Abstract
Purpose
Transcatheter aortic valve replacement (TAVR) is the standard of care in a large population of patients with severe symptomatic aortic valve stenosis. The sizing of TAVR devices is done from ECG-gated CT angiographic image volumes. The most crucial step of the analysis is the determination of the aortic valve annular plane. In this paper, we present a fully tridimensional recursive multiresolution convolutional neural network (CNN) to infer the location and orientation of the aortic valve annular plane.
Methods
We manually labeled 1007 ECG-gated CT volumes from 94 patients with severe degenerative aortic valve stenosis. The algorithm was implemented and trained using the TensorFlow framework (Google LLC, USA). We performed K-fold cross-validation with K = 9 groups such that CT volumes from a given patient are assigned to only one group.
Results
We achieved an average out-of-plane localization error of (0.7 ± 0.6) mm for the training dataset and of (0.9 ± 0.8) mm for the evaluation dataset, which is on par with other published methods and clinically insignificant. The angular orientation error was (3.9 ± 2.3)° for the training dataset and (6.4 ± 4.0)° for the evaluation dataset. For the evaluation dataset, 84.6% of evaluation image volumes had a better than 10° angular error, which is similar to expert-level accuracy. When measured in the inferred annular plane, the relative measurement error was (4.73 ± 5.32)% for the annular area and (2.46 ± 2.94)% for the annular perimeter.
Conclusions
The proposed algorithm is the first application of CNN to aortic valve planimetry and achieves an accuracy on par with proposed automated methods for localization and approaches an expert-level accuracy for orientation. The method relies on no heuristic specific to the aortic valve and may be generalizable to other anatomical features.
Similar content being viewed by others
References
Matiasz R, Rigolin VH (2018) 2017 Focused update for management of patients with valvular heart disease: summary of new recommendations. J Am Heart Assoc 7(1):e007596
Blanke P, Weir-McCall J, Achenbach S, Delgado V, Hausleiter J, Jilaihawi H, Marwan M, Norgaard BL, Piazza N, Schoenhagen P, Leipsic JA (2019) Computed tomography imaging in the context of transcatheter aortic valve implantation (TAVI)/transcatheter aortic valve replacement (TAVR): an expert consensus document of the society of cardiovascular computed tomography. J Cardiovasc Comput Tomogr 13(1):1–20. https://doi.org/10.1016/j.jcct.2018.11.008
Vaquerizo B, Spaziano M, Alali J, Mylote D, Theriault-Lauzier P, Alfagih R, Martucci G, Buithieu J, Piazza N (2015) Three-dimensional echocardiography vs. computed tomography for transcatheter aortic valve replacement sizing. Eur Heart J Cardiovasc Imag 17(1):15–23
Mylotte D, Dorfmeister M, Elhmidi Y, Mazzitelli D, Bleiziffer S, Wagner A, Noterdaeme T, Lange R, Piazza N (2014) Erroneous measurement of the aortic annular diameter using 2-dimensional echocardiography resulting in inappropriate corevalve size selection. JACC Cardiovasc Intervent 7(6):652–661
Piazza N, de Jaegere P, Schultz C, Becker AE, Serruys PW, Anderson RH (2008) Anatomy of the aortic valvar complex and its implications for transcatheter implantation of the aortic valve. Circ Cardiovasc Interv 1(1):74–81
Schuhbaeck A, Achenbach S, Pflederer T, Marwan M, Schmid J, Nef H, Rixe J, Hecker F, Schneider C, Lell M, Uder M, Arnold M (2014) Reproducibility of aortic annulus measurements by computed tomography. Eur Radiol 24(8):1878–1888. https://doi.org/10.1007/s00330-014-3199-5
Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84–90. https://doi.org/10.1145/3065386
LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Backpropagation Applied to Handwritten Zip Code Recognition. Neural Comput 1(4):541–551
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention—MICCAI 2015, pp 234–241
Zhang W, Doi K, Giger ML, Wu Y, Nishikawa RM, Schmidt RA (1994) Computerized detection of clustered microcalcifications in digital mammograms using a shift-invariant artificial neural network. Med Phys 21(4):517–524. https://doi.org/10.1118/1.597177
Tajbakhsh N, Shin JY, Gurudu SR, Hurst RT, Kendall CB, Gotway MB, Liang J (2016) Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans Med Imaging 35(5):1299–1312
Milletari F, Navab N, Ahmadi S (2016) V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 fourth international conference on 3D vision (3DV), pp 565–571
Hennemuth A, Boskamp T, Fritz D, Kühnel C, Bock S, Rinck D, Scheuering M, Peitgen H (2005) One-click coronary tree segmentation in CT angiographic images. Int Congr Ser 1281:317–321
Ecabert O, Peters J, Schramm H, Lorenz C, von Berg J, Walker MJ, Vembar M, Olszewski ME, Subramanyan K, Lavi G, Weese J (2008) Automatic model-based segmentation of the heart in CT images. IEEE Trans Med Imaging 27(9):1189–1201
