Biomedical Engineering and Bioengineering Commons^™

Application Of Deep Learning For Medical Sciences And Epidemiology Data Analysis And Diagnostic Modeling, Somenath Chakraborty

Dissertations

Machine Learning and Artificial Intelligence have made significant progress concurrent with new advancements in hardware and software technologies. Deep learning methods heavily utilize parallel computing and Graphical Processing Units(GPU). It is already used in many applications ranging from image classification, object detection, segmentation, cyber security problems and others. Deep Learning is emerging as a viable choice in dealing with today’s real-time medical problems. We need new methods and technologies in the field of Medical Science and Epidemiology for detecting and diagnosing emerging threats from new viruses such as COVID-19. The use of Artificial Intelligence in these domains is becoming more …

Machine Learning Approaches For Lung Cancer Diagnosis., Ahmed Mahmoud Ahmed Shaffie

Electronic Theses and Dissertations

The enormity of changes and development in the field of medical imaging technology is hard to fathom, as it does not just represent the technique and process of constructing visual representations of the body from inside for medical analysis and to reveal the internal structure of different organs under the skin, but also it provides a noninvasive way for diagnosis of various disease and suggest an efficient ways to treat them. While data surrounding all of our lives are stored and collected to be ready for analysis by data scientists, medical images are considered a rich source that could provide …

Incorporating Cardiac Substructures Into Radiation Therapy For Improved Cardiac Sparing, Eric Daniel Morris

Wayne State University Dissertations

Growing evidence suggests that radiation therapy (RT) doses to the heart and cardiac substructures (CS) are strongly linked to cardiac toxicities, though only the heart is considered clinically. This work aimed to utilize the superior soft-tissue contrast of magnetic resonance (MR) to segment CS, quantify uncertainties in their position, assess their effect on treatment planning and an MR-guided environment.

Automatic substructure segmentation of 12 CS was completed using a novel hybrid MR/computed tomography (CT) atlas method and was improved upon using a 3-dimensional neural network (U-Net) from deep learning. Intra-fraction motion due to respiration was then quantified. The inter-fraction setup …

Motion Artifact Evaluation Of Coronary Ct Angiography Images, Hongfeng Ma

Dissertations (1934 -)

The objective of this dissertation was to develop and validate an automated algorithm to quantify motion artifact level on coronary CT angiography (CCTA) images. Unlike existing motion artifact reduction techniques that evaluate the relative level of motion artifacts within one exam, this dissertation aims to quantify the absolute level of motion artifacts across exams from varying patients. The ability to quantify absolute motion artifact level enables several potential applications, for example, assessing and comparing two motion artifact reduction techniques. This dissertation includes three specific aims. Aim 1 investigated the absolute motion artifact quantification effectiveness of six motion artifact metrics using …

A Software Application For Cardiac-Gated Computerized Tomography Scanning, Stephen Caldwell, Trevor Engelsman

Williams Honors College, Honors Research Projects

Computerized tomography (CT) scans are a common clinical imaging procedure used worldwide. Operating in the X-Ray spectrum, these machines rotate scanners around a stationary body in order to compile two-dimensional images into a unified three-dimensional image. With adjustment to scan frequency and intensity, internal features such as muscles, organs, and tendons can easily be viewed. However, the heart has long evaded CT use due to its near-constant motion. Recently, cardiac-gated scans have entered the market as a technique to image the heart at a specific moment in time when it is nearly still - the quiescent period. Occurring during rapid …

The Effects Of Organ-Based Tube Current Modulation On Radiation Dose And Image Quality In Computed Tