1
|
Morales MA, Ghanbari F, Nakamori S, Assana S, Amyar A, Yoon S, Rodriguez J, Maron MS, Rowin EJ, Kim J, Judd RM, Weinsaft JW, Nezafat R. Deformation-encoding Deep Learning Transformer for High-Frame-Rate Cardiac Cine MRI. Radiol Cardiothorac Imaging 2024; 6:e230177. [PMID: 38722232 PMCID: PMC11211941 DOI: 10.1148/ryct.230177] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2023] [Revised: 02/15/2024] [Accepted: 03/21/2024] [Indexed: 06/07/2024]
Abstract
Purpose To develop a deep learning model for increasing cardiac cine frame rate while maintaining spatial resolution and scan time. Materials and Methods A transformer-based model was trained and tested on a retrospective sample of cine images from 5840 patients (mean age, 55 years ± 19 [SD]; 3527 male patients) referred for clinical cardiac MRI from 2003 to 2021 at nine centers; images were acquired using 1.5- and 3-T scanners from three vendors. Data from three centers were used for training and testing (4:1 ratio). The remaining data were used for external testing. Cines with downsampled frame rates were restored using linear, bicubic, and model-based interpolation. The root mean square error between interpolated and original cine images was modeled using ordinary least squares regression. In a prospective study of 49 participants referred for clinical cardiac MRI (mean age, 56 years ± 13; 25 male participants) and 12 healthy participants (mean age, 51 years ± 16; eight male participants), the model was applied to cines acquired at 25 frames per second (fps), thereby doubling the frame rate, and these interpolated cines were compared with actual 50-fps cines. The preference of two readers based on perceived temporal smoothness and image quality was evaluated using a noninferiority margin of 10%. Results The model generated artifact-free interpolated images. Ordinary least squares regression analysis accounting for vendor and field strength showed lower error (P < .001) with model-based interpolation compared with linear and bicubic interpolation in internal and external test sets. The highest proportion of reader choices was "no preference" (84 of 122) between actual and interpolated 50-fps cines. The 90% CI for the difference between reader proportions favoring collected (15 of 122) and interpolated (23 of 122) high-frame-rate cines was -0.01 to 0.14, indicating noninferiority. Conclusion A transformer-based deep learning model increased cardiac cine frame rates while preserving both spatial resolution and scan time, resulting in images with quality comparable to that of images obtained at actual high frame rates. Keywords: Functional MRI, Heart, Cardiac, Deep Learning, High Frame Rate Supplemental material is available for this article. © RSNA, 2024.
Collapse
Affiliation(s)
- Manuel A. Morales
- From the Cardiovascular Medicine Division, Department of Medicine,
Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline
Ave, Boston, MA 02215 (M.A.M., F.G., S.N., S.A., A.A., S.Y., J.R., R.N.);
Division of Cardiology, Department of Medicine, Tufts Medical Center, Boston,
Mass (M.S.M., E.J.R.); Division of Cardiology, Weill Cornell Medicine, New York,
NY (J.K., J.W.W.); and Division of Cardiology, Department of Medicine, Duke
University School of Medicine, Durham, NC (R.M.J.)
| | - Fahime Ghanbari
- From the Cardiovascular Medicine Division, Department of Medicine,
Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline
Ave, Boston, MA 02215 (M.A.M., F.G., S.N., S.A., A.A., S.Y., J.R., R.N.);
Division of Cardiology, Department of Medicine, Tufts Medical Center, Boston,
Mass (M.S.M., E.J.R.); Division of Cardiology, Weill Cornell Medicine, New York,
NY (J.K., J.W.W.); and Division of Cardiology, Department of Medicine, Duke
University School of Medicine, Durham, NC (R.M.J.)
| | - Shiro Nakamori
- From the Cardiovascular Medicine Division, Department of Medicine,
Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline
Ave, Boston, MA 02215 (M.A.M., F.G., S.N., S.A., A.A., S.Y., J.R., R.N.);
Division of Cardiology, Department of Medicine, Tufts Medical Center, Boston,
Mass (M.S.M., E.J.R.); Division of Cardiology, Weill Cornell Medicine, New York,
NY (J.K., J.W.W.); and Division of Cardiology, Department of Medicine, Duke
University School of Medicine, Durham, NC (R.M.J.)