Ionasec RI, Voigt I, Georgescu B, Wang Y, Houle H, Vega-Higuera F, Navab N, Comaniciu D (2010) Patient-specific modeling and quantification of the aortic and mitral valves from 4-D cardiac CT and TEE. IEEE Trans Med Imaging 29(9):1636–1651
Waechter I, Kneser R, Korosoglou G, Peters J, Bakker NH, van der Boomen R, Weese J (2010) Patient specific models for planning and guidance of minimally invasive aortic valve implantation. Med Image Comput Comput Assist Interv 13(Pt 1):526–533
Zheng Y, John M, Liao R, Nottling A, Boese J, Kempfert J, Walther T, Brockmann G, Comaniciu D (2012) Automatic aorta segmentation and valve landmark detection in C-Arm CT for transcatheter aortic valve implantation. IEEE Trans Med Imaging 31(12):2307–2321
Elattar MA, Wiegerinck EM, Planken RN, vanbavel E, van Assen HC, Baan J, Marquering HA (2014) Automatic segmentation of the aortic root in CT angiography of candidate patients for transcatheter aortic valve implantation. Med Biol Eng Comput 52(7):611–618. https://doi.org/10.1007/s11517-014-1165-7
Elattar M, Wiegerinck E, van Kesteren F, Dubois L, Planken N, Vanbavel E, Baan J, Marquering H (2016) Automatic aortic root landmark detection in CTA images for preprocedural planning of transcatheter aortic valve implantation. Int J Cardiovasc Imaging 32(3):501–511
Jeganathan J, Knio Z, Amador Y, Hai T, Khamooshian A, Matyal R, Khabbaz KR, Mahmood F (2017) Artificial intelligence in mitral valve analysis. Ann Cardiac Anaesth 20(2):129–134
Liang L, Kong F, Martin C, Pham T, Wang Q, Duncan J, Sun W (2017) Machine learning-based 3-D geometry reconstruction and modeling of aortic valve deformation using 3-D computed tomography images. Int J Numer Method Biomed Eng. https://doi.org/10.1002/cnm.2827
Al WA, Jung HY, Yun ID, Jang Y, Park H, Chang H (2018) Automatic aortic valve landmark localization in coronary CT angiography using colonial walk. PLoS ONE 13(7):e0200317. https://doi.org/10.1371/journal.pone.0200317
Noothout JM, de Vos BD, Wolterink JM, Leiner T, Išgum I (2018) CNN-based landmark detection in cardiac CTA Scans. arXiv Preprint arXiv:1804.04963
Zheng Y, Liu D, Georgescu B, Nguyen H, Comaniciu D (2015) 3D deep learning for efficient and robust landmark detection in volumetric data. In: International conference on medical image computing and computer-assisted intervention, 2015, pp 565–572
Binder RK, Webb JG, Willson AB, Urena M, Hansson NC, Norgaard BL, Pibarot P, Barbanti M, Larose E, Freeman M, Dumont E, Thompson C, Wheeler M, Moss RR, Yang T, Pasian S, Hague CJ, Nguyen G, Raju R, Toggweiler S, Min JK, Wood DA, Rodés-Cabau J, Leipsic J (2013) The Impact of integration of a multidetector computed tomography annulus area sizing algorithm on outcomes of transcatheter aortic valve replacement: a prospective, multicenter, controlled trial. J Am Coll Cardiol 62(5):431–438
Spaziano M, Thériault-Lauzier P, Meti N, Vaquerizo B, Blanke P, Deli-Hussein J, Chetrit M, Galatas C, Buithieu J, Lange R, Martucci G, Leipsic J, Piazza N (2016) Optimal fluoroscopic viewing angles of left-sided heart structures in patients with aortic stenosis and mitral regurgitation based on multislice computed tomography. J Cardiovasc Comput Tomogr 10(2):162–172
Hesamian MH, Jia W, He X, Kennedy P (2019) Deep learning techniques for medical image segmentation: achievements and challenges. J Digit Imag 32(4):582–596. https://doi.org/10.1007/s10278-019-00227-x
Astudillo P, Mortier P, Bosmans J, De Backer O, de Jaegere P, De Beule M, Dambre J (2019) Enabling automated device size selection for transcatheter aortic valve implantation. J Interv Cardiol 2019:3591314. https://doi.org/10.1155/2019/3591314
Funding
This study received no external funding.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Pascal Theriault-Lauzier is a consultant for Circle CVI and receives royalties from sales of their software. Nicolo Piazza is a consultant and proctor for Medtronic and receives royalties from sales of Circle CVI software. Giuseppe Martucci is a proctor for Medtronic. All other authors have no conflict of interest to declare.
Ethical approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Declaration of Helsinki and its later amendments or comparable ethical standards.
Informed consent
Informed consent was obtained from all individual participants included in the study.
Human and animal rights
This article does not contain any studies involving animals performed by any of the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
P. Theriault-Lauzier formally at the Division of Cardiology, McGill University, Montreal, QC, Canada.
Rights and permissions
About this article
Cite this article
Theriault-Lauzier, P., Alsosaimi, H., Mousavi, N. et al. Recursive multiresolution convolutional neural networks for 3D aortic valve annulus planimetry. Int J CARS 15, 577–588 (2020). https://doi.org/10.1007/s11548-020-02131-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-020-02131-0