View Presentation Video

Keywords: Vessels, Cardiovascular, Deep Learning

This study aims to investigate the feasibility of a compressed sensing artificial intelligence (CSAI) framework for non-contrast-enhanced coronary MRA. The image quality and the diagnostic performance of CSAI coronary MRA in patients with suspected CAD were fully evaluated using coronary computed tomography angiography (CTA) as the non-invasive clinical reference standard. The results shows that all recruited patients completed coronary MRA with high image quality and diagnostic performance within short scan time. Therefore, we conclude that the CASI coronary MRA could be a robust and safe non-invasive alternative for excluding significant disease in patients with suspected CAD.

View Presentation Video

Eva S. Peper^1,2, Dieuwertje Alblas³, Renske Merton⁴, Sibbeliene E. van den Bosch⁵, Anne Spakman⁴, Bram F. Coolen⁶, Gustav J. Strijkers⁶, Aart J. Nederveen⁴, Albert Wiegman⁵, Jelmer M. Wolterink³, Barbara A. Hutten⁷, and Pim van Ooij^4
1Bern University Hospital, University of Bern, Bern, Switzerland, ²Translation Imaging Center (TIC), Swiss Institute for Translational and Entrepreneurial Medicine, Bern, Switzerland, ³Department of Applied Mathematics, Technical Medical Center, University of Twente, Enschede, Netherlands, ⁴Department of Radiology and Nuclear Medicine, Amsterdam Cardiovascular Sciences, Amsterdam University Medical Center, location AMC, Amsterdam, Netherlands, ⁵Department of Pediatrics, Amsterdam University Medical Center, location AMC, Amsterdam, Netherlands, ⁶Department of Biomedical Engineering & Physics, Amsterdam Cardiovascular Sciences, Amsterdam University Medical Center, location AMC, Amsterdam, Netherlands, ⁷Department of Epidemiology and Data Science, Amsterdam Cardiovascular Sciences, Amsterdam University Medical Center, location AMC, Amsterdam, Netherlands

Keywords: Flow, Velocity & Flow, vessel wall, carotids, familial hypercholesterolemia

Familial hypercholesterolemia (FH) leads to premature atherosclerosis. In this study we use 4D flow and 3D black blood (BB) MRI to investigate carotid artery wall shear stress (WSS) and wall thickness (WT) 3D maps and their relation, in FH patients on lifelong statin prescriptions and their unaffected siblings (n=234). We applied machine learning segmentation technology and 3D statistical analysis methods and found that ensemble-averaged carotid WSS and WT maps were highly similar between the groups. However, the 3D carotid correlation coefficient maps showed lower agreement between WT and WSS in patients, suggesting abnormal wall remodeling processes compared to the siblings.

Yan Gong¹, Menglin Wu², Dingwei Fu³, Yu Guo⁴, Xiudi Lu⁵, Ying Zou⁶, Xiang Zhang¹, Jinxia Zhu⁷, Xianchang Zhang⁷, Xue Li², and Shuang Xia^5
1Department of Radiology, Tianjin Nankai Hospital, Tianjin, China, ²Department of Radiology, Second Hospital of Tianjin Medical University, Tianjin, China, ³Department of Radiology, First Central Clinical College, Tianjin Medical University, Tianjin, China, ⁴Department of Radiology, Medical Imaging Institute of Tianjin, Tianjin First Central Hospital, School of Medicine, Nankai University, Tianjin, China, ⁵Department of Radiology, First Teaching Hospital of Tianjin University of Traditional Chinese Medicine, Tianjin，China National Clinical Research Center for Chinese Medicine Acupuncture and Moxibustion, Tianjin, China, ⁶First Teaching Hospital of Tianjin University of Traditional Chinese Medicine, Tianjin，China National Clinical Research Center for Chinese Medicine Acupuncture and Moxibustion, Tianjin, China, ⁷MR Collaboration, Siemens Healthcare Ltd., Beijing, China

Keywords: Vessel Wall, Atherosclerosis, macrophage

Ischemic stroke can be attributed to the sudden rupture of high-risk atherosclerotic plaques. Therefore, identifying vulnerable plaque is essential for preventing acute vascular events. Increasing evidence has established that macrophages play a vital role in the pathogenesis of atherosclerosis. Using the black-blood technique, an imaging approach that suppresses blood signals to highlight the arterial wall, and a macrophage-targeted contrast agent, plaque vulnerability could be quantitatively assessed for the macrophage burden. This in vivo animal study non-invasively evaluated the plaque vulnerability, which may provide information on the clinical risk stratification.

