Louise Anne Elizabeth Brown
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Louise Anne Elizabeth Brown has a total of 126 co-authors. Here are the top co-authors by number of shared publications:
- Sven Plein
University of Leeds
12 shared publications - Peter P. Swoboda
Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds
10 shared publications - Peter Kellman
National Institutes of Health
9 shared publications - Hui Xue
National Heart, Lung, and Blood Institute, National Institutes of Health, DHHS, Bethesda, MD, USA
8 shared publications - John Pierre Greenwood
Baker Heart and Diabetes Institute, Melbourne, Australia
8 shared publications - Amrit Chowdhary
Department of Biomedical Imaging Science, Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, Clarendon Way, Leeds LS2 9JT, UK
6 shared publications
Latest Publications
- Open Access
- 19 June 2025
- Published by Elsevier in Journal of Cardiovascular Magnetic Resonance
- Vol. 27 (2) , 101927
Normal values of high-resolution transmural perfusion distribution metrics for automated quantitative pixel-wise myocardial perfusion cardiovascular magnetic resonance
- 19 June 2025
- Published by Elsevier in Journal of Cardiovascular Magnetic Resonance
- Vol. 27 (2) , 101927
Open AccessNormal values of high-resolution transmural perfusion distribution metrics for automated quantitative pixel-wise myocardial perfusion cardiovascular magnetic resonance
- 7 August 2024
- Published by Elsevier in JACC: Cardiovascular Imaging
- Vol. 17 (11) , 1305-1316
The Impact of Bariatric Surgery on Coronary Microvascular Function Assessed Using Automated Quantitative Perfusion CMR
- 7 August 2024
- Published by Elsevier in JACC: Cardiovascular Imaging
- Vol. 17 (11) , 1305-1316
The Impact of Bariatric Surgery on Coronary Microvascular Function Assessed Using Automated Quantitative Perfusion CMR
- Open Access
Metformin associates with improved myocardial perfusion reserve and survival in patients with Type 2 Diabetes Mellitus
Background: Metformin is an antihyperglycemic agent frequently used in the treatment of Type 2 Diabetes Mellitus (T2DM). Patients with T2DM are at increased risk of cardiovascular diseases, including coronary artery disease (CAD), silent myocardial infarction (MI) and coronary microvascular dysfunction (CMD), all of which can be detected and quantified using Cardiovascular Magnetic Resonance (CMR). We explored the association between metformin use, stress Myocardial Blood Flow (MBF), Myocardial Perfusion Reserve (MPR), survival and major adverse cardiovascular and cerbrovasular events (MACCE; a composite of all-cause death, MI, stroke, heart failure hospitalisation and coronary revascularisation) in patients with T2DM. Methods: A multi-centre study of patients with T2DM, and a cohort of healthy controls underwent quantitative myocardial perfusion CMR. Global MBF and MPR were derived using an automatic artificial intelligence-supported process. Multivariable regression analysis and cox proportional hazard models quantified associations between metformin use, MBF, MPR, all-cause death and MACCE. Results: Analysis included 572 patients with T2DM (68% prescribed metformin) with median follow-up 851 days (interquartile range 935-765). Metformin use was associated with an increase in MPR of 0.12 [0.08-0.40], P=0.004. There was a total of 82 (14.3%) first MACCE in all T2DM patients including a total of 25 (4.4%) deaths. Although the number of first MACCE events was similar for patients prescribed metformin (53 (14%)) compared to those who were not (29 (15.8%) (P=0.73)), there was a total of 9 deaths (2.3%) in patients prescribed metformin compred to 16 (8.7%) in patients who were not, adjusted hazard ratio 0.29 [95% CI 0.12-0.73] P=0.009). Conclusion: In patients with T2DM, metformin use is associated with higher MPR and improved survival. Clinical Perspective: Patients with Type 2 Diabetes Mellitus (T2DM) are at increased risk of cardiovascular disease. Cardiovascular Magnetic Resonane (CMR) can be used to detect and quantify absolute stress myocardial blood flow (MBF) and myocardial perfusion reserve (MPR), both of which are objective measures of coronary microvascular function. Metformin is frequently used in the treatment of T2DM. We investigated the association between metformin use, CMR-derived stress MBF, MPR and clinical outcomes in patients with T2DM. In a longitudinal cohort study of patients with T2DM, metformin use was associated with higher MPR as a marker of microvascular function, and improved survival after adjusting for certain confounding parameters. Further prospective studies are needed to confirm the association between metformin use and improved MPR and reduced mortality, as well as to clarify the mechanisms responsible and quantify the dose these associated outcomes are observed. Central illustration:
Open AccessMetformin associates with improved myocardial perfusion reserve and survival in patients with Type 2 Diabetes Mellitus
