CINENet: deep learning-based 3D cardiac CINE MRI reconstruction with multi-coil complex-valued 4D spatio-temporal convolutions
| Autor: | René M. Botnar, Thomas Küstner, Reza Hajhosseiny, Kerstin Hammernik, Daniel Rueckert, Haikun Qi, Radhouene Neji, Pier Giorgio Masci, Claudia Prieto, Niccolo Fuin, Aurelien Bustin |
|---|---|
| Přispěvatelé: | Engineering & Physical Science Research Council (EPSRC) |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
0301 basic medicine
Male Computer science Image quality lcsh:Medicine Breath Holding 0302 clinical medicine Multi coil Computational models Computer vision Prospective Studies lcsh:Science Multidisciplinary Ejection fraction medicine.diagnostic_test Computational science Healthy subjects Complex valued Middle Aged Cine mri Cine imaging Cardiovascular Diseases Three-dimensional imaging Female Biomedical engineering Adult Cardiology Magnetic Resonance Imaging Cine Article 03 medical and health sciences Magnetic resonance imaging Deep Learning Imaging Three-Dimensional Spatio-Temporal Analysis Image processing Machine learning Image Interpretation Computer-Assisted medicine Humans business.industry Deep learning lcsh:R Data acquisition 030104 developmental biology Case-Control Studies lcsh:Q Artificial intelligence business 030217 neurology & neurosurgery |
| Zdroj: | Scientific Reports, Vol 10, Iss 1, Pp 1-13 (2020) Scientific Reports |
| ISSN: | 2045-2322 |
| DOI: | 10.1038/s41598-020-70551-8 |
| Popis: | Cardiac CINE magnetic resonance imaging is the gold-standard for the assessment of cardiac function. Imaging accelerations have shown to enable 3D CINE with left ventricular (LV) coverage in a single breath-hold. However, 3D imaging remains limited to anisotropic resolution and long reconstruction times. Recently deep learning has shown promising results for computationally efficient reconstructions of highly accelerated 2D CINE imaging. In this work, we propose a novel 4D (3D + time) deep learning-based reconstruction network, termed 4D CINENet, for prospectively undersampled 3D Cartesian CINE imaging. CINENet is based on (3 + 1)D complex-valued spatio-temporal convolutions and multi-coil data processing. We trained and evaluated the proposed CINENet on in-house acquired 3D CINE data of 20 healthy subjects and 15 patients with suspected cardiovascular disease. The proposed CINENet network outperforms iterative reconstructions in visual image quality and contrast (+ 67% improvement). We found good agreement in LV function (bias ± 95% confidence) in terms of end-systolic volume (0 ± 3.3 ml), end-diastolic volume (− 0.4 ± 2.0 ml) and ejection fraction (0.1 ± 3.2%) compared to clinical gold-standard 2D CINE, enabling single breath-hold isotropic 3D CINE in less than 10 s scan and ~ 5 s reconstruction time. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|