View Presentation Video

Keywords: Vessels, Cardiovascular, angiography

Cardiovascular MRA is established for serial anatomical evaluation of patients with congenital heart disease (CHD). However, this approach is limited by diaphragmatic respiratory navigation, that leads to long acquisition times and degraded image quality due to residual motion artefacts. Here we evaluate a novel accelerated whole-heart framework in patients with adult CHD. This approach incorporates image-based navigation for translational and non-rigid motion-correction along with 3D patch-based denoising for efficient, free-breathing 3D whole-heart imaging. Comparison between the conventional and the research sequence shows superior diagnostic confidence and diagnostic accuracy for the proposed technique in significantly faster acquisition time (~3min proposed,~15min clinical). 

View Presentation Video

Ludovica Romanin^1,2, Bastien Milani¹, Christopher W. Roy¹, Aurélien Bustin^1,3,4, Salim Si-Mohamed^1,5,6, Milan Prsa⁷, Tobias Rutz⁸, Estelle Tenisch¹, Juerg Schwitter^8,9, Matthias Stuber^1,10, and Davide Piccini^1,2
1Diagnostic and Interventional Radiology, University Hospital of Lausanne (CHUV), Lausanne, Switzerland, ²Advanced Clinical Imaging Technology, Siemens Healthineers International AG, Lausanne, Switzerland, ³IHU LIRYC, Electrophysiology and Heart Modeling Institute, Université de Bordeaux – INSERM U1045, Pessac-Bordeaux, France, ⁴Department of Cardiovascular Imaging, Hôpital Cardiologique du Haut-Lévêque, CHU de Bordeaux, Pessac, France, ⁵INSA-Lyon, CNRS, Inserm, CREATIS, Université de Lyon, Villeurbanne, France, ⁶Département de Radiologie, Louis Pradel Hospital, Hospices Civils de Lyon, Bron, France, ⁷Woman-Mother-Child Department, Lausanne University Hospital and University of Lausanne, Division of Pediatric Cardiology, Lausanne, Switzerland, ⁸Heart and Vessel Department, Lausanne University Hospital and University of Lausanne, Service of Cardiology, Lausanne, Switzerland, ⁹Cardiac MR Center, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland, ¹⁰Center for Biomedical Imaging (CIBM), Lausanne, Switzerland

Keywords: Heart, Motion Correction

Ferumoxytol-enhanced free-running whole-heart MRI allows for a comprehensive evaluation of the cardiovascular anatomy in 3D. A similarity-driven multi-dimensional binning algorithm (SIMBA) has been proposed as a fast and efficient reconstruction of such data, by clustering and selecting motion-consistent information. In this work, we extend the SIMBA reconstruction to make use of the inherent redundancy of motion-consistent information using a compressed-sensing reconstruction, in which sparsity is maximized by the integration of inter-cluster non-rigid 3D motion-fields. With this new framework we demonstrate improved image quality, increased coronary sharpness and vessel conspicuity.

View Presentation Video

Alma Spahic¹, Grant S. Roberts¹, Anthony Peret², Rebecca L. Koscik³, Erin Jonaitis^3,4, Carson A. Hoffman², Leonardo A. Rivera-Rivera^1,4, Karly A. Cody⁴, Howard A. Rowley², Sterling C. Johnson^3,4,5, Oliver Wieben^1,2, Kevin M. Johnson^1,2, and Laura Eisenmenger^2
1Medical Physics, University of Wisconsin- Madison, Madison, WI, United States, ²Radiology, University of Wisconsin- Madison, Madison, WI, United States, ³Wisconsin Alzheimer's Institute, University of Wisconsin- Madison, Madison, WI, United States, ⁴Wisconsin Alzheimer's Disease Research Center, University of Wisconsin- Madison, Madison, WI, United States, ⁵Geriatric Research Education and Clinical Center, William S. Middleton Memorial Veterans Hospital, Madison, WI, United States

Keywords: Flow, Aging

Vascular disease is strongly associated with Alzheimer’s disease. Therefore, it is important to establish normative cerebrovascular changes in aging populations. In this study, we assess sex-specific, age-related changes in total cerebral blood flow (tCBF) and total parenchymal volume in 754 cognitively healthy, older adults. We further investigate whether the same changes are observed in flow normalized by total parenchymal volume. We found (1) significant decrease in tCBF and total parenchymal volume with age in both sexes, (2) no correlation between age and normalized flow in male subjects, and (3) significant decrease in normalized flow with age in female subjects.