Background: Metformin is an antihyperglycemic agent frequently used in the treatment of Type 2 Diabetes Mellitus (T2DM). Patients with T2DM are at increased risk of cardiovascular diseases, including coronary artery disease (CAD), silent myocardial infarction (MI) and coronary microvascular dysfunction (CMD), all of which can be detected and quantified using Cardiovascular Magnetic Resonance (CMR). We explored the association between metformin use, stress Myocardial Blood Flow (MBF), Myocardial Perfusion Reserve (MPR), survival and major adverse cardiovascular and cerbrovasular events (MACCE; a composite of all-cause death, MI, stroke, heart failure hospitalisation and coronary revascularisation) in patients with T2DM. Methods: A multi-centre study of patients with T2DM, and a cohort of healthy controls underwent quantitative myocardial perfusion CMR. Global MBF and MPR were derived using an automatic artificial intelligence-supported process. Multivariable regression analysis and cox proportional hazard models quantified associations between metformin use, MBF, MPR, all-cause death and MACCE. Results: Analysis included 572 patients with T2DM (68% prescribed metformin) with median follow-up 851 days (interquartile range 935-765). Metformin use was associated with an increase in MPR of 0.12 [0.08-0.40], P=0.004. There was a total of 82 (14.3%) first MACCE in all T2DM patients including a total of 25 (4.4%) deaths. Although the number of first MACCE events was similar for patients prescribed metformin (53 (14%)) compared to those who were not (29 (15.8%) (P=0.73)), there was a total of 9 deaths (2.3%) in patients prescribed metformin compred to 16 (8.7%) in patients who were not, adjusted hazard ratio 0.29 [95% CI 0.12-0.73] P=0.009). Conclusion: In patients with T2DM, metformin use is associated with higher MPR and improved survival. Clinical Perspective: Patients with Type 2 Diabetes Mellitus (T2DM) are at increased risk of cardiovascular disease. Cardiovascular Magnetic Resonane (CMR) can be used to detect and quantify absolute stress myocardial blood flow (MBF) and myocardial perfusion reserve (MPR), both of which are objective measures of coronary microvascular function. Metformin is frequently used in the treatment of T2DM. We investigated the association between metformin use, CMR-derived stress MBF, MPR and clinical outcomes in patients with T2DM. In a longitudinal cohort study of patients with T2DM, metformin use was associated with higher MPR as a marker of microvascular function, and improved survival after adjusting for certain confounding parameters. Further prospective studies are needed to confirm the association between metformin use and improved MPR and reduced mortality, as well as to clarify the mechanisms responsible and quantify the dose these associated outcomes are observed. Central illustration:
- Open Access
- 2 December 2022
- Published by Oxford University Press (OUP) in European Heart Journal - Cardiovascular Imaging
- Vol. 24 (4) , 426-434
Sex- and age-specific normal values for automated quantitative pixel-wise myocardial perfusion cardiovascular magnetic resonance
Recently developed in-line automated cardiovascular magnetic resonance (CMR) myocardial perfusion mapping has been shown to be reproducible and comparable with positron emission tomography (PET), and can be easily integrated into clinical workflows. Bringing quantitative myocardial perfusion CMR into routine clinical care requires knowledge of sex- and age-specific normal values in order to define thresholds for disease detection. This study aimed to establish sex- and age-specific normal values for stress and rest CMR myocardial blood flow (MBF) in healthy volunteers. A total of 151 healthy volunteers recruited from two centres underwent adenosine stress and rest myocardial perfusion CMR. In-line automatic reconstruction and post processing of perfusion data were implemented within the Gadgetron software framework, creating pixel-wise perfusion maps. Rest and stress MBF were measured, deriving myocardial perfusion reserve (MPR) and were subdivided by sex and age. Mean MBF in all subjects was 0.62 ± 0.13 mL/g/min at rest and 2.24 ± 0.53 mL/g/min during stress. Mean MPR was 3.74 ± 1.00. Compared with males, females had higher rest (0.69 ± 0.13 vs. 0.58 ± 0.12 mL/g/min, P < 0.01) and stress MBF (2.41 ± 0.47 vs. 2.13 ± 0.54 mL/g/min, P = 0.001). Stress MBF and MPR showed significant negative correlations with increasing age (r = −0.43, P < 0.001 and r = −0.34, P < 0.001, respectively). Fully automated in-line CMR myocardial perfusion mapping produces similar normal values to the published CMR and PET literature. There is a significant increase in rest and stress MBF, but not MPR, in females and a reduction of stress MBF and MPR with advancing age, advocating the use of sex- and age-specific reference ranges for diagnostic use. A total of 150 healthy volunteers underwent adenosine stress and rest quantitative perfusion cardiovascular magnetic resonance. Normal values were established in this large cohort with a wide age range. We demonstrated higher stress and rest myocardial blood flow in females compared with males, and a decrease in stress myocardial blood flow and myocardial perfusion reserve with increasing age. Suggested normal ranges referenced to age and sex have been created with this data.
