» Articles » PMID: 34857009

MVnet: Automated Time-resolved Tracking of the Mitral Valve Plane in CMR Long-axis Cine Images with Residual Neural Networks: a Multi-center, Multi-vendor Study

Abstract

Background: Mitral annular plane systolic excursion (MAPSE) and left ventricular (LV) early diastolic velocity (e') are key metrics of systolic and diastolic function, but not often measured by cardiovascular magnetic resonance (CMR). Its derivation is possible with manual, precise annotation of the mitral valve (MV) insertion points along the cardiac cycle in both two and four-chamber long-axis cines, but this process is highly time-consuming, laborious, and prone to errors. A fully automated, consistent, fast, and accurate method for MV plane tracking is lacking. In this study, we propose MVnet, a deep learning approach for MV point localization and tracking capable of deriving such clinical metrics comparable to human expert-level performance, and validated it in a multi-vendor, multi-center clinical population.

Methods: The proposed pipeline first performs a coarse MV point annotation in a given cine accurately enough to apply an automated linear transformation task, which standardizes the size, cropping, resolution, and heart orientation, and second, tracks the MV points with high accuracy. The model was trained and evaluated on 38,854 cine images from 703 patients with diverse cardiovascular conditions, scanned on equipment from 3 main vendors, 16 centers, and 7 countries, and manually annotated by 10 observers. Agreement was assessed by the intra-class correlation coefficient (ICC) for both clinical metrics and by the distance error in the MV plane displacement. For inter-observer variability analysis, an additional pair of observers performed manual annotations in a randomly chosen set of 50 patients.

Results: MVnet achieved a fast segmentation (<1 s/cine) with excellent ICCs of 0.94 (MAPSE) and 0.93 (LV e') and a MV plane tracking error of -0.10 ± 0.97 mm. In a similar manner, the inter-observer variability analysis yielded ICCs of 0.95 and 0.89 and a tracking error of -0.15 ± 1.18 mm, respectively.

Conclusion: A dual-stage deep learning approach for automated annotation of MV points for systolic and diastolic evaluation in CMR long-axis cine images was developed. The method is able to carefully track these points with high accuracy and in a timely manner. This will improve the feasibility of CMR methods which rely on valve tracking and increase their utility in a clinical setting.

Citing Articles

Diastolic dysfunction evaluation by cardiovascular magnetic resonance derived E, a, e': Comparison to echocardiography.

Lamy J, Xiang J, Shah N, Kwan J, Kim Y, Upadhyaya K Physiol Rep. 2024; 12(23):e70078.

PMID: 39604208 PMC: 11602526. DOI: 10.14814/phy2.70078.


Improved Robustness for Deep Learning-based Segmentation of Multi-Center Myocardial Perfusion MRI Datasets Using Data Adaptive Uncertainty-guided Space-time Analysis.

Yalcinkaya D, Youssef K, Heydari B, Wei J, Merz N, Judd R ArXiv. 2024; .

PMID: 39148930 PMC: 11326424.


Improved robustness for deep learning-based segmentation of multi-center myocardial perfusion cardiovascular MRI datasets using data-adaptive uncertainty-guided space-time analysis.

Yalcinkaya D, Youssef K, Heydari B, Wei J, Merz C, Judd R J Cardiovasc Magn Reson. 2024; 26(2):101082.

PMID: 39142567 PMC: 11663771. DOI: 10.1016/j.jocmr.2024.101082.


Tricuspid valve flow measurement using a deep learning framework for automated valve-tracking 2D phase contrast.

Lamy J, Gonzales R, Xiang J, Seemann F, Huber S, Steele J Magn Reson Med. 2024; 92(5):1838-1850.

PMID: 38817154 PMC: 11341256. DOI: 10.1002/mrm.30163.


K-t PCA accelerated in-plane balanced steady-state free precession phase-contrast (PC-SSFP) for all-in-one diastolic function evaluation.

Xiang J, Lamy J, Qiu M, Galiana G, Peters D Magn Reson Med. 2023; 91(3):911-925.

PMID: 37927206 PMC: 10803002. DOI: 10.1002/mrm.29897.

References
1.
Wu V, Chyou J, Chung S, Bhagavatula S, Axel L . Evaluation of diastolic function by three-dimensional volume tracking of the mitral annulus with cardiovascular magnetic resonance: comparison with tissue Doppler imaging. J Cardiovasc Magn Reson. 2014; 16:71. PMC: 4169226. DOI: 10.1186/s12968-014-0071-3. View

2.
Gyllenhammar T, Kanski M, Engblom H, Wuttge D, Carlsson M, Hesselstrand R . Decreased global myocardial perfusion at adenosine stress as a potential new biomarker for microvascular disease in systemic sclerosis: a magnetic resonance study. BMC Cardiovasc Disord. 2018; 18(1):16. PMC: 5791343. DOI: 10.1186/s12872-018-0756-x. View

3.
Seemann F, Heiberg E, Carlsson M, Gonzales R, Baldassarre L, Qiu M . Valvular imaging in the era of feature-tracking: A slice-following cardiac MR sequence to measure mitral flow. J Magn Reson Imaging. 2019; 51(5):1412-1421. PMC: 7217167. DOI: 10.1002/jmri.26971. View

4.
Heiberg E, Sjogren J, Ugander M, Carlsson M, Engblom H, Arheden H . Design and validation of Segment--freely available software for cardiovascular image analysis. BMC Med Imaging. 2010; 10:1. PMC: 2822815. DOI: 10.1186/1471-2342-10-1. View

5.
Jahnke C, Paetsch I, Nehrke K, Schnackenburg B, Bornstedt A, Gebker R . A new approach for rapid assessment of the cardiac rest period for coronary MRA. J Cardiovasc Magn Reson. 2005; 7(2):395-9. DOI: 10.1081/jcmr-200053616. View