Lei Ren¹ and Shuang Xia^2
1Department of Radiology, First Central Clinical School, Tianjin Medical University, Tianjin, China, ²Tianjin First Central Hospital, Tianjin, China

Keywords: Atherosclerosis, Blood vessels, computational fluid dynamics

This study was performed from a vessel wall imaging database, and investigated plaque characteristics, as well as geometric and hemodynamic parameters among different carotid bulb plaque locations caused by atherosclerosis. The results showed that wall shear stress (WSS) magnitudes around plaque side were lower than non-plaque side. Tortuosity of stenosed region, magnitudes of relative residence time and transverse WSS in the proximal part of the lesion were the key factors independently associated with plaque location. This suggested that plaque formation was associated with local flow pattern; and tortuosity, proximal-specific hemodynamics were significantly associated with plaque location in the carotid bulb.

View Presentation Video

Keywords: Vessel Wall, Atherosclerosis

3D MR vessel wall imaging (VWI) is a non-invasive imaging modality for directly assessing intracranial arterial wall diseases. A typical intracranial VWI protocol requires 6-12 minutes per scan to obtain adequate spatial coverage and resolution. Such a long scan time hinders widespread use of VWI in clinical settings. We have developed a multi-channel application-ready intracranial vessel-dedicated CAscaded Multi-level WAvelet REfine (CAMWARE) network that enables a VWI scan within 4 minutes. The proposed network achieved significant improvement in vessel wall delination over conventional compressed sensing reconstruction.

View Presentation Video

Jiayu Xiao¹, Yang Chen¹, Xin Liu², Zhehao Hu¹, Debiao Li³, Anthony Christodoulou³, Parveen Garg⁴, Michael Fong⁴, Alison Wilcox⁴, Qi Yang², and Zhaoyang Fan^1,5,6
1Radiology, Keck School of Medicine of USC, Los Angeles, CA, United States, ²Beijing Chaoyang Hospital, Beijing, China, ³Cedars-Sinai Medical Center, Los Angeles, CA, United States, ⁴Cardiology, Keck School of Medicine of USC, Los Angeles, CA, United States, ⁵Radiation Oncology, Keck School of Medicine of USC, Los Angeles, CA, United States, ⁶Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States

Keywords: Myocardium, Cardiomyopathy

Cardiovascular diseases are common causes of mortality and morbidity globally. An MR MultiTasking based 3D Multi-dimensional Assessment of Cardiovascular System (MT-MACS) technique has recently been developed to provide multi-contrast, cardiac phase-resolved imaging of the whole heart and thoracic aorta in a single scan without the need for ECG triggering or respiratory navigation. We aimed to assess the performance of MT-MACS in patients with suspicious cardiovascular diseases. We demonstrated the feasibility of using MT-MACS in a routine clinical setting. More importantly, it achieved good image quality in most patients with almost perfect inter-reader agreement and diagnostic accuracy.

View Presentation Video

Keywords: Vessels, Blood vessels

Relaxation-Enhanced Angiography without Contrast and Triggering (REACT) is a novel flow-independent MR angiography technique without cardiac triggering, breath holding and contrast agent injection and has promising results to show robust blood-to-tissue contrast over multiple anatomies. This study aims to investigate the feasibility of REACT for evaluation iliac vein compression syndrome in comparison with catheter angiography. Results showed that with comparable image quality to catheter angiography and high sensitivity and specificity for the detection of stenosis, REACT was proven to be a clinically applicable method for assessing iliac vein compression syndrome.

