CINENet: deep learning-based 3D cardiac CINE MRI reconstruction with multi-coil complex-valued 4D spatio-temporal convolutions.

Autor: Küstner T; School of Biomedical Engineering and Imaging Sciences, King's College London, St. Thomas' Hospital, Lambeth Wing, London, UK. thomas.kuestner@kcl.ac.uk., Fuin N; School of Biomedical Engineering and Imaging Sciences, King's College London, St. Thomas' Hospital, Lambeth Wing, London, UK., Hammernik K; Department of Computing, Imperial College London, London, UK., Bustin A; School of Biomedical Engineering and Imaging Sciences, King's College London, St. Thomas' Hospital, Lambeth Wing, London, UK., Qi H; School of Biomedical Engineering and Imaging Sciences, King's College London, St. Thomas' Hospital, Lambeth Wing, London, UK., Hajhosseiny R; School of Biomedical Engineering and Imaging Sciences, King's College London, St. Thomas' Hospital, Lambeth Wing, London, UK., Masci PG; School of Biomedical Engineering and Imaging Sciences, King's College London, St. Thomas' Hospital, Lambeth Wing, London, UK., Neji R; School of Biomedical Engineering and Imaging Sciences, King's College London, St. Thomas' Hospital, Lambeth Wing, London, UK.; MR Research Collaborations, Siemens Healthcare Limited, Frimley, UK., Rueckert D; Department of Computing, Imperial College London, London, UK., Botnar RM; School of Biomedical Engineering and Imaging Sciences, King's College London, St. Thomas' Hospital, Lambeth Wing, London, UK.; Escuela de Ingeniería, Pontificia Universidad Católica de Chile, Santiago, Chile., Prieto C; School of Biomedical Engineering and Imaging Sciences, King's College London, St. Thomas' Hospital, Lambeth Wing, London, UK.; Escuela de Ingeniería, Pontificia Universidad Católica de Chile, Santiago, Chile.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2020 Aug 13; Vol. 10 (1), pp. 13710. Date of Electronic Publication: 2020 Aug 13.
DOI: 10.1038/s41598-020-70551-8
Abstrakt: 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: MEDLINE
Externí odkaz: