Browsing by Author "Phair, Andrew"

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    A motion-corrected deep-learning reconstruction framework for accelerating whole-heart magnetic resonance imaging in patients with congenital heart disease
    (Elsevier B.V., 2024) Phair, Andrew; Fotaki, Anastasia; Felsner, Lina; Fletcher, Thomas J.; Qi, Haikun; Botnar, Rene Michael; Prieto Vásquez, Claudia del Carmen
    Background: Cardiovascular magnetic resonance (CMR) is an important imaging modality for the assessment and management of adult patients with congenital heart disease (CHD). However, conventional techniques for three-dimensional (3D) whole-heart acquisition involve long and unpredictable scan times and methods that accelerate scans via k-space undersampling often rely on long iterative reconstructions. Deep-learning-based reconstruction methods have recently attracted much interest due to their capacity to provide fast reconstructions while often outperforming existing state-of-the-art methods. In this study, we sought to adapt and validate a non-rigid motion-corrected model-based deep learning (MoCo-MoDL) reconstruction framework for 3D whole-heart MRI in a CHD patient cohort. Methods: The previously proposed deep-learning reconstruction framework MoCo-MoDL, which incorporates a non-rigid motion-estimation network and a denoising regularization network within an unrolled iterative reconstruction, was trained in an end-to-end manner using 39 CHD patient datasets. Once trained, the framework was evaluated in eight CHD patient datasets acquired with seven-fold prospective undersampling. Reconstruction quality was compared with the state-of-the-art non-rigid motion-corrected patch-based low-rank reconstruction method (NR-PROST) and against reference images (acquired with three-or-four-fold undersampling and reconstructed with NR-PROST). Results: Seven-fold undersampled scan times were 2.1 ± 0.3 minutes and reconstruction times were ∼30 seconds, approximately 240 times faster than an NR-PROST reconstruction. Image quality comparable to the reference images was achieved using the proposed MoCo-MoDL framework, with no statistically significant differences found in any of the assessed quantitative or qualitative image quality measures. Additionally, expert image quality scores indicated the MoCo-MoDL reconstructions were consistently of a higher quality than the NR-PROST reconstructions of the same data, with the differences in 12 of the 22 scores measured for individual vascular structures found to be statistically significant. Conclusion: The MoCo-MoDL framework was applied to an adult CHD patient cohort, achieving good quality 3D whole-heart images from ∼2-minute scans with reconstruction times of ∼30 seconds.
  • No Thumbnail Available
    Item
    Cardiovascular magnetic resonance imaging: Principles and advanced techniques
    (2025) Si, Dongyue; Littlewood, Simon J.; Crabb, Michael G.; Phair, Andrew; Prieto Vásquez, Claudia; Botnar, René Michael
    Cardiovascular magnetic resonance (CMR) imaging is an established non-invasive tool for the assessment of cardiovascular diseases, which are the leading cause of death globally. CMR provides dynamic and static multi-contrast and multi-parametric images, including cine for functional evaluation, contrast-enhanced imaging and parametric mapping for tissue characterization, and MR angiography for the assessment of the aortic, coronary and pulmonary circulation. However, clinical CMR imaging sequences still have some limitations such as the requirement for multiple breath-holds, incomplete spatial coverage, complex planning and acquisition, low scan efficiency and long scan times. To address these challenges, novel techniques have been developed during the last two decades, focusing on automated planning and acquisition timing, improved respiratory and cardiac motion handling strategies, image acceleration algorithms employing undersampled reconstruction, all-in-one imaging techniques that can acquire multiple contrast/parameters in a single scan, deep learning based methods applied along the entire CMR imaging pipeline, as well as imaging at high- and low-field strengths. In this article, we aim to provide a comprehensive review of CMR imaging, covering both established and emerging techniques, to give an overview of the present and future applications of CMR.
  • No Thumbnail Available
    Item
    End-to-end deep learning-based motion correction and reconstruction for accelerated whole-heart joint T 1/T 2 mapping.
    (2025) Felsner, Lina; Velasco, Carlos; Phair, Andrew; Fletcher, Thomas J.; Qi, Haikun; Botnar, René Michael; Prieto Vásquez, Claudia
    PURPOSE: To accelerate 3D whole-heart joint T 1/T 2 mapping for myocardial tissue characterization using an end-to-end deep learning algorithm for joint motion estimation and model-based motion-corrected reconstruction of multi-contrast undersampled data.METHODS: A free-breathing high-resolution motion-compensated 3D joint T 1/T 2 water/fat sequence is employed. The sequence consists of the acquisition of four interleaved volumes with 2-echo encoding, resulting in eight volumes with different contrasts. An end-to-end non-rigid motion-corrected reconstruction network is used to estimate high quality motion-corrected reconstructions from the eight multi-contrast undersampled data for subsequent joint T 1/T 2 mapping. Reconstruction with the proposed approach was compared against state-of-the-art motion-corrected HD-PROST reconstruction.RESULTS: The proposed approach yields images with good visual agreement compared to the reference reconstructions. The comparison of the quantitative values in the T 1 and T 2 maps showed the absence of systematic errors, and a small bias of -6.35 ms and -1.8 ms, respectively. The proposed reconstruction time was 24 seconds in comparison to 2.5 hours with motion-corrected HD-PROST, resulting in a reconstruction speed-up of over 370 times.CONCLUSION: In conclusion, this study presents a promising method for efficient whole-heart myocardial tissue characterization. Specifically, the research highlights the potential of the multi-contrast end-to-end deep learning algorithm for joint motion estimation and model-based motion-corrected reconstruction of multi-contrast undersampled data. The findings underscore its ability to compute T 1 and T 2 values with good agreement when compared to the reference motion-corrected HD-PROST method, while substantially reducing reconstruction time.
  • No Thumbnail Available
    Item
    Free-running 3D whole-heart T1 and T2 mapping and cine MRI using low-rank reconstruction with non-rigid cardiac motion correction
    (2023) Phair, Andrew; Cruz, Gastao; Qi, Haikun; Botnar, Rene M.; Prieto, Claudia
    Purpose: To introduce non-rigid cardiac motion correction into a novel free-running framework for the simultaneous acquisition of 3D whole-heart myocardial T-1 and T-2 maps and cine images, enabling a similar to 3-min scan.
  • Thumbnail Image
    Item
    Reconstruction Techniques for Accelerating Dynamic Cardiac MRI
    (Elsevier Inc., 2025) Phair, Andrew; Botnar, René Michael; Prieto Vásquez, Claudia
    Achieving sufficient spatial and temporal resolution for dynamic applications in cardiac MRI is a challenging task due to the inherently slow nature of MR imaging. In order to accelerate scans and allow improved resolution, much research over the past three decades has been aimed at developing innovative reconstruction methods that can yield high-quality images from reduced amounts of k-space data. In this review, we describe the evolution of these reconstruction techniques, with a particular focus on those advances that have shifted the dynamic reconstruction paradigm as it relates to cardiac MRI. This review discusses and explains the fundamental ideas behind the success of modern reconstruction algorithms, including parallel imaging, spatio-temporal redundancies, compressed sensing, low-rank methods and machine learning.