Jennifer A. Steeden
YOU?
Author Swipe
View article: Real-time, inline quantitative MRI enabled by scanner-integrated machine learning: a proof of principle with NODDI.
Real-time, inline quantitative MRI enabled by scanner-integrated machine learning: a proof of principle with NODDI. Open
Real-time, inline parameter estimation with the proposed generalisable framework resolves a key practical barrier to clinical uptake of advanced qMRI methods and enables their efficient integration into clinical workflows.
View article: Fully automated measurement of aortic pulse wave velocity from routine cardiac MRI studies
Fully automated measurement of aortic pulse wave velocity from routine cardiac MRI studies Open
We describe a fully automated method for measuring PWV from standard cardiac MRI localizers and a single phase contrast imaging plane. The method is robust and can be applied to routine clinical scans, and could unlock the potential of mea…
View article: Polyacrylamide Gel Calibration Phantoms for Quantification in Sodium MRI
Polyacrylamide Gel Calibration Phantoms for Quantification in Sodium MRI Open
Quantitative sodium ( 23 Na) MRI utilises a signal calibration approach to derive maps of total sodium concentration (TSC). Agarose gel vials are often used as calibration phantoms, but as a naturally occurring substance, agarose may exhib…
View article: MultiFlow: A unified deep learning framework for multi-vessel classification, segmentation and clustering of phase-contrast MRI validated on a multi-site single ventricle patient cohort
MultiFlow: A unified deep learning framework for multi-vessel classification, segmentation and clustering of phase-contrast MRI validated on a multi-site single ventricle patient cohort Open
We present a deep learning framework with two models for automated segmentation and large-scale flow phenotyping in a registry of single-ventricle patients. MultiFlowSeg simultaneously classifies and segments five key vessels, left and rig…
View article: A machine learning algorithm for creating isotropic 3D aortic segmentations from routine cardiac MR localizers
A machine learning algorithm for creating isotropic 3D aortic segmentations from routine cardiac MR localizers Open
A new method of producing isotropic 3D aortic segmentations from routine CMR 2D anisotropic localizers shows good agreement with segmentation made directly from 3D isotropic images. The method has the potential to be used as a simple scree…
View article: Multimodal optical ultrasound imaging: Real-time imaging under concurrent CT or MRI
Multimodal optical ultrasound imaging: Real-time imaging under concurrent CT or MRI Open
Optical ultrasound (OpUS) imaging is an ultrasound modality that utilizes fiber-optic ultrasound sources and detectors to perform pulse-echo ultrasound imaging. These probes can be constructed entirely from glass optical fibers and plastic…
View article: Prognostic utility of exercise cardiovascular magnetic resonance in patients with systemic sclerosis-associated pulmonary arterial hypertension
Prognostic utility of exercise cardiovascular magnetic resonance in patients with systemic sclerosis-associated pulmonary arterial hypertension Open
Aims Systemic sclerosis complicated by pulmonary arterial hypertension (SSc-PAH) is a rare condition with poor prognosis. The majority of patients are categorized as intermediate risk of mortality. Cardiovascular magnetic resonance (CMR) i…
View article: Image2Flow: A proof-of-concept hybrid image and graph convolutional neural network for rapid patient-specific pulmonary artery segmentation and CFD flow field calculation from 3D cardiac MRI data
Image2Flow: A proof-of-concept hybrid image and graph convolutional neural network for rapid patient-specific pulmonary artery segmentation and CFD flow field calculation from 3D cardiac MRI data Open
Computational fluid dynamics (CFD) can be used for non-invasive evaluation of hemodynamics. However, its routine use is limited by labor-intensive manual segmentation, CFD mesh creation, and time-consuming simulation. This study aims to tr…
View article: Training deep learning based dynamic MR image reconstruction using open-source natural videos
Training deep learning based dynamic MR image reconstruction using open-source natural videos Open
View article: Rapid 2D 23Na MRI of the calf using a denoising convolutional neural network
Rapid 2D 23Na MRI of the calf using a denoising convolutional neural network Open
