Skip to main content
SpringerLink
Log in

Use of a semi-automated cardiac segmentation tool improves reproducibility and speed of segmentation of contaminated right heart magnetic resonance angiography

  • Original Paper
  • Published:
The International Journal of Cardiovascular Imaging Aims and scope Submit manuscript

Abstract

Three-dimensional printing has an increasing number of clinical applications in pediatric cardiology. Time required for dataset segmentation and conversion to stereolithography (STL) format remains a significant limitation. We investigated the impact of semi-automated cardiovascular-specific segmentation software on time and reproducibility of segmentation. Magnetic resonance angiograms (MRAs) of 19 patients undergoing intervention for right ventricular outflow lesions were segmented to demonstrate the right heart. STLs were created by two independent clinicians using semi-automated cardiovascular segmentation (SAS) and traditional manual segmentation (MS). Time was recorded and geometric STL disagreement was determined (0 % = no disagreement, 100 % = complete disagreement). MRA datasets were categorized as clean when only right heart structures were present in the MRA, or contaminated when left heart structures were also present and required removal. Eighteen (seven clean and 11 contaminated) cases were successfully segmented with both methods. Time to STL for clean datasets was faster with MS than SAS [median 209 s (IQR 192–252) vs. 296 s (272–317), p = 0.018] while contaminated datasets were faster with SAS [455 s (384–561) vs. 866 s (310–1429), p = 0.033]. Interobserver STL geometric disagreement was significantly lower using SAS than MS overall (0.70 ± 1.15 % vs. 1.31 ± 1.52 %, p = 0.030), and for the contaminated subset (0.81 ± 1.08 % vs. 1.75 ± 1.57 %, p = 0.036). Most geometric disagreement occurred at areas where left heart contamination was removed. Semi-automated segmentation was faster and more reproducible for contaminated datasets, while MS was faster but equally reproducible for clean datasets. Semi-automated segmentation methods are preferable for contaminated datasets and continued refinement of these tools should be supported.

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

Similar content being viewed by others

References

  1. Dankowski R, Baszko A, Sutherland M, Firek L, Kalmucki P, Wroblewska K, Szyszka A, Groothuis A, Siminiak T (2014) 3D heart model printing for preparation of percutaneous structural interventions: description of the technology and case report. Kardiol Pol 6:546–551. doi:10.5603/KP.2014.0119

    Article  Google Scholar 

  2. Olivieri L, Krieger A, Chen MY, Kim P, Kanter JP (2014) 3D heart model guides complex stent angioplasty of pulmonary venous baffle obstruction in a mustard repair of D-TGA. Int J Cardiol 2:e297–e298. doi:10.1016/j.ijcard.2013.12.192

    Article  Google Scholar 

  3. O’Neill B, Wang DD, Pantelic M, Song T, Guerrero M, Greenbaum A, O’Neill WW (2015) Transcatheter caval valve implantation using multimodality imaging: roles of TEE, CT, and 3D printing. J Am Coll Cardiol Cardiovasc Imaging 2:221–225. doi:10.1016/j.jcmg.2014.12.006

    Article  Google Scholar 

  4. Mathur M, Patil P, Bove A (2015) The role of 3D printing in structural heart disease: all that glitters is not gold. J Am Coll Cardiol Cardiovasc Imaging 8:987–988. doi:10.1016/j.jcmg.2015.03.009

    Article  Google Scholar 

  5. Babar JL, Jones RG, Hudsmith L, Steeds R, Guest P (2010) Application of MR imaging in assessment and follow-up of congenital heart disease in adults. Radiographics 4:1145. doi:10.1148/rg.e40

    Google Scholar 

  6. Fratz S, Chung T, Greil GF, Samyn MM, Taylor AM, Valsangiacomo Buechel ER, Yoo SJ, Powell AJ (2013) Guidelines and protocols for cardiovascular magnetic resonance in children and adults with congenital heart disease: SCMR expert consensus group on congenital heart disease. J Cardiovasc Magn Reson 15(1):51. doi:10.1186/1532-429X-15-51

