, Wåhlin A, Ambarki K, Spaak E, Malm J, Wieben O, Eklund A (2015) Fast 4D flow MRI intracranial segmentation and quantification in tortuous arteries. J Magn Reson Imaging 42:1458–1464. https://doi.org/10.1002/jmri.24900

    Article  PubMed  PubMed Central  Google Scholar 

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

    Article  Google Scholar 

  21. Markl M, Kilner PJ, Ebbers T (2011) Comprehensive 4D velocity mapping of the heart and great vessels by cardiovascular magnetic resonance. J Cardiovasc Magn Reson 13:1–22

    Article  Google Scholar 

  22. Bustamante M, Gupta V, Forsberg D, Carlhäll CJ, Engvall J, Ebbers T (2018) Automated multi-atlas segmentation of cardiac 4D flow MRI. Med Image Anal 49:128–140. https://doi.org/10.1016/j.media.2018.08.003

    Article  PubMed  Google Scholar 

  23. Oktay O, Bai W, Guerrero R, Rajchl M, De Marvao A, O’Regan DP, Cook SA, Heinrich MP, Glocker B, Rueckert D (2017) Stratified decision forests for accurate anatomical landmark localization in cardiac images. IEEE Trans Med Imaging 36:332–342. https://doi.org/10.1109/TMI.2016.2597270

    Article  PubMed  Google Scholar 

  24. Alansary A, Oktay O, Li Y, Le FL, Hou B, Vaillant G, Kamnitsas K, Vlontzos A, Glocker B, Kainz B, Rueckert D (2019) Evaluating reinforcement learning agents for anatomical landmark detection. Med Image Anal 53:156–164. https://doi.org/10.1016/j.media.2019.02.007

    Article  PubMed  PubMed Central  Google Scholar 

  25. Wang Z, Schaul T, Hessel M, Hasselt H, Lanctot M, Freitas N (2016) Dueling Network Architectures for Deep Reinforcement Learning. In: Proceedings of the 33rd international conference on machine learning, PMLR, vol 48. pp. 1995–2003

  26. van Pelt R, Olivan Bescos J, Breeuwer M, Clough RE, Groller ME, ter Haar RB, Vilanova A (2011) Interactive virtual probing of 4D MRI blood-flow. IEEE Trans Vis Comput Graph 17:2153–2162. https://doi.org/10.1109/TVCG.2011.215

    Article  PubMed  Google Scholar 

Download references

Funding

Philip A Corrado is supported by the National Heart, Lung, And Blood Institute of the NIH under Award Number F31HL144020. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

Author information

Authors and Affiliations

  1. Department of Medical Physics, University of Wisconsin-Madison, Madison, WI, USA

    Philip A. Corrado & Daniel P. Seiter

  2. Departments of Medical Physics and Radiology, University of Wisconsin-Madison, Madison, WI, USA

    Oliver Wieben

Authors
  1. Philip A. Corrado
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Daniel P. Seiter
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Oliver Wieben
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

PAC and OW designed the study. PAC wrote the code for the manual annotation GUI. PAC and DPS performed the manual plane placement. PAC designed the algorithm and trained the network, with input from DPS. PAC drafted the initial manuscript. All authors helped edit the manuscript and approved the final version.

Corresponding author

Correspondence to Philip A. Corrado.

Ethics declarations

Conflict of interest

Philip A. Corrado has no relevant conflicts of interest or competing interests to disclose. Daniel P. Seiter has no relevant conflicts of interest or competing interests to disclose. Oliver Wieben has no relevant conflicts of interest or competing interests to disclose.

Ethical approval

The studies used to acquire the data used in this study were approved by the University of Wisconsin-Madison Health Sciences Institutional Review Board (IRB) and were compliant with the Health Insurance Portability and Accountability Act.

Consent to participate

In accordance with our IRB protocols, written informed consent was obtained from all subjects.

Consent for publication

Not applicable as this manuscript does not contain any identifiable data from any individual person.

Additional information

Publisher's Note

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

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file 1 (PDF 10 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Corrado, P.A., Seiter, D.P. & Wieben, O. Automatic measurement plane placement for 4D Flow MRI of the great vessels using deep learning. Int J CARS 17, 199–210 (2022). https://doi.org/10.1007/s11548-021-02475-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-021-02475-1

Keywords

Search

Navigation