Highly Accelerated Free-breathing Real-time Phase Contrast Cardiovascular MRI Via Complex-difference Deep Learning

Overview

Journal Magn Reson Med

Publisher Wiley

Specialty Radiology

Date 2021 Mar 15

PMID 33720465

Citations 7

Authors

Hassan Haji-Valizadeh

Rui Guo

Selcuk Kucukseymen

Amanda Paskavitz

Xiaoying Cai

Jennifer Rodriguez

Patrick Pierce

Beth Goddu

Daniel Kim

Warren Manning

Reza Nezafat

Affiliations

Soon will be listed here.

Abstract

Purpose: To develop and evaluate a real-time phase contrast (PC) MRI protocol via complex-difference deep learning (DL) framework.

Methods: DL used two 3D U-nets to separately filter aliasing artifact from radial real-time velocity-compensated and complex-difference images. U-nets were trained with synthetic real-time PC generated from electrocardiograph (ECG) -gated, breath-hold, segmented PC (ECG-gated segmented PC) acquired at the ascending aorta of 510 patients. In 21 patients, free-breathing, ungated real-time (acceleration rate = 28.8) and ECG-gated segmented (acceleration rate = 2) PC were prospectively acquired at the ascending aorta. Hemodynamic parameters (cardiac output [CO], stroke volume [SV], and mean velocity at peak systole [peak mean velocity]) were measured for ECG-gated segmented and DL-filtered synthetic real-time PC and compared using Bland-Altman and linear regression analyses. Additionally, hemodynamic parameters were quantified from DL-filtered, compressed-sensing (CS) -reconstructed, and gridding reconstructed prospective real-time PC and compared to ECG-gated segmented PC.

Results: Synthetic real-time PC with DL showed strong correlation (R > 0.98) and good agreement with ECG-gated segmented PC for quantified hemodynamic parameters (mean-difference: CO = -0.3 L/min, SV = -4.3 mL, peak mean velocity = -2.3 cm/s). On average, DL required 0.39 s/frame to filter prospective real-time PC, which was 4.6-fold faster than CS. Compared to CS, DL showed superior correlation, tighter limits of agreement (LOAs), better bias for peak mean velocity, and worse bias for CO and SV. Compared to gridding, DL showed similar correlation, tighter LOAs for CO and SV, similar bias for CO, and worse bias for SV and peak mean velocity.

Conclusion: The complex-difference DL framework accelerated real-time PC-MRI by nearly 28-fold, enabling rapid free-running real-time assessment of flow hemodynamics.

Citing Articles

Accelerated phase-contrast magnetic resonance imaging with use of resolution enhancement generative adversarial neural network.

Morales M, Ghanbari F, Demirel O, Street J, Wallace T, Davids R J Cardiovasc Magn Reson. 2024; 27(1):101128.

PMID: 39615655 PMC: 11758573. DOI: 10.1016/j.jocmr.2024.101128.

The future of CMR: All-in-one vs. real-time CMR (Part 2).

Contijoch F, Rasche V, Seiberlich N, Peters D J Cardiovasc Magn Reson. 2024; 26(1):100998.

PMID: 38237901 PMC: 11211235. DOI: 10.1016/j.jocmr.2024.100998.

Present and Future Innovations in AI and Cardiac MRI.

Morales M, Manning W, Nezafat R Radiology. 2024; 310(1):e231269.

PMID: 38193835 PMC: 10831479. DOI: 10.1148/radiol.231269.

GRASP reconstruction amplified with view-sharing and KWIC filtering reduces underestimation of peak velocity in highly-accelerated real-time phase-contrast MRI: A preliminary evaluation in pediatric patients with congenital heart disease.

Yang H, Hong K, Baraboo J, Fan L, Larsen A, Markl M Magn Reson Med. 2023; 91(5):1965-1977.

PMID: 38084397 PMC: 10950531. DOI: 10.1002/mrm.29974.

Highly accelerated free-breathing real-time 2D flow imaging using compressed sensing and shared velocity encoding.

Xiong F, Emrich T, Schoepf U, Jin N, Hall S, Ruddy J Eur Radiol. 2023; 34(3):1692-1703.

PMID: 37658887 DOI: 10.1007/s00330-023-10157-6.

References

Winkelmann S, Schaeffter T, Koehler T, Eggers H, Doessel O . An optimal radial profile order based on the Golden Ratio for time-resolved MRI. IEEE Trans Med Imaging. 2007; 26(1):68-76. DOI: 10.1109/TMI.2006.885337. View

Tan Z, Roeloffs V, Voit D, Joseph A, Untenberger M, Merboldt K . Model-based reconstruction for real-time phase-contrast flow MRI: Improved spatiotemporal accuracy. Magn Reson Med. 2016; 77(3):1082-1093. DOI: 10.1002/mrm.26192. View

El-Rewaidy H, Neisius U, Mancio J, Kucukseymen S, Rodriguez J, Paskavitz A . Deep complex convolutional network for fast reconstruction of 3D late gadolinium enhancement cardiac MRI. NMR Biomed. 2020; 33(7):e4312. DOI: 10.1002/nbm.4312. View

