End-to-end deep learning nonrigid motion-corrected reconstruction for highly accelerated free-breathing coronary MRA
link https://doi.org/10.1002/mrm.28851account_box Qi, Haikunaccount_box Hajhosseiny, Rezaaccount_box Cruz, Gastaoaccount_box Kuestner, Thomasaccount_box Kunze, Karlaccount_box Neji, Radhoueneaccount_box Botnar, René Michaelaccount_box Prieto Vásquez, Claudia
Comparte este registro
Purpose: To develop an end-to-end deep learning technique for nonrigid motion-corrected (MoCo) reconstruction of ninefold undersampled free-breathing whole-heart coronary MRA (CMRA).
Registro Sencillo
Registro Completo
| Autor | Qi, Haikun Hajhosseiny, Reza Cruz, Gastao Kuestner, Thomas Kunze, Karl Neji, Radhouene Botnar, René Michael Prieto Vásquez, Claudia |
| Título | End-to-end deep learning nonrigid motion-corrected reconstruction for highly accelerated free-breathing coronary MRA |
| Revista | Magnetic Resonance in Medicine |
| ISSN | 0740-3194 |
| ISSN electrónico | 1522-2594 |
| Volumen | 86 |
| Número de publicación | 4 |
| Página inicio | 1983 |
| Página final | 1996 |
| Fecha de publicación | 2021 |
| Resumen | Purpose: To develop an end-to-end deep learning technique for nonrigid motion-corrected (MoCo) reconstruction of ninefold undersampled free-breathing whole-heart coronary MRA (CMRA). Methods: A novel deep learning framework was developed consisting of a diffeomorphic registration network and a motion-informed model-based deep learning (MoDL) reconstruction network. The registration network receives as input highly undersampled (similar to 22x) respiratory-resolved images and outputs 3D nonrigid respiratory motion fields between the images. The motion-informed MoDL performs MoCo reconstruction from undersampled data using the predicted motion fields. The whole deep learning framework, termed as MoCo-MoDL, was trained end-to-end in a supervised manner for simultaneous 3D nonrigid motion estimation and MoCo reconstruction. MoCo-MoDL was compared with a state-of-the-art nonrigid MoCo CMRA reconstruction technique in 15 retrospectively undersampled datasets and 9 prospectively undersampled acquisitions. Results: The acquisition time for ninefold accelerated CMRA was similar to 2.5 min. The reconstruction time was similar to 22 s for the proposed MoCo-MoDL and similar to 35 min for the conventional approach. MoCo-MoDL achieved higher peak SNR (27.86 +/- 3.00 vs. 26.71 +/- 2.79; P < .05) and structural similarity (0.78 +/- 0.06 vs. 0.75 +/- 0.06; P < .05) than the conventional approach. Similar vessel length and visual image quality score were obtained with the 2 methods, whereas improved vessel sharpness was observed with MoCo-MoDL. Conclusion: An end-to-end deep learning approach was introduced for simultaneous nonrigid motion estimation and MoCo reconstruction of highly undersampled free-breathing whole-heart CMRA. The rapid free-breathing CMRA acquisition together with the fast reconstruction of the proposed approach promises easy integration into clinical workflow. |
| Derechos | acceso abierto |
| DOI | 10.1002/mrm.28851 |
| Enlace | |
| Id de publicación en Pubmed | PMID: 34096095 |
| Id de publicación en WoS | WOS:000658225600001 |
| Palabra clave | Coronary MRA Deep learning nonrigid motion correction Deep learning reconstruction Free-breathing cardiac MRI |
| Tema ODS | 03 Good health and well-being |
| Tema ODS español | 03 Salud y bienestar |
| Temática | Ingeniería |
| Tipo de documento | artículo |