- 2 December 2022
- Published by Oxford University Press (OUP) in European Heart Journal - Cardiovascular Imaging
- Vol. 24 (4) , 426-434
Open AccessSex- and age-specific normal values for automated quantitative pixel-wise myocardial perfusion cardiovascular magnetic resonance
Recently developed in-line automated cardiovascular magnetic resonance (CMR) myocardial perfusion mapping has been shown to be reproducible and comparable with positron emission tomography (PET), and can be easily integrated into clinical workflows. Bringing quantitative myocardial perfusion CMR into routine clinical care requires knowledge of sex- and age-specific normal values in order to define thresholds for disease detection. This study aimed to establish sex- and age-specific normal values for stress and rest CMR myocardial blood flow (MBF) in healthy volunteers. A total of 151 healthy volunteers recruited from two centres underwent adenosine stress and rest myocardial perfusion CMR. In-line automatic reconstruction and post processing of perfusion data were implemented within the Gadgetron software framework, creating pixel-wise perfusion maps. Rest and stress MBF were measured, deriving myocardial perfusion reserve (MPR) and were subdivided by sex and age. Mean MBF in all subjects was 0.62 ± 0.13 mL/g/min at rest and 2.24 ± 0.53 mL/g/min during stress. Mean MPR was 3.74 ± 1.00. Compared with males, females had higher rest (0.69 ± 0.13 vs. 0.58 ± 0.12 mL/g/min, P < 0.01) and stress MBF (2.41 ± 0.47 vs. 2.13 ± 0.54 mL/g/min, P = 0.001). Stress MBF and MPR showed significant negative correlations with increasing age (r = −0.43, P < 0.001 and r = −0.34, P < 0.001, respectively). Fully automated in-line CMR myocardial perfusion mapping produces similar normal values to the published CMR and PET literature. There is a significant increase in rest and stress MBF, but not MPR, in females and a reduction of stress MBF and MPR with advancing age, advocating the use of sex- and age-specific reference ranges for diagnostic use. A total of 150 healthy volunteers underwent adenosine stress and rest quantitative perfusion cardiovascular magnetic resonance. Normal values were established in this large cohort with a wide age range. We demonstrated higher stress and rest myocardial blood flow in females compared with males, and a decrease in stress myocardial blood flow and myocardial perfusion reserve with increasing age. Suggested normal ranges referenced to age and sex have been created with this data.