| | - Salah Assana
- From the Cardiovascular Medicine Division, Department of Medicine,
Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline
Ave, Boston, MA 02215 (M.A.M., F.G., S.N., S.A., A.A., S.Y., J.R., R.N.);
Division of Cardiology, Department of Medicine, Tufts Medical Center, Boston,
Mass (M.S.M., E.J.R.); Division of Cardiology, Weill Cornell Medicine, New York,
NY (J.K., J.W.W.); and Division of Cardiology, Department of Medicine, Duke
University School of Medicine, Durham, NC (R.M.J.)
| | - Amine Amyar
- From the Cardiovascular Medicine Division, Department of Medicine,
Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline
Ave, Boston, MA 02215 (M.A.M., F.G., S.N., S.A., A.A., S.Y., J.R., R.N.);
Division of Cardiology, Department of Medicine, Tufts Medical Center, Boston,
Mass (M.S.M., E.J.R.); Division of Cardiology, Weill Cornell Medicine, New York,
NY (J.K., J.W.W.); and Division of Cardiology, Department of Medicine, Duke
University School of Medicine, Durham, NC (R.M.J.)
| | - Siyeop Yoon
- From the Cardiovascular Medicine Division, Department of Medicine,
Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline
Ave, Boston, MA 02215 (M.A.M., F.G., S.N., S.A., A.A., S.Y., J.R., R.N.);
Division of Cardiology, Department of Medicine, Tufts Medical Center, Boston,
Mass (M.S.M., E.J.R.); Division of Cardiology, Weill Cornell Medicine, New York,
NY (J.K., J.W.W.); and Division of Cardiology, Department of Medicine, Duke
University School of Medicine, Durham, NC (R.M.J.)
| | - Jennifer Rodriguez
- From the Cardiovascular Medicine Division, Department of Medicine,
Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline
Ave, Boston, MA 02215 (M.A.M., F.G., S.N., S.A., A.A., S.Y., J.R., R.N.);
Division of Cardiology, Department of Medicine, Tufts Medical Center, Boston,
Mass (M.S.M., E.J.R.); Division of Cardiology, Weill Cornell Medicine, New York,
NY (J.K., J.W.W.); and Division of Cardiology, Department of Medicine, Duke
University School of Medicine, Durham, NC (R.M.J.)
| | - Martin S. Maron
- From the Cardiovascular Medicine Division, Department of Medicine,
Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline
Ave, Boston, MA 02215 (M.A.M., F.G., S.N., S.A., A.A., S.Y., J.R., R.N.);
Division of Cardiology, Department of Medicine, Tufts Medical Center, Boston,
Mass (M.S.M., E.J.R.); Division of Cardiology, Weill Cornell Medicine, New York,
NY (J.K., J.W.W.); and Division of Cardiology, Department of Medicine, Duke
University School of Medicine, Durham, NC (R.M.J.)
| | - Ethan J. Rowin
- From the Cardiovascular Medicine Division, Department of Medicine,
Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline
Ave, Boston, MA 02215 (M.A.M., F.G., S.N., S.A., A.A., S.Y., J.R., R.N.);
Division of Cardiology, Department of Medicine, Tufts Medical Center, Boston,
Mass (M.S.M., E.J.R.); Division of Cardiology, Weill Cornell Medicine, New York,
NY (J.K., J.W.W.); and Division of Cardiology, Department of Medicine, Duke
University School of Medicine, Durham, NC (R.M.J.)
| | - Jiwon Kim
- From the Cardiovascular Medicine Division, Department of Medicine,
Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline
Ave, Boston, MA 02215 (M.A.M., F.G., S.N., S.A., A.A., S.Y., J.R., R.N.);
Division of Cardiology, Department of Medicine, Tufts Medical Center, Boston,
Mass (M.S.M., E.J.R.); Division of Cardiology, Weill Cornell Medicine, New York,
NY (J.K., J.W.W.); and Division of Cardiology, Department of Medicine, Duke
University School of Medicine, Durham, NC (R.M.J.)