Denoising CNNs trained on 1H data can be successfully applied to 23Na images of the calf; thus, allowing scan time to be reduced from ten minutes to two minutes with little impact on image quality or apparent TSC quan…
View article: Rapid 2D 23Na MRI of the calf using a denoising convolutional neural network
Rapid 2D 23Na MRI of the calf using a denoising convolutional neural network Open
23Na MRI can be used to quantify in-vivo tissue sodium concentration (TSC), but the low 23Na signal leads to long scan times and/or noisy or low-resolution images. Reconstruction algorithms such as CS have been proposed to mitigate low SNR…
View article: Image2Flow: A hybrid image and graph convolutional neural network for rapid patient-specific pulmonary artery segmentation and CFD flow field calculation from 3D cardiac MRI data
Image2Flow: A hybrid image and graph convolutional neural network for rapid patient-specific pulmonary artery segmentation and CFD flow field calculation from 3D cardiac MRI data Open
Computational fluid dynamics (CFD) can be used for evaluation of hemodynamics. However, its routine use is limited by labor-intensive manual segmentation, CFD mesh creation, and time-consuming simulation. This study aims to train a deep le…
View article: image2flow: Fast Calculation of Pulmonary Artery Flow Fields Directly FBom 3D MR Angiography Using Graph Convolutional Neural Networks
image2flow: Fast Calculation of Pulmonary Artery Flow Fields Directly FBom 3D MR Angiography Using Graph Convolutional Neural Networks Open
View article: Investigating the use of publicly available natural videos to learn Dynamic MR image reconstruction
Investigating the use of publicly available natural videos to learn Dynamic MR image reconstruction Open
Purpose: To develop and assess a deep learning (DL) pipeline to learn dynamic MR image reconstruction from publicly available natural videos (Inter4K). Materials and Methods: Learning was performed for a range of DL architectures (VarNet, …
View article: A Deep Learning Pipeline for Assessing Ventricular Volumes from a Cardiac MRI Registry of Patients with Single Ventricle Physiology
A Deep Learning Pipeline for Assessing Ventricular Volumes from a Cardiac MRI Registry of Patients with Single Ventricle Physiology Open
Purpose To develop an end-to-end deep learning (DL) pipeline for automated ventricular segmentation of cardiac MRI data from a multicenter registry of patients with Fontan circulation (Fontan Outcomes Registry Using CMR Examinations [FORCE…
View article: <scp>HyperSLICE</scp>: <scp>HyperBand</scp> optimized spiral for low‐latency interactive cardiac examination
<span>HyperSLICE</span>: <span>HyperBand</span> optimized spiral for low‐latency interactive cardiac examination Open
Purpose Interactive cardiac MRI is used for fast scan planning and MR‐guided interventions. However, the requirement for real‐time acquisition and near‐real‐time visualization constrains the achievable spatio‐temporal resolution. This stud…
View article: 2D sodium <scp>MRI</scp> of the human calf using half‐sinc excitation pulses and compressed sensing
2D sodium <span>MRI</span> of the human calf using half‐sinc excitation pulses and compressed sensing Open
Purpose Sodium MRI can be used to quantify tissue sodium concentration (TSC) in vivo; however, UTE sequences are required to capture the rapidly decaying signal. 2D MRI enables high in‐plane resolution but typically has long TEs. Half‐sinc…
View article: CLADE: Cycle Loss Augmented Degradation Enhancement for Unpaired Super-Resolution of Anisotropic Medical Images
CLADE: Cycle Loss Augmented Degradation Enhancement for Unpaired Super-Resolution of Anisotropic Medical Images Open
Three-dimensional (3D) imaging is popular in medical applications, however, anisotropic 3D volumes with thick, low-spatial-resolution slices are often acquired to reduce scan times. Deep learning (DL) offers a solution to recover high-reso…
View article: Deep Learning Pipeline for Preprocessing and Segmenting Cardiac Magnetic Resonance of Single Ventricle Patients from an Image Registry
Deep Learning Pipeline for Preprocessing and Segmenting Cardiac Magnetic Resonance of Single Ventricle Patients from an Image Registry Open
Purpose: To develop and evaluate an end-to-end deep learning pipeline for segmentation and analysis of cardiac magnetic resonance images to provide core-lab processing for a multi-centre registry of Fontan patients. Materials and Methods: …
View article: HyperSLICE: HyperBand optimized Spiral for Low-latency Interactive Cardiac Examination
HyperSLICE: HyperBand optimized Spiral for Low-latency Interactive Cardiac Examination Open