- Open Access
- 26 October 2022
- Published by Oxford University Press (OUP) in European Heart Journal - Cardiovascular Imaging
- Vol. 24 (1) , 38-45
Cardiovascular magnetic resonance phenotyping of heart failure with mildly reduced ejection fraction
The 2016 European Society of Cardiology Heart Failure Guidelines defined a new category: heart failure with mid-range ejection fraction (HFmrEF) of 40–49%. This new category was highlighted as having limited evidence and research was advocated into underlying characteristics, pathophysiology, and diagnosis. We used multi-parametric cardiovascular magnetic resonance (CMR) to define the cardiac phenotype of presumed non-ischaemic HFmrEF. Patients (N = 300, 62.7 ± 13 years, 63% males) with a clinical diagnosis of heart failure with no angina symptoms, history of myocardial infarction, or coronary intervention were prospectively recruited. Patients underwent clinical assessment and CMR including T1 mapping, extracellular volume (ECV) mapping, late gadolinium enhancement, and measurement of myocardial blood flow at rest and maximal hyperaemia. Of 273 patients in the final analysis, 93 (34%) patients were categorized as HFmrEF, 46 (17%) as heart failure with preserved ejection fraction (HFpEF), and 134 (49%) as heart failure with reduced ejection fraction (HFrEF). Nineteen (20%) patients with HFmrEF had evidence of occult ischaemic heart disease. Diffuse fibrosis and hyperaemic myocardial blood flow were similar in HFmrEF and HFpEF, but HFmrEF showed significantly lower native T1 (1311 ± 32 vs. 1340 ± 45 ms, P < 0.001), ECV (24.6 ± 3.2 vs. 26.3 ± 3.1%, P < 0.001), and higher myocardial perfusion reserve (2.75 ± 0.84 vs. 2.28 ± 0.84, P < 0.001) compared with HFrEF. Patients with HFmrEF share most phenotypic characteristics with HFpEF, including the degree of microvascular impairment and fibrosis, but have a high prevalence of occult ischaemic heart disease similar to HFrEF. Further work is needed to confirm how the phenotype of HFmrEF responds to medical therapy. There is limited research into the mechanisms of heart failure with mildly reduced ejection fraction (HFmrEF, 40–49%). Using cardiovascular magnetic resonance, we have shown that patients with HFmrEF share most phenotypic characteristics with heart failure with preserved ejection fraction (HFpEF, ≥50%), including the degree of microvascular impairment and fibrosis. However, they also have a high prevalence of occult ischaemic heart disease similar to heart failure with reduced ejection fraction (HFrEF, <40%).
- 26 October 2022
- Published by Oxford University Press (OUP) in European Heart Journal - Cardiovascular Imaging
- Vol. 24 (1) , 38-45
Open AccessCardiovascular magnetic resonance phenotyping of heart failure with mildly reduced ejection fraction
The 2016 European Society of Cardiology Heart Failure Guidelines defined a new category: heart failure with mid-range ejection fraction (HFmrEF) of 40–49%. This new category was highlighted as having limited evidence and research was advocated into underlying characteristics, pathophysiology, and diagnosis. We used multi-parametric cardiovascular magnetic resonance (CMR) to define the cardiac phenotype of presumed non-ischaemic HFmrEF. Patients (N = 300, 62.7 ± 13 years, 63% males) with a clinical diagnosis of heart failure with no angina symptoms, history of myocardial infarction, or coronary intervention were prospectively recruited. Patients underwent clinical assessment and CMR including T1 mapping, extracellular volume (ECV) mapping, late gadolinium enhancement, and measurement of myocardial blood flow at rest and maximal hyperaemia. Of 273 patients in the final analysis, 93 (34%) patients were categorized as HFmrEF, 46 (17%) as heart failure with preserved ejection fraction (HFpEF), and 134 (49%) as heart failure with reduced ejection fraction (HFrEF). Nineteen (20%) patients with HFmrEF had evidence of occult ischaemic heart disease. Diffuse fibrosis and hyperaemic myocardial blood flow were similar in HFmrEF and HFpEF, but HFmrEF showed significantly lower native T1 (1311 ± 32 vs. 1340 ± 45 ms, P < 0.001), ECV (24.6 ± 3.2 vs. 26.3 ± 3.1%, P < 0.001), and higher myocardial perfusion reserve (2.75 ± 0.84 vs. 2.28 ± 0.84, P < 0.001) compared with HFrEF. Patients with HFmrEF share most phenotypic characteristics with HFpEF, including the degree of microvascular impairment and fibrosis, but have a high prevalence of occult ischaemic heart disease similar to HFrEF. Further work is needed to confirm how the phenotype of HFmrEF responds to medical therapy. There is limited research into the mechanisms of heart failure with mildly reduced ejection fraction (HFmrEF, 40–49%). Using cardiovascular magnetic resonance, we have shown that patients with HFmrEF share most phenotypic characteristics with heart failure with preserved ejection fraction (HFpEF, ≥50%), including the degree of microvascular impairment and fibrosis. However, they also have a high prevalence of occult ischaemic heart disease similar to heart failure with reduced ejection fraction (HFrEF, <40%).
