Fully Automatic Segmentation of the Mitral Leaflets in 3D Transesophageal Echocardiographic Images Using Multi-atlas Joint Label Fusion and Deformable Medial Modeling

Overview

Journal Med Image Anal

Publisher Elsevier

Specialty Radiology

Date 2013 Nov 5

PMID 24184435

Citations 32

Authors

A M Pouch

H Wang

M Takabe

B M Jackson

J H Gorman 3rd

R C Gorman

P A Yushkevich

C M Sehgal

Affiliations

Soon will be listed here.

Abstract

Comprehensive visual and quantitative analysis of in vivo human mitral valve morphology is central to the diagnosis and surgical treatment of mitral valve disease. Real-time 3D transesophageal echocardiography (3D TEE) is a practical, highly informative imaging modality for examining the mitral valve in a clinical setting. To facilitate visual and quantitative 3D TEE image analysis, we describe a fully automated method for segmenting the mitral leaflets in 3D TEE image data. The algorithm integrates complementary probabilistic segmentation and shape modeling techniques (multi-atlas joint label fusion and deformable modeling with continuous medial representation) to automatically generate 3D geometric models of the mitral leaflets from 3D TEE image data. These models are unique in that they establish a shape-based coordinate system on the valves of different subjects and represent the leaflets volumetrically, as structures with locally varying thickness. In this work, expert image analysis is the gold standard for evaluating automatic segmentation. Without any user interaction, we demonstrate that the automatic segmentation method accurately captures patient-specific leaflet geometry at both systole and diastole in 3D TEE data acquired from a mixed population of subjects with normal valve morphology and mitral valve disease.

Citing Articles

Automatic 4D mitral valve segmentation from transesophageal echocardiography: a semi-supervised learning approach.

Munafo R, Saitta S, Tondi D, Ingallina G, Denti P, Maisano F Med Biol Eng Comput. 2025; .

PMID: 39797996 DOI: 10.1007/s11517-024-03275-w.

Euclidean and Shape-Based Analysis of the Dynamic Mitral Annulus in Children using a Novel Open-Source Framework.

Amin S, Dewey H, Lasso A, Sabin P, Han Y, Vicory J J Am Soc Echocardiogr. 2023; 37(2):259-267.

PMID: 37995938 PMC: 10872766. DOI: 10.1016/j.echo.2023.11.011.

SlicerHeart: An open-source computing platform for cardiac image analysis and modeling.

Lasso A, Herz C, Nam H, Cianciulli A, Pieper S, Drouin S Front Cardiovasc Med. 2022; 9:886549.

PMID: 36148054 PMC: 9485637. DOI: 10.3389/fcvm.2022.886549.

Interplay between Artificial Intelligence and Biomechanics Modeling in the Cardiovascular Disease Prediction.

Li X, Liu X, Deng X, Fan Y Biomedicines. 2022; 10(9).

PMID: 36140258 PMC: 9495955. DOI: 10.3390/biomedicines10092157.

Multimodal image analysis and subvalvular dynamics in ischemic mitral regurgitation.

Aly A, Saito Y, Bouma W, Pilla J, Pouch A, Yushkevich P JTCVS Open. 2022; 5:48-60.

PMID: 36003177 PMC: 9390375. DOI: 10.1016/j.xjon.2020.10.007.

References

Eng M, Salcedo E, Quaife R, Carroll J . Implementation of real time three-dimensional transesophageal echocardiography in percutaneous mitral balloon valvuloplasty and structural heart disease interventions. Echocardiography. 2009; 26(8):958-66. DOI: 10.1111/j.1540-8175.2009.00928.x. View

Schneider R, Tenenholtz N, Perrin D, Marx G, Del Nido P, Howe R . Patient-specific mitral leaflet segmentation from 4D ultrasound. Med Image Comput Comput Assist Interv. 2011; 14(Pt 3):520-7. PMC: 3201763. DOI: 10.1007/978-3-642-23626-6_64. View

Garcia-Orta R, Moreno E, Vidal M, Ruiz-Lopez F, Oyonarte J, Lara J . Three-dimensional versus two-dimensional transesophageal echocardiography in mitral valve repair. J Am Soc Echocardiogr. 2007; 20(1):4-12. DOI: 10.1016/j.echo.2006.07.005. View

Kwan J, Shiota T, Agler D, Popovic Z, Qin J, Gillinov M . Geometric differences of the mitral apparatus between ischemic and dilated cardiomyopathy with significant mitral regurgitation: real-time three-dimensional echocardiography study. Circulation. 2003; 107(8):1135-40. DOI: 10.1161/01.cir.0000053558.55471.2d. View