| | - Robert M. Judd
- From the Cardiovascular Medicine Division, Department of Medicine,
Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline
Ave, Boston, MA 02215 (M.A.M., F.G., S.N., S.A., A.A., S.Y., J.R., R.N.);
Division of Cardiology, Department of Medicine, Tufts Medical Center, Boston,
Mass (M.S.M., E.J.R.); Division of Cardiology, Weill Cornell Medicine, New York,
NY (J.K., J.W.W.); and Division of Cardiology, Department of Medicine, Duke
University School of Medicine, Durham, NC (R.M.J.)
| | - Jonathan W. Weinsaft
- From the Cardiovascular Medicine Division, Department of Medicine,
Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline
Ave, Boston, MA 02215 (M.A.M., F.G., S.N., S.A., A.A., S.Y., J.R., R.N.);
Division of Cardiology, Department of Medicine, Tufts Medical Center, Boston,
Mass (M.S.M., E.J.R.); Division of Cardiology, Weill Cornell Medicine, New York,
NY (J.K., J.W.W.); and Division of Cardiology, Department of Medicine, Duke
University School of Medicine, Durham, NC (R.M.J.)
| | - Reza Nezafat
- From the Cardiovascular Medicine Division, Department of Medicine,
Beth Israel Deaconess Medical Center and Harvard Medical School, 330 Brookline
Ave, Boston, MA 02215 (M.A.M., F.G., S.N., S.A., A.A., S.Y., J.R., R.N.);
Division of Cardiology, Department of Medicine, Tufts Medical Center, Boston,
Mass (M.S.M., E.J.R.); Division of Cardiology, Weill Cornell Medicine, New York,
NY (J.K., J.W.W.); and Division of Cardiology, Department of Medicine, Duke
University School of Medicine, Durham, NC (R.M.J.)
| |
Collapse
|
7
|
Demirel ÖB, Zhang C, Yaman B, Gulle M, Shenoy C, Leiner T, Kellman P, Akçakaya M. High-fidelity Database-free Deep Learning Reconstruction for Real-time Cine Cardiac MRI. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.02.13.528388. [PMID: 36824797 PMCID: PMC9948950 DOI: 10.1101/2023.02.13.528388] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 06/18/2023]
Abstract
Real-time cine cardiac MRI provides an ECG-free free-breathing alternative to clinical gold-standard ECG-gated breath-hold segmented cine MRI for evaluation of heart function. Real-time cine MRI data acquisition during free breathing snapshot imaging enables imaging of patient cohorts that cannot be imaged with segmented or breath-hold acquisitions, but requires rapid imaging to achieve sufficient spatial-temporal resolutions. However, at high acceleration rates, conventional reconstruction techniques suffer from residual aliasing and temporal blurring, including advanced methods such as compressed sensing with radial trajectories. Recently, deep learning (DL) reconstruction has emerged as a powerful tool in MRI. However, its utility for free-breathing real-time cine MRI has been limited, as database-learning of spatio-temporal correlations with varying breathing and cardiac motion patterns across subjects has been challenging. Zero-shot self-supervised physics-guided deep learning (PG-DL) reconstruction has been proposed to overcome such challenges of database training by enabling subject-specific training. In this work, we adapt zero-shot PG-DL for real-time cine MRI with a spatio-temporal regularization. We compare our method to TGRAPPA, locally low-rank (LLR) regularized reconstruction and database-trained PG-DL reconstruction, both for retrospectively and prospectively accelerated datasets. Results on highly accelerated real-time Cartesian cine MRI show that the proposed method outperforms other reconstruction methods, both visibly in terms of noise and aliasing, and quantitatively.
Collapse
Affiliation(s)
- Ömer Burak Demirel
- Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, USA
| | - Chi Zhang
- Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, USA
| | - Burhaneddin Yaman
- Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, USA
| | - Merve Gulle
- Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, USA
| | - Chetan Shenoy
- Department of Medicine (Cardiology), University of Minnesota, Minneapolis, MN, USA
| | - Tim Leiner
- Department of Radiology, Mayo Clinic, Rochester, MN, USA
| | - Peter Kellman
- National Heart-Lung and Blood Institute, Bethesda, MD, USA
| | - Mehmet Akçakaya
- Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, USA
| |
Collapse
|