A5084960775- Advanced MRI Techniques and Applications
- Cardiac pacing and defibrillation studies
- Radiomics and Machine Learning in Medical Imaging
- Radiation Dose and Imaging
- Advanced X-ray and CT Imaging
- Cardiac Imaging and Diagnostics
- Medical Imaging Techniques and Applications
- Artificial Intelligence in Healthcare and Education
- Neurological disorders and treatments
- Cardiovascular Function and Risk Factors
- AI in cancer detection
- Health Systems, Economic Evaluations, Quality of Life
- Machine Learning in Healthcare
- Digital Radiography and Breast Imaging
- Statistical Methods in Clinical Trials
- Cardiac Arrhythmias and Treatments
- Radiology practices and education
- Healthcare Operations and Scheduling Optimization
- Statistical Methods and Inference
- Fault Detection and Control Systems
- Advanced Statistical Process Monitoring
- Cardiomyopathy and Myosin Studies
- Atomic and Subatomic Physics Research
- MRI in cancer diagnosis
- Traumatic Brain Injury and Neurovascular Disturbances
Center for Devices and Radiological Health
2014-2024
United States Food and Drug Administration
2014-2024
Office of Science
2023-2024
Food and Drug Administration
2015-2023
Center for Drug Evaluation and Research
2021
Emory University
2005-2013
Georgia Institute of Technology
2006-2009
Emory University Hospital
2008
Emory and Henry College
2008
Abstract Purpose To compare longitudinal myocardial velocity and time to peak obtained with magnetic resonance phase mapping (MR‐PVM) tissue Doppler imaging (TDI), assess the reproducibility of each method. Materials Methods Longitudinal was measured by TDI MR‐PVM in 10 normal volunteers patients dyssynchrony. The assessed on repeated measurements volunteers. Results MR correlated well (r = 0.86) both subjects However, velocities consistently exceeded TDI. agreed strongly measuring 0.97)....
The study protocol was HIPAA compliant and institutional review board approved. Informed consent obtained from all participants. purpose of the to prospectively validate capability navigator-echo-gated phase-contrast magnetic resonance (MR) imaging for measurement myocardial velocities in a phantom use MR sequence measure three-directional velocity myocardium vivo volunteers patients scheduled cardiac resynchronization therapy. An excellent correlation between measured true motion (R = 0.90...
Abstract A key challenge for the development and deployment of artificial intelligence (AI) solutions in radiology is solving associated data limitations. Obtaining sufficient representative patient datasets with appropriate annotations may be burdensome due to high acquisition cost, safety limitations, privacy restrictions, or low disease prevalence rates. In silico offers a number potential advantages data, such as diminished harm, reduced simplified acquisition, scalability, improved...
Abstract Purpose To develop a method for computing radial strain (ε) and rate (SR) from phase contrast magnetic resonance (PCMR) myocardial tissue velocity data. Materials Methods PCMR maps were acquired at basal mid‐short‐axis slices in the myocardium 10 healthy volunteers. An algorithm SR data was developed. values compared to computed independently contours drawn on cine steady‐state free procession (SSFP) images. Peak endocardial epicardial compared. Results Excellent agreement observed...
Patients with heart block have conventionally received a pacemaker that stimulates the right ventricular apex (RVA) to restore rate control. While RVA pacing has been shown create systolic dyssynchrony acutely, can also occur in diastole. The effects of acute on diastolic synchrony not investigated. acutely impairs function by increasing time constant relaxation, decreasing peak lengthening and negative dP/dt. We therefore hypothesized would cause addition creating dyssynchrony.Fourteen...
Purpose To develop a robust method to assess regional mechanical dyssynchrony from cine short‐axis MR images. Cardiac resynchronization therapy (CRT) is an effective treatment for patients with heart failure and evidence of left‐ventricular (LV) dyssynchrony. Patient response CRT greatest when the LV pacing lead placed in most dyssynchronous segment. Existing techniques assessing require difficult acquisition and/or postprocessing. Our goal was widely applicable Materials Methods Using...
To generate evidence regarding the safety and efficacy of artificial intelligence (AI) enabled medical devices, AI models need to be evaluated on a diverse population patient cases, some which may not readily available. We propose an evaluation approach for testing imaging that relies in silico pipelines stochastic digital human anatomy (in object space) with without pathology are imaged using replica acquisition system realistic synthetic image datasets. Here, we release M-SYNTH, dataset...
Abstract Machine learning (ML) models often fail with data that deviates from their training distribution. This is a significant concern for ML-enabled devices as drift may lead to unexpected performance. work introduces new framework out of distribution (OOD) detection and monitoring combines ML geometric methods statistical process control (SPC). We investigated different design choices, including extracting feature representations quantification OOD in individual images an approach input...
Abstract Purpose To apply cross‐correlation delay (XCD) analysis to myocardial phase contrast magnetic resonance (PCMR) tissue velocity data and compare XCD three established “time‐to‐peak” dyssynchrony parameters. Materials Methods Myocardial was acquired using PCMR in 10 healthy volunteers (negative controls) heart failure patients who met criteria for cardiac resynchronization therapy (positive controls). All parameters were computed from curves. Sensitivity, specificity, receiver...