PURPOSE: Interactive cardiac magnetic resonance imaging is used for fast scan planning and MR guided interventions. However, the requirement for real-time acquisition and near real-time visualization constrains the achievable spatio-tempor…
View article: Automatic Segmentation of the Great Arteries for Computational Hemodynamic Assessment
Automatic Segmentation of the Great Arteries for Computational Hemodynamic Assessment Open
Background: Computational fluid dynamics (CFD) is increasingly used to assess blood flow conditions in patients with congenital heart disease (CHD). This requires patient-specific anatomy, usually obtained from segmented 3D cardiovascular …
View article: <scp>FReSCO</scp>: Flow Reconstruction and Segmentation for low‐latency Cardiac Output monitoring using deep artifact suppression and segmentation
<span>FReSCO</span>: Flow Reconstruction and Segmentation for low‐latency Cardiac Output monitoring using deep artifact suppression and segmentation Open
Purpose Real‐time monitoring of cardiac output (CO) requires low‐latency reconstruction and segmentation of real‐time phase‐contrast MR, which has previously been difficult to perform. Here we propose a deep learning framework for “FReSCO”…
View article: FReSCO: Flow Reconstruction and Segmentation for low latency Cardiac Output monitoring using deep artifact suppression and segmentation
FReSCO: Flow Reconstruction and Segmentation for low latency Cardiac Output monitoring using deep artifact suppression and segmentation Open
Purpose: Real-time monitoring of cardiac output (CO) requires low latency reconstruction and segmentation of real-time phase contrast MR (PCMR), which has previously been difficult to perform. Here we propose a deep learning framework for …
View article: Automatic segmentation of the great arteries for computational hemodynamic assessment
Automatic segmentation of the great arteries for computational hemodynamic assessment Open
ML can successfully segment the great vessels for CFD, with errors similar to inter-observer variability. This fast, automatic method reduces the time and effort needed for CFD analysis, making it more attractive for routine clinical use.
View article: Comprehensive mechanical & metabolic imaging of abdominal aortic aneurysm with 4D flow/ FDG PET on an integrated PETMRI: a feasibility study
Comprehensive mechanical & metabolic imaging of abdominal aortic aneurysm with 4D flow/ FDG PET on an integrated PETMRI: a feasibility study Open
Funding Acknowledgements Type of funding sources: Public Institution(s). Main funding source(s): NIHR Biomedical Research Centre, University College London Hospitals. Background A number of non-invasive imaging derived parameters have been…
View article: Real‐time deep artifact suppression using recurrent U‐Nets for low‐latency cardiac MRI
Real‐time deep artifact suppression using recurrent U‐Nets for low‐latency cardiac MRI Open
Purpose Real‐time low latency MRI is performed to guide various cardiac interventions. Real‐time acquisitions often require iterative image reconstruction strategies, which lead to long reconstruction times. In this study, we aim to recons…
View article: Machine Learning aided k-t SENSE for fast reconstruction of highly\n accelerated PCMR data
Machine Learning aided k-t SENSE for fast reconstruction of highly\n accelerated PCMR data Open
Purpose: We implemented the Machine Learning (ML) aided k-t SENSE\nreconstruction to enable high resolution quantitative real-time phase contrast\nMR (PCMR). Methods: A residual U-net and our U-net M were used to generate the\nhigh resolut…
View article: Machine Learning aided k-t SENSE for fast reconstruction of highly accelerated PCMR data
Machine Learning aided k-t SENSE for fast reconstruction of highly accelerated PCMR data Open
Purpose: We implemented the Machine Learning (ML) aided k-t SENSE reconstruction to enable high resolution quantitative real-time phase contrast MR (PCMR). Methods: A residual U-net and our U-net M were used to generate the high resolution…
View article: Reduced exercise capacity in patients with systemic sclerosis is associated with lower peak tissue oxygen extraction: a cardiovascular magnetic resonance-augmented cardiopulmonary exercise study
Reduced exercise capacity in patients with systemic sclerosis is associated with lower peak tissue oxygen extraction: a cardiovascular magnetic resonance-augmented cardiopulmonary exercise study Open
View article: Machine learning in Magnetic Resonance Imaging: Image reconstruction
Machine learning in Magnetic Resonance Imaging: Image reconstruction Open