Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network

Open Access. Powered by Scholars. Published by Universities.®

Articles 1 - 6 of 6

Full-Text Articles in Entire DC Network

Fast Magnetic Resonance Image Reconstruction With Deep Learning Using An Efficientnet Encoder, Tahsin Rahman Aug 2021

Fast Magnetic Resonance Image Reconstruction With Deep Learning Using An Efficientnet Encoder, Tahsin Rahman

Open Access Theses & Dissertations

This thesis aims to develop an efficient, deep network based method for Magnetic Resonance Imaging (MRI) acceleration through undersampled MR image reconstruction. Deep Neural Networks, particularly Deep Convolutional Networks, have been demonstrated to be highly effective in a wide variety of computer vision tasks, including MRI reconstruction. However, modern highly efficient encoder structures, such as the EfficientNet can potentially reduce reconstruction times further while improving reconstruction quality. To that end, we have developed a multi-channel U-Net MRI reconstruction network which uses an EfficientNet encoder and a custom asymmetric. The network was trained and tested using 5x undersampled multi-channel brain MR …


Measuring Inflammation In The Entire Myocardium In A Canine Model Of Myocardial Infarction With Hybrid Pet/Mri, Benjamin Wilk Jun 2021

Measuring Inflammation In The Entire Myocardium In A Canine Model Of Myocardial Infarction With Hybrid Pet/Mri, Benjamin Wilk

Electronic Thesis and Dissertation Repository

Background: After myocardial infarction (MI), fibrosis and an ongoing dysregulated inflammatory response are associated with adverse cardiac remodeling. Fluorodeoxyglucose (FDG) positron emission tomography (PET) is sensitive to inflammation provided suppression protocols are implemented to restrict the uptake of glucose in myocytes. Magnetic resonance imaging can be used to determine extracellular volume, a surrogate measure of fibrosis. In some cases, patients present with markedly reduced flow in the setting of a large infarct, i.e. microvascular obstruction, restricting the delivery of FDG and contrast agents. To overcome this problem, a constant infusion was explored as an alternative to the clinical standard bolus …


Validity Of Intrinsic Foot Muscle Size Measured By Ultrasound And Mri, Dallin Swanson Jun 2021

Validity Of Intrinsic Foot Muscle Size Measured By Ultrasound And Mri, Dallin Swanson

Undergraduate Honors Theses

Intrinsic foot muscles maintain foot structural integrity and contribute to functional movement, posture and balance. Thus, assessing intrinsic foot muscle size and strength are important. Magnetic resonance imaging (MRI) has been shown to accurately image the individual muscles but is costly and time consuming. Ultrasound (US) imaging may provide an alternative that is less costly and more readily available. The purpose of this study was to investigate the validity and reproducibility of US imaging in measuring intrinsic foot muscle size in comparison to MRI. US and MRI were employed to measure the intrinsic foot muscle size involving 35 participants (females …


Ischemic Stroke Thrombus Characterization Through Quantitative Magnetic Resonance Imaging, Spencer D. Christiansen Apr 2021

Ischemic Stroke Thrombus Characterization Through Quantitative Magnetic Resonance Imaging, Spencer D. Christiansen

Electronic Thesis and Dissertation Repository

Stroke is a pervasive, devastating disease and remains one of the most challenging conditions to treat. In particular, risk of recurrence is dramatically heightened after a primary stroke and requires urgent preventative therapy to effectively mitigate. However, the appropriate preventative therapy depends on the underlying source of the stroke, known as etiology, which is challenging to determine promptly. Current diagnostic tests for determining etiology underwhelm in both sensitivity and specificity, and in as much as 35% of cases etiology is never determined. In ischemic stroke, the composition of the occluding thrombus, specifically its red blood cell (RBC) content, has been …


Assessing Midbrain Abnormalities In Parkinson’S Disease Using Magnetic Resonance Imaging, Kiarash Ghassaban Jan 2021

Assessing Midbrain Abnormalities In Parkinson’S Disease Using Magnetic Resonance Imaging, Kiarash Ghassaban

Wayne State University Dissertations

Diagnosing early-stage Parkinson’s disease (PD) and its manifestations is still a clinical challenge. Previous imaging studies using iron, neuromelanin (NM) and the Nigrosome-1 (N1) measures in the substantia nigra (SN) by themselves have been unable to provide sufficiently high diagnostic performance for these methods to be adopted clinically. In this dissertation, we start by studying idiopathic PD patients at their intermediate stages of the disease to evaluate the role of global and regional iron in the major deep gray matter nuclei. Then, we only focus on the NM complex in the midbrain and how neuronal loss interact with iron overload …


The Theory And Design Of Class E Power Amplifiers For Impulse Excitation In Nuclear Magnetic Resonance, Owen D. Riemer Jan 2021

The Theory And Design Of Class E Power Amplifiers For Impulse Excitation In Nuclear Magnetic Resonance, Owen D. Riemer

Browse all Theses and Dissertations

A new method for analyzing the effectiveness of NMR impulse power amplifiers was developed using a classical linear systems approach to NMR. The method demonstrates a way to compare NMR power amplifiers and outputs. Thermodynamic calculations and the harmonic content of NMR amplifiers is presented to provide a complete description of the NMR power amplifier design problem. A design procedure for class E NMR power amplifiers with a pi-impedance matching network is outlined for matching the amplifier to the transmitter coil. The thesis concludes with the presentation of a 53 MHz power amplifier developed with the procedure. The complete amplifier …