Abstract
Tracking the tricuspid valve (TV) in magnetic resonance imaging (MRI) long-axis cine images has the potential to aid in the evaluation of right ventricular dysfunction, which is common in congenital heart disease and pulmonary hypertension. However, this annotation task remains difficult and time-demanding as the TV moves rapidly and is barely distinguishable from the myocardium. This study presents TVnet, a novel dual-stage deep learning pipeline based on ResNet-50 and automated image linear transformation, able to automatically derive tricuspid annular plane systolic excursion. Stage 1 uses a trained network for a coarse detection of the TV points, which are used by stage 2 to reorient the cine into a standardized size, cropping, resolution, and heart orientation and to accurately locate the TV points with another trained network. The model was trained and evaluated on 4170 images from 140 patients with diverse cardiovascular pathologies. A baseline model without standardization achieved a Euclidean distance error of 4.0 ± 3.1 mm and a clinical-metric agreement of ICC = 0.87, whereas a standardized model improved the agreement to 2.4 ± 1.7 mm and an ICC = 0.94, on par with an evaluated inter-observer variability of 2.9 ± 2.9 mm and an ICC = 0.92, respectively. This novel dual-stage deep learning pipeline substantially improved the annotation accuracy compared to a baseline model, paving the way towards reliable right ventricular dysfunction assessment with MRI.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Change history
21 September 2021
In a former version of this paper, Reference 12 referred to issue 1 rather than to issue 63, which led to an error in the CrossRef link. This has been corrected.
References
Dimopoulos, K., et al.: Echocardiographic screening for pulmonary hypertension in congenital heart disease: JACC review topic of the week. J. Am. Coll. Cardiol. 72(22), 2778–2788 (2018)
Amsallem, M., Mercier, O., Kobayashi, Y., Moneghetti, K., Haddad, F.: Forgotten no more: a focused update on the right ventricle in cardiovascular disease. JACC: Heart Failure 6(11), 891–903 (2018)
D’Andrea, A., et al.: The impact of age and gender on right ventricular diastolic function among healthy adults. J. Cardiol. 70(4), 387–395 (2017)
Ho, C.Y., Solomon, S.D.: A clinician’s guide to tissue doppler imaging. Circulation 113(10), e396–e398 (2006)
Abraham, T.P., Dimaano, V.L., Liang, H.Y.: Role of tissue doppler and strain echocardiography in current clinical practice. Circulation 116(22), 2597–2609 (2007)
Valsangiacomo Buechel, E.R., Mertens, L.L.: Imaging the right heart: the use of integrated multimodality imaging. Eur. Heart J. 33(8), 949–960 (2012)
Carlsson, M., Ugander, M., Mosén, H., Buhre, T., Arheden, H.: Atrioventricular plane displacement is the major contributor to left ventricular pumping in healthy adults, athletes, and patients with dilated cardiomyopathy. Am. J. Physiol. Heart Circulatory Physiol. 292(3), H1452–H1459 (2007)
Seemann, F., et al.: Valvular imaging in the era of feature-tracking: a slice-following cardiac MR sequence to measure mitral flow. J. Magn. Reson. Imag. 51(5), 1412–1421 (2020)
Caudron, J., Fares, J., Vivier, P.H., Lefebvre, V., Petitjean, C., Dacher, J.N.: Diagnostic accuracy and variability of three semi-quantitative methods for assessing right ventricular systolic function from cardiac MRI in patients with acquired heart disease. Eur. Radiol. 21(10), 2111–2120 (2011)
Leng, S., et al.: Three-dimensional tricuspid annular motion analysis from cardiac magnetic resonance feature-tracking. Ann. Biomed. Eng. 44(12), 3522–3538 (2016)
Seemann, F., et al.: Time-resolved tracking of the atrioventricular plane displacement in cardiovascular magnetic resonance (CMR) images. BMC Med. Imag. 17(1), 19 (2017)
Hu, C., et al.: T1-refBlochi: high resolution 3D post-contrast T1 myocardial mapping based on a single 3D late gadolinium enhancement volume, Bloch equations, and a reference T1. J. Cardiovascular Magn. Reson. 19, 63 (2017)
Seemann, F., et al.: Assessment of diastolic function and atrial remodeling by MRI-validation and correlation with echocardiography and filling pressure. Physiol. Rep. 6(17), e13828 (2018)
Gonzales, R.A., et al.: Automated left atrial time-resolved segmentation in MRI long-axis cine images using active contours. BMC Med. Imag. 21(1), 1–12 (2021)
Heiberg, E., Sjögren, J., Ugander, M., Carlsson, M., Engblom, H., Arheden, H.: Design and validation of segment-freely available software for cardiovascular image analysis. BMC Med. Imag. 10(1), 1 (2010)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Kingma, D.P., Ba, J.L.: Adam: a method for stochastic gradient descent. In: ICLR: International Conference on Learning Representations (2015)
Acknowledgement
The authors gratefully acknowledge funding from NHLBI R01HL144706, RAG acknowledges Magnus Caspersen, MSc for his guidance in deep learning, and DCP acknowledges James W. Goldfarb, PhD for his ideas on the utilization of deep learning for cine valve-tracking, many years ago.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Supplementary material 1 (mp4 7559 KB)
Supplementary material 2 (mp4 6613 KB)
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Gonzales, R.A., Lamy, J., Seemann, F., Heiberg, E., Onofrey, J.A., Peters, D.C. (2021). TVnet: Automated Time-Resolved Tracking of the Tricuspid Valve Plane in MRI Long-Axis Cine Images with a Dual-Stage Deep Learning Pipeline. In: de Bruijne, M., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science(), vol 12906. Springer, Cham. https://doi.org/10.1007/978-3-030-87231-1_55
Download citation
DOI: https://doi.org/10.1007/978-3-030-87231-1_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87230-4
Online ISBN: 978-3-030-87231-1
eBook Packages: Computer ScienceComputer Science (R0)