    Article  PubMed  PubMed Central  Google Scholar 

  7. Heathfield E, Hussain T, Qureshi S, Valverde I, Witter T, Douiri A, Bell A, Beerbaum P, Razavi R, Greil GF (2013) Cardiovascular magnetic resonance imaging in congenital heart disease as an alternative to diagnostic invasive cardiac catheterization: a single center experience. Congenit Heart Dis 4:322–327. doi:10.1111/chd.12032

    Article  Google Scholar 

  8. Kilner PJ, Geva T, Kaemmerer H, Trindade PT, Schwitter J, Webb GD (2010) Recommendations for cardiovascular magnetic resonance in adults with congenital heart disease from the respective working groups of the European Society of Cardiology. Eur Heart J 7:794–805. doi:10.1093/eurheartj/ehp586

    Article  Google Scholar 

  9. Ntsinjana HN, Hughes ML, Taylor AM (2011) The role of cardiovascular magnetic resonance in pediatric congenital heart disease. J Cardiovasc Magn Reson 13(1):51. doi:10.1186/1532-429X-13-51

    Article  PubMed  PubMed Central  Google Scholar 

  10. Valsangiacomo Buechel ER, Grosse-Wortmann L, Fratz S, Eichhorn J, Sarikouch S, Greil GF, Beerbaum P, Bucciarelli-Ducci C, Bonello B, Sieverding L, Schwitter J, Helbing WA, Eacvi, Galderisi M, Miller O, Sicari R, Rosa J, Thaulow E, Edvardsen T, Brockmeier K, Qureshi S, Stein J (2015) Indications for cardiovascular magnetic resonance in children with congenital and acquired heart disease: an expert consensus paper of the Imaging Working Group of the AEPC and the Cardiovascular Magnetic Resonance Section of the EACVI. Eur Heart J Cardiovasc Imaging 3:281–297. doi:10.1093/ehjci/jeu129

    Article  Google Scholar 

  11. Valverde I, Parish V, Hussain T, Rosenthal E, Beerbaum P, Krasemann T (2011) Planning of catheter interventions for pulmonary artery stenosis: improved measurement agreement with magnetic resonance angiography using identical angulations. Catheter Cardiovasc Interv 3:400–408. doi:10.1002/ccd.22695

    Article  Google Scholar 

  12. Chung R, Taylor AM (2014) Imaging for preintervention planning: transcatheter pulmonary valve therapy. Circ Cardiovasc Imaging 1:182–189. doi:10.1161/CIRCIMAGING.113.000826

    Article  Google Scholar 

  13. Goreczny S, Eicken A, Ewert P, Morgan GJ, Fratz S (2014) A new strategy to identify potentially dangerous coronary arterial patterns before percutaneous pulmonary valve implantation. Postep Kardiol Interwencyjnej 4:294–297. doi:10.5114/pwki.2014.46773

    Google Scholar 

  14. Khambadkone S (2012) Percutaneous pulmonary valve implantation. Ann Pediatr Cardiol 1:53–60. doi:10.4103/0974-2069.93713

    Article  Google Scholar 

  15. Schievano S, Migliavacca F, Coats L, Khambadkone S, Carminati M, Wilson N, Deanfield JE, Bonhoeffer P, Taylor AM (2007) Percutaneous pulmonary valve implantation based on rapid prototyping of right ventricular outflow tract and pulmonary trunk from MR data. Radiology 2:490–497. doi:10.1148/radiol.2422051994

    Article  Google Scholar 

  16. Hussain T, Greil GF, Bilska K, Miller OI (2011) Toward defining pulmonary sequestration in infancy using two-dimensional echocardiography and novel high temporal resolution "keyhole" three-dimensional magnetic resonance angiography. Congenit Heart Dis 5:488–491. doi:10.1111/j.174-0803.2011.00551.x