- Open Access
- 1 May 2021
- Published by SAGE Publications in Diabetes & Vascular Disease Research
- Vol. 18 (3)
Rationale and design of the randomised controlled cross-over trial: Cardiovascular effects of empaglifozin in diabetes mellitus
Background: Type 2 diabetes (T2D) is associated with an increased risk of cardiovascular (CV) disease. In patients with T2D and established CV disease, selective inhibitors of sodium–glucose cotransporter 2 (SGLT2) have been shown to decrease CV and all-cause mortality, and heart failure (HF) admissions. Utilising CV magnetic resonance imaging (CMR) and continuous glucose monitoring (CGM) by FreeStyle Libre Pro Sensor, we aim to explore the mechanisms of action which give Empagliflozin, an SGLT2 inhibitor, its beneficial CV effects and compare these to the effects of dipeptidyl peptidase-4 inhibitor Sitagliptin. Methods: This is a single centre, open-label, cross-over trial conducted at the Leeds Teaching Hospitals NHS Trust. Participants are randomised for the order of treatment and receive 3 months therapy with Empagliflozin, and 3 months therapy with Sitagliptin sequentially. Twenty-eight eligible T2D patients with established ischaemic heart disease will be recruited. Patients undergo serial CMR scans on three visits. Discussion: The primary outcome measure is the myocardial perfusion reserve in remote myocardium. We hypothesise that Empaglifozin treatment is associated with improvements in myocardial blood flow and reductions in myocardial interstitial fibrosis, independent of CGM measured glycemic control in patients with T2D and established CV disease. Trial registration: This study has full research ethics committee approval (REC: 18/YH/0190) and data collection is anticipated to finish in December 2021. This study was retrospectively registered at https://doi.org/10.1186/ISRCTN82391603 and monitored by the University of Leeds. The study results will be submitted for publication within 6 months of completion.
- 1 May 2021
- Published by SAGE Publications in Diabetes & Vascular Disease Research
- Vol. 18 (3)
Open AccessRationale and design of the randomised controlled cross-over trial: Cardiovascular effects of empaglifozin in diabetes mellitus
Background: Type 2 diabetes (T2D) is associated with an increased risk of cardiovascular (CV) disease. In patients with T2D and established CV disease, selective inhibitors of sodium–glucose cotransporter 2 (SGLT2) have been shown to decrease CV and all-cause mortality, and heart failure (HF) admissions. Utilising CV magnetic resonance imaging (CMR) and continuous glucose monitoring (CGM) by FreeStyle Libre Pro Sensor, we aim to explore the mechanisms of action which give Empagliflozin, an SGLT2 inhibitor, its beneficial CV effects and compare these to the effects of dipeptidyl peptidase-4 inhibitor Sitagliptin. Methods: This is a single centre, open-label, cross-over trial conducted at the Leeds Teaching Hospitals NHS Trust. Participants are randomised for the order of treatment and receive 3 months therapy with Empagliflozin, and 3 months therapy with Sitagliptin sequentially. Twenty-eight eligible T2D patients with established ischaemic heart disease will be recruited. Patients undergo serial CMR scans on three visits. Discussion: The primary outcome measure is the myocardial perfusion reserve in remote myocardium. We hypothesise that Empaglifozin treatment is associated with improvements in myocardial blood flow and reductions in myocardial interstitial fibrosis, independent of CGM measured glycemic control in patients with T2D and established CV disease. Trial registration: This study has full research ethics committee approval (REC: 18/YH/0190) and data collection is anticipated to finish in December 2021. This study was retrospectively registered at https://doi.org/10.1186/ISRCTN82391603 and monitored by the University of Leeds. The study results will be submitted for publication within 6 months of completion.
