eprintid: 10134941 rev_number: 21 eprint_status: archive userid: 608 dir: disk0/10/13/49/41 datestamp: 2021-09-23 10:06:57 lastmod: 2022-08-21 06:10:21 status_changed: 2021-09-23 10:06:57 type: article metadata_visibility: show creators_name: Jaubert, O creators_name: Steeden, J creators_name: Montalt-Tordera, J creators_name: Arridge, S creators_name: Kowalik, GT creators_name: Muthurangu, V title: Deep artifact suppression for spiral real-time phase contrast cardiac magnetic resonance imaging in congenital heart disease ispublished: pub divisions: UCL divisions: B02 divisions: D14 divisions: GA1 divisions: B04 divisions: C05 divisions: F48 keywords: Cardiac MRI, Congenital heart disease, Real time, Flow imaging, Image reconstruction, Machine learning note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions. abstract: PURPOSE: Real-time spiral phase contrast MR (PCMR) enables rapid free-breathing assessment of flow. Target spatial and temporal resolutions require high acceleration rates often leading to long reconstruction times. Here we propose a deep artifact suppression framework for fast and accurate flow quantification. METHODS: U-Nets were trained for deep artifact suppression using 520 breath-hold gated spiral PCMR aortic datasets collected in congenital heart disease patients. Two spiral trajectories (uniform and perturbed) and two losses (Mean Absolute Error -MAE- and average structural similarity index measurement -SSIM-) were compared in synthetic data in terms of MAE, peak SNR (PSNR) and SSIM. Perturbed spiral PCMR was prospectively acquired in 20 patients. Stroke Volume (SV), peak mean velocity and edge sharpness measurements were compared to Compressed Sensing (CS) and Cartesian reference. RESULTS: In synthetic data, perturbed spiral consistently outperformed uniform spiral for the different image metrics. U-Net MAE showed better MAE and PSNR while U-Net SSIM showed higher SSIM based metrics. In-vivo, there were no significant differences in SV between any of the real-time reconstructions and the reference standard Cartesian data. However, U-Net SSIM had better image sharpness and lower biases for peak velocity when compared to U-Net MAE. Reconstruction of 96 frames took ~59 s for CS and 3.9 s for U-Nets. CONCLUSION: Deep artifact suppression of complex valued images using an SSIM based loss was successfully demonstrated in a cohort of congenital heart disease patients for fast and accurate flow quantification. date: 2021-11 date_type: published official_url: https://doi.org/10.1016/j.mri.2021.08.005 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1884741 doi: 10.1016/j.mri.2021.08.005 lyricists_name: Arridge, Simon lyricists_name: Jaubert, Olivier lyricists_name: Kowalik, Grzegorz lyricists_name: Muthurangu, Vivek lyricists_name: Steeden, Jennifer lyricists_id: SRARR14 lyricists_id: OJAUB16 lyricists_id: GKOWA82 lyricists_id: VMUTH99 lyricists_id: JAEDG41 actors_name: Muthurangu, Vivek actors_id: VMUTH99 actors_role: owner full_text_status: public publication: Magnetic Resonance Imaging volume: 83 pagerange: 125-132 citation: Jaubert, O; Steeden, J; Montalt-Tordera, J; Arridge, S; Kowalik, GT; Muthurangu, V; (2021) Deep artifact suppression for spiral real-time phase contrast cardiac magnetic resonance imaging in congenital heart disease. Magnetic Resonance Imaging , 83 pp. 125-132. 10.1016/j.mri.2021.08.005 <https://doi.org/10.1016/j.mri.2021.08.005>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10134941/3/Muthurangu_Deep%20artifact%20suppression%20for%20spiral%20real-time%20phase%20contrast%20cardiac%20magnetic%20resonance%20imaging%20in%20congenital%20heart%20disease_AAM.pdf