    Article  Google Scholar 

  17. Zou KH, Warfield SK, Bharatha A, Tempany CM, Kaus MR, Haker SJ, Wells WM 3rd, Jolesz FA, Kikinis R (2004) Statistical validation of image segmentation quality based on a spatial overlap index. Acad Radiol 2:178–189

    Article  Google Scholar 

  18. Willinek WA, Hadizadeh DR, von Falkenhausen M, Urbach H, Hoogeveen R, Schild HH, Gieseke J (2008) 4D time-resolved MR angiography with keyhole (4D-TRAK): more than 60 times accelerated MRA using a combination of CENTRA, keyhole, and SENSE at 3.0T. J Magn Reson Imaging 6:1455–1460. doi:10.1002/jmri.21354

    Article  Google Scholar 

  19. Prieto C, Uribe S, Razavi R, Atkinson D, Schaeffter T (2010) 3D undersampled golden-radial phase encoding for DCE-MRA using inherently regularized iterative SENSE. Magn Reson Med 2:514–526. doi:10.1002/mrm.22446

    Google Scholar 

  20. Rapacchi S, Han F, Natsuaki Y, Kroeker R, Plotnik A, Lehrman E, Sayre J, Laub G, Finn JP, Hu P (2014) High spatial and temporal resolution dynamic contrast-enhanced magnetic resonance angiography using compressed sensing with magnitude image subtraction. Magn Reson Med 5:1771–1783. doi:10.1002/mrm.24842

    Article  Google Scholar 

Download references

Acknowledgments

AT, TH, and GFG were supported by the Early Career Research Award, Children’s Clinical Research Advisory Committee, Children’s Medical Center, Dallas.

Author contribution

AT and TH performed the segmentation. SZ, TH, and AT performed data analysis. All authors contributed to project design, drafting the article, and critical revision of the article. All authors approve of the content of the article.

Author information

Authors and Affiliations

  1. Department of Pediatrics, University of Texas Southwestern Medical Center, Dallas, TX, USA

    Animesh Tandon, Adrian K. Dyer, Gerald F. Greil & Tarique Hussain

  2. Department of Radiology, University of Texas Southwestern Medical Center, Dallas, TX, USA

    Animesh Tandon, Jeanne M. Dillenbeck, Gerald F. Greil & Tarique Hussain

  3. Pediatric Cardiology, Children’s Medical Center Dallas, 1935 Medical District Drive, Dallas, TX, 75235, USA

    Animesh Tandon, Adrian K. Dyer, Jeanne M. Dillenbeck, Gerald F. Greil & Tarique Hussain

  4. Department of Clinical Sciences, University of Texas Southwestern Medical Center, Dallas, TX, USA

    Song Zhang

  5. Division of Imaging Sciences and Biomedical Engineering, King’s College London, London, UK

    Nicholas Byrne & Maria de las Nieves Velasco Forte

  6. Medical Physics, Guy’s and St. Thomas’ NHS Foundation Trust, London, UK

    Nicholas Byrne

Authors
  1. Animesh Tandon
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nicholas Byrne
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Maria de las Nieves Velasco Forte
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Song Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Adrian K. Dyer
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jeanne M. Dillenbeck
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Gerald F. Greil
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Tarique Hussain
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Animesh Tandon.

Ethics declarations

Conflicts of interest

All authors report no conflict of interest. AT, AKD, JMD, GFG, and TH all work at Children’s Medical Center, Dallas. We have full control of the primary data and agree to allow review of the data if requested.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tandon, A., Byrne, N., Nieves Velasco Forte, M. et al. Use of a semi-automated cardiac segmentation tool improves reproducibility and speed of segmentation of contaminated right heart magnetic resonance angiography. Int J Cardiovasc Imaging 32, 1273–1279 (2016). https://doi.org/10.1007/s10554-016-0906-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10554-016-0906-0

Keywords

Search

Navigation