Crabtree T, Bailey M, Moon M, Munfakh N, Pasque M, Lawton J . Recurrent mitral regurgitation and risk factors for early and late mortality after mitral valve repair for functional ischemic mitral regurgitation. Ann Thorac Surg. 2008; 85(5):1537-42. DOI: 10.1016/j.athoracsur.2008.01.079. View

Pizer S, Fletcher P, Joshi S, Thall A, Chen J, Fridman Y . Deformable M-Reps for 3D Medical Image Segmentation. Int J Comput Vis. 2013; 55(2-3):85-106. PMC: 3697155. DOI: 10.1023/a:1026313132218. View

Lotjonen J, Wolz R, Koikkalainen J, Thurfjell L, Waldemar G, Soininen H . Fast and robust multi-atlas segmentation of brain magnetic resonance images. Neuroimage. 2009; 49(3):2352-65. DOI: 10.1016/j.neuroimage.2009.10.026. View

Wang H, Suh J, Das S, Pluta J, Craige C, Yushkevich P . Multi-Atlas Segmentation with Joint Label Fusion. IEEE Trans Pattern Anal Mach Intell. 2012; 35(3):611-23. PMC: 3864549. DOI: 10.1109/TPAMI.2012.143. View

Mihaljevic T, Lam B, Rajeswaran J, Takagaki M, Lauer M, Gillinov A . Impact of mitral valve annuloplasty combined with revascularization in patients with functional ischemic mitral regurgitation. J Am Coll Cardiol. 2007; 49(22):2191-201. DOI: 10.1016/j.jacc.2007.02.043. View

10.

Collins D, Pruessner J . Towards accurate, automatic segmentation of the hippocampus and amygdala from MRI by augmenting ANIMAL with a template library and label fusion. Neuroimage. 2010; 52(4):1355-66. DOI: 10.1016/j.neuroimage.2010.04.193. View

11.

Votta E, Caiani E, Veronesi F, Soncini M, Montevecchi F, Redaelli A . Mitral valve finite-element modelling from ultrasound data: a pilot study for a new approach to understand mitral function and clinical scenarios. Philos Trans A Math Phys Eng Sci. 2008; 366(1879):3411-34. DOI: 10.1098/rsta.2008.0095. View

12.

Levine R, Hung J, Otsuji Y, Messas E, Liel-Cohen N, Nathan N . Mechanistic insights into functional mitral regurgitation. Curr Cardiol Rep. 2002; 4(2):125-9. DOI: 10.1007/s11886-002-0024-6. View

13.

Ionasec R, Voigt I, Georgescu B, Wang Y, Houle H, Vega-Higuera F . Patient-specific modeling and quantification of the aortic and mitral valves from 4-D cardiac CT and TEE. IEEE Trans Med Imaging. 2010; 29(9):1636-51. DOI: 10.1109/TMI.2010.2048756. View

14.

Flameng W, Herijgers P, Bogaerts K . Recurrence of mitral valve regurgitation after mitral valve repair in degenerative valve disease. Circulation. 2003; 107(12):1609-13. DOI: 10.1161/01.CIR.0000058703.26715.9D. View

15.

Yushkevich P, Zhang H, Gee J . Continuous medial representation for anatomical structures. IEEE Trans Med Imaging. 2006; 25(12):1547-64. DOI: 10.1109/tmi.2006.884634. View

16.

Vergnat M, Jassar A, Jackson B, Ryan L, Eperjesi T, Pouch A . Ischemic mitral regurgitation: a quantitative three-dimensional echocardiographic analysis. Ann Thorac Surg. 2010; 91(1):157-64. PMC: 3021251. DOI: 10.1016/j.athoracsur.2010.09.078. View

17.

Sugeng L, Shernan S, Salgo I, Weinert L, Shook D, Raman J . Live 3-dimensional transesophageal echocardiography initial experience using the fully-sampled matrix array probe. J Am Coll Cardiol. 2008; 52(6):446-9. DOI: 10.1016/j.jacc.2008.04.038. View

18.

Pouch A, Xu C, Yushkevich P, Jassar A, Vergnat M, Gorman 3rd J . Semi-automated mitral valve morphometry and computational stress analysis using 3D ultrasound. J Biomech. 2012; 45(5):903-7. PMC: 3294138. DOI: 10.1016/j.jbiomech.2011.11.033. View

19.

Louie E, Langholz D, Mackin W, WALLIS D, Jacobs W, SCANLON P . Transesophageal echocardiographic assessment of the contribution of intrinsic tissue thickness to the appearance of a thick mitral valve in patients with mitral valve prolapse. J Am Coll Cardiol. 1996; 28(2):465-71. DOI: 10.1016/0735-1097(96)00160-X. View

20.

Jenkinson M, Smith S . A global optimisation method for robust affine registration of brain images. Med Image Anal. 2001; 5(2):143-56. DOI: 10.1016/s1361-8415(01)00036-6. View