- Open Access
- 1 May 2021
- Published by Wolters Kluwer Health in Circulation: Cardiovascular Imaging
- Vol. 14 (5) , e012256
Detrimental Immediate- and Medium-Term Clinical Effects of Right Ventricular Pacing in Patients With Myocardial Fibrosis
Background: Long-term right ventricular (RV) pacing leads to heart failure or a decline in left ventricular (LV) function in up to a fifth of patients. We aimed to establish whether patients with focal fibrosis detected on late gadolinium enhancement cardiovascular magnetic resonance (CMR) have deterioration in LV function after RV pacing. Methods: We recruited 84 patients with LV ejection fraction ≥40% into 2 observational CMR studies. Patients (n=34) with a dual-chamber device and preserved atrioventricular conduction underwent CMR in 2 asynchronous pacing modes (atrial asynchronous and dual-chamber asynchronous) to compare intrinsic atrioventricular conduction with forced RV pacing. Patients (n=50) with high-grade atrioventricular block underwent CMR before and 6 months after pacemaker implantation to investigate the medium-term effects of RV pacing. Results: The key findings were (1) initiation of RV pacing in patients with fibrosis, compared with those without, was associated with greater immediate changes in both LV end-systolic volume index (5.3±3.5 versus 2.1±2.4 mL/m 2 ; P P =0.02); (2) medium-term RV pacing in patients with fibrosis, compared with those without, was associated with greater changes in LV end-systolic volume index (8.0±10.4 versus −0.6±7.3 mL/m 2 ; P =0.008) and LV ejection fraction (−12.3±7.9% versus −6.7±6.2%; P =0.012); (3) patients with fibrosis did not experience an improvement in quality of life, biomarkers, or functional class after pacemaker implantation; (4) after 6 months of RV pacing, 10 of 50 (20%) patients developed LV ejection fraction 1.1 g of fibrosis with 90% sensitivity and 70% specificity. Conclusions: Fibrosis detected on CMR is associated with immediate- and medium-term deterioration in LV function following RV pacing and could be used to identify those at risk of heart failure before pacemaker implantation.
- 1 May 2021
- Published by Wolters Kluwer Health in Circulation: Cardiovascular Imaging
- Vol. 14 (5) , e012256
Open AccessDetrimental Immediate- and Medium-Term Clinical Effects of Right Ventricular Pacing in Patients With Myocardial Fibrosis
Background: Long-term right ventricular (RV) pacing leads to heart failure or a decline in left ventricular (LV) function in up to a fifth of patients. We aimed to establish whether patients with focal fibrosis detected on late gadolinium enhancement cardiovascular magnetic resonance (CMR) have deterioration in LV function after RV pacing. Methods: We recruited 84 patients with LV ejection fraction ≥40% into 2 observational CMR studies. Patients (n=34) with a dual-chamber device and preserved atrioventricular conduction underwent CMR in 2 asynchronous pacing modes (atrial asynchronous and dual-chamber asynchronous) to compare intrinsic atrioventricular conduction with forced RV pacing. Patients (n=50) with high-grade atrioventricular block underwent CMR before and 6 months after pacemaker implantation to investigate the medium-term effects of RV pacing. Results: The key findings were (1) initiation of RV pacing in patients with fibrosis, compared with those without, was associated with greater immediate changes in both LV end-systolic volume index (5.3±3.5 versus 2.1±2.4 mL/m 2 ; P P =0.02); (2) medium-term RV pacing in patients with fibrosis, compared with those without, was associated with greater changes in LV end-systolic volume index (8.0±10.4 versus −0.6±7.3 mL/m 2 ; P =0.008) and LV ejection fraction (−12.3±7.9% versus −6.7±6.2%; P =0.012); (3) patients with fibrosis did not experience an improvement in quality of life, biomarkers, or functional class after pacemaker implantation; (4) after 6 months of RV pacing, 10 of 50 (20%) patients developed LV ejection fraction 1.1 g of fibrosis with 90% sensitivity and 70% specificity. Conclusions: Fibrosis detected on CMR is associated with immediate- and medium-term deterioration in LV function following RV pacing and could be used to identify those at risk of heart failure before pacemaker implantation.
- 1 April 2021
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 299 (1) , 86-96
Acute Microstructural Changes after ST-Segment Elevation Myocardial Infarction Assessed with Diffusion Tensor Imaging
Cardiac diffusion tensor imaging can be used to detect early and irreversible myocardial microstructural remodeling that may improve the prediction of left ventricular functional recovery at 3 months. Background Cardiac diffusion tensor imaging (cDTI) allows for in vivo characterization of myocardial microstructure. In cDTI, mean diffusivity and fractional anisotropy (FA)—markers of magnitude an...