View Presentation Video

Victor de Villedon de Naide¹, Indra Ribal¹, Pauline Gut^1,2, Valéry Ozenne¹, Géraldine Montier³, Jean-David Maes³, Thibault Boullé³, Guillaume Delclaux³, Aurélien Maillot¹, Soumaya Sridi³, Bruno Quesson¹, Matthias Stuber^1,2,4, Hubert Cochet^1,3, and Aurélien Bustin^1,2,3
1IHU LIRYC, Electrophysiology and Heart Modeling Institute, Université de Bordeaux – INSERM U1045, Avenue du Haut Lévêque, 33604, Pessac, France, Bordeaux, France, ²Department of Diagnostic and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland, Lausanne, Switzerland, ³Department of Cardiovascular Imaging, Hôpital Cardiologique du Haut-Lévêque, CHU de Bordeaux, Avenue de Magellan, 33604 Pessac, France, Bordeaux, France, ⁴CIBM Center for Biomedical Imaging, Lausanne, Switzerland, Lausanne, Switzerland

Keywords: Heart, Data Processing, late gadolinium enhancement, black-blood, TI scout

Phase-sensitive inversion recovery is the reference imaging technique for the assessment of myocardial scars. Despite its ability to provide excellent contrast between healthy and scar tissue, small subendocardial scars can be challenging to detect due to poor scar-to-blood contrast. Joint bright- and black-blood late gadolinium enhancement techniques have been developed to provide both scar and anatomy information. Black-blood contrast is obtained after manual selection of an optimal inversion time (TI). This often results in uncertainties, variability, increased workload, and operator-dependency. In this work, we propose a method exploiting artificial intelligence to fully automate TI selection for more robust cardiac imaging.

Priya Jagia¹, Mansi Verma², and Sanjeev Kumar^3
1Dept of cardiovascular radiology and Endovascular interventions, All India institute of medical sciences, Delhi, India, ²Dept of cardiovascular radiology and Endovascular interventions, All India institute of medical sciences, Delhi, Delhi, India, ³Dept of Cardiovascular radiology and Endovascular interventions, All India institute of medical sciences, Delhi, Delhi, India

Keywords: Heart, Lung, Heart failure

The present study sought to determine whether CMR-derived lung water density (LWD) measurement in pulmonary congestion has prognostic relevance in predicting adverse cardiovascular outcomes in patients with heart failure. The primary endpoint was all-cause mortality or HF-related hospitalization within 6 months from CMR.

It concluded -

1.      The mean lung water density was significantly higher in heart failure patients compared to healthy controls.

2.      Patients with “wet lungs” i.e., lung water density >18.1%, had higher incidence of adverse cardiovascular outcomes compared to patients with “dry lungs”.

3.         Lung water density was an independent predictor of adverse cardiovascular outcomes

Jens Wetzl¹, Seung Su Yoon¹, Michaela Schmidt¹, Alexander Haenel², Alexandra-Bianca Weißgerber², Jörg Barkhausen², and Alex Frydrychowicz^2
1Siemens Healthcare GmbH, Erlangen, Germany, ²Klinik für Radiologie und Nuklearmedizin, Universitätsklinikum Schleswig-Holstein Campus Lübeck, Lübeck, Germany

Keywords: Machine Learning/Artificial Intelligence, Cardiovascular, Workflow

We propose an Artificial Intelligence-based single-click cardiac MR exam to support technicians and increase standardization and repeatability of cardiac exams, which we evaluate in a clinical setting with 44 patients. Automations include setting of the isocenter position, slice planning in standard and cardiac orientations, adjustment volume and inversion time. Clinical sequences that can be acquired without manual planning include CINE, STIR, T1 mapping, 3D MRA and LGE. 91% (n=40) of the acquisitions could be completed without manual operator intervention, with the majority (n=3) of failed cases caused by abnormal heart geometries leading to inadequate slice planning.

View Presentation Video

Keywords: Flow, Valves

4D Flow MRI can identify aortic regions exposed to high wall shear stress (WSS) compared to age and sex-matched controls. This concept, known as WSS ‘heatmaps’, has recently shown potential to improve risk stratification in patients with bicuspid aortic valve (BAV). We examined the reproducibility of heatmaps in a cohort of 20 stable BAV patients with five consecutive 4D flow MRI scans and found no significant change over time. In addition, we found high reproducibility of WSS patterns and regions of elevated WSS across scans. Our findings, therefore, suggest that heatmaps can serve as a robust BAV risk measure.

View Presentation Video

Xiaorui Xiang¹, Xiaoqiang Lin², and Shihua Zhao^1
1Fuwai Hospital and National Center for Cardiovascular Diseases, Beijing, China, ²Union Hospital of Fujian Medical University, Fujian, China

Keywords: Cardiomyopathy, Cardiomyopathy

Risk evaluation for patients with NIDCM remains an important public health challenging, and new techniques and strategies are expected to be used to prevent cardiac death. This study was designed to develop and validate a novel nomogram score to predict outcomes in patients with NIDCM over a long follow-up time period.