Walsh D, Gmitro A, Marcellin M . Adaptive reconstruction of phased array MR imagery. Magn Reson Med. 2000; 43(5):682-90. DOI: 10.1002/(sici)1522-2594(200005)43:5<682::aid-mrm10>3.0.co;2-g. View

Lin H, Bender J, Ding Y, Chung Y, Hinton A, Pennell M . Shared velocity encoding: a method to improve the temporal resolution of phase-contrast velocity measurements. Magn Reson Med. 2011; 68(3):703-10. PMC: 3339280. DOI: 10.1002/mrm.23273. View

Smith D, Sengupta S, Smith S, Welch E . Trajectory optimized NUFFT: Faster non-Cartesian MRI reconstruction through prior knowledge and parallel architectures. Magn Reson Med. 2018; 81(3):2064-2071. PMC: 6347498. DOI: 10.1002/mrm.27497. View

Fan L, Shen D, Haji-Valizadeh H, Naresh N, Carr J, Freed B . Rapid dealiasing of undersampled, non-Cartesian cardiac perfusion images using U-net. NMR Biomed. 2020; 33(5):e4239. PMC: 7165063. DOI: 10.1002/nbm.4239. View

Haji-Valizadeh H, Shen D, Avery R, Serhal A, Schiffers F, Katsaggelos A . Rapid Reconstruction of Four-dimensional MR Angiography of the Thoracic Aorta Using a Convolutional Neural Network. Radiol Cardiothorac Imaging. 2020; 2(3):e190205. PMC: 7325698. DOI: 10.1148/ryct.2020190205. View

Benkert T, Tian Y, Huang C, DiBella E, Chandarana H, Feng L . Optimization and validation of accelerated golden-angle radial sparse MRI reconstruction with self-calibrating GRAPPA operator gridding. Magn Reson Med. 2017; 80(1):286-293. PMC: 5876102. DOI: 10.1002/mrm.27030. View

10.

Schlemper J, Caballero J, Hajnal J, Price A, Rueckert D . A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction. IEEE Trans Med Imaging. 2017; 37(2):491-503. DOI: 10.1109/TMI.2017.2760978. View

11.

Nezafat R, Kellman P, Derbyshire J, McVeigh E . Real-time blood flow imaging using autocalibrated spiral sensitivity encoding. Magn Reson Med. 2005; 54(6):1557-61. PMC: 2396269. DOI: 10.1002/mrm.20690. View

12.

Shankaranarayanan A, Simonetti O, Laub G, Lewin J, Duerk J . Segmented k-space and real-time cardiac cine MR imaging with radial trajectories. Radiology. 2001; 221(3):827-36. DOI: 10.1148/radiol.2213010455. View

13.

Hauptmann A, Arridge S, Lucka F, Muthurangu V, Steeden J . Real-time cardiovascular MR with spatio-temporal artifact suppression using deep learning-proof of concept in congenital heart disease. Magn Reson Med. 2018; 81(2):1143-1156. PMC: 6492123. DOI: 10.1002/mrm.27480. View

14.

Bernstein M, Ikezaki Y . Comparison of phase-difference and complex-difference processing in phase-contrast MR angiography. J Magn Reson Imaging. 1991; 1(6):725-9. DOI: 10.1002/jmri.1880010620. View

15.

Griswold M, Jakob P, Heidemann R, Nittka M, Jellus V, Wang J . Generalized autocalibrating partially parallel acquisitions (GRAPPA). Magn Reson Med. 2002; 47(6):1202-10. DOI: 10.1002/mrm.10171. View

16.

Haji-Valizadeh H, Feng L, Ma L, Shen D, Block K, Robinson J . Highly accelerated, real-time phase-contrast MRI using radial k-space sampling and GROG-GRASP reconstruction: a feasibility study in pediatric patients with congenital heart disease. NMR Biomed. 2020; 33(5):e4240. PMC: 7165070. DOI: 10.1002/nbm.4240. View

17.

Lustig M, Donoho D, Pauly J . Sparse MRI: The application of compressed sensing for rapid MR imaging. Magn Reson Med. 2007; 58(6):1182-95. DOI: 10.1002/mrm.21391. View

18.

Stalder A, Russe M, Frydrychowicz A, Bock J, Hennig J, Markl M . Quantitative 2D and 3D phase contrast MRI: optimized analysis of blood flow and vessel wall parameters. Magn Reson Med. 2008; 60(5):1218-31. DOI: 10.1002/mrm.21778. View

19.

Matej S, Fessler J, Kazantsev I . Iterative tomographic image reconstruction using Fourier-based forward and back-projectors. IEEE Trans Med Imaging. 2004; 23(4):401-12. DOI: 10.1109/TMI.2004.824233. View

20.

Nayak K, Pauly J, KERR A, Hu B, Nishimura D . Real-time color flow MRI. Magn Reson Med. 2000; 43(2):251-8. DOI: 10.1002/(sici)1522-2594(200002)43:2<251::aid-mrm12>3.0.co;2-#. View