- 1 April 2021
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 299 (1) , 86-96
Acute Microstructural Changes after ST-Segment Elevation Myocardial Infarction Assessed with Diffusion Tensor Imaging
Cardiac diffusion tensor imaging can be used to detect early and irreversible myocardial microstructural remodeling that may improve the prediction of left ventricular functional recovery at 3 months. Background Cardiac diffusion tensor imaging (cDTI) allows for in vivo characterization of myocardial microstructure. In cDTI, mean diffusivity and fractional anisotropy (FA)—markers of magnitude an...
- 1 November 2020
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 2 (6) , e200009
Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning
The described convolutional neural network was capable of segmenting and determining the mean stress and rest myocardial blood flow in a manner comparable to manual segmentation. Purpose To develop a deep neural network–based computational workflow for inline myocardial perfusion analysis that automatically delineates the myocardium, which improves the clinical workflow and...
- 1 November 2020
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 2 (6) , e200009
Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning
The described convolutional neural network was capable of segmenting and determining the mean stress and rest myocardial blood flow in a manner comparable to manual segmentation. Purpose To develop a deep neural network–based computational workflow for inline myocardial perfusion analysis that automatically delineates the myocardium, which improves the clinical workflow and...
- Open Access
Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning
Recent development of quantitative myocardial blood flow (MBF) mapping allows direct evaluation of absolute myocardial perfusion, by computing pixel-wise flow maps. Clinical studies suggest quantitative evaluation would be more desirable for objectivity and efficiency. Objective assessment can be further facilitated by segmenting the myocardium and automatically generating reports following the AHA model. This will free user interaction for analysis and lead to a 'one-click' solution to improve workflow. This paper proposes a deep neural network based computational workflow for inline myocardial perfusion analysis. Adenosine stress and rest perfusion scans were acquired from three hospitals. Training set included N=1,825 perfusion series from 1,034 patients. Independent test set included 200 scans from 105 patients. Data were consecutively acquired at each site. A convolution neural net (CNN) model was trained to provide segmentation for LV cavity, myocardium and right ventricular by processing incoming 2D+T perfusion Gd series. Model outputs were compared to manual ground-truth for accuracy of segmentation and flow measures derived on global and per-sector basis. The trained models were integrated onto MR scanners for effective inference. Segmentation accuracy and myocardial flow measures were compared between CNN models and manual ground-truth. The mean Dice ratio of CNN derived myocardium was 0.93 +/- 0.04. Both global flow and per-sector values showed no significant difference, compared to manual results. The AHA 16 segment model was automatically generated and reported on the MR scanner. As a result, the fully automated analysis of perfusion flow mapping was achieved. This solution was integrated on the MR scanner, enabling 'one-click' analysis and reporting of myocardial blood flow.
Open AccessAutomated Inline Analysis of Myocardial Perfusion MRI with Deep Learning
Recent development of quantitative myocardial blood flow (MBF) mapping allows direct evaluation of absolute myocardial perfusion, by computing pixel-wise flow maps. Clinical studies suggest quantitative evaluation would be more desirable for objectivity and efficiency. Objective assessment can be further facilitated by segmenting the myocardium and automatically generating reports following the AHA model. This will free user interaction for analysis and lead to a 'one-click' solution to improve workflow. This paper proposes a deep neural network based computational workflow for inline myocardial perfusion analysis. Adenosine stress and rest perfusion scans were acquired from three hospitals. Training set included N=1,825 perfusion series from 1,034 patients. Independent test set included 200 scans from 105 patients. Data were consecutively acquired at each site. A convolution neural net (CNN) model was trained to provide segmentation for LV cavity, myocardium and right ventricular by processing incoming 2D+T perfusion Gd series. Model outputs were compared to manual ground-truth for accuracy of segmentation and flow measures derived on global and per-sector basis. The trained models were integrated onto MR scanners for effective inference. Segmentation accuracy and myocardial flow measures were compared between CNN models and manual ground-truth. The mean Dice ratio of CNN derived myocardium was 0.93 +/- 0.04. Both global flow and per-sector values showed no significant difference, compared to manual results. The AHA 16 segment model was automatically generated and reported on the MR scanner. As a result, the fully automated analysis of perfusion flow mapping was achieved. This solution was integrated on the MR scanner, enabling 'one-click' analysis and reporting of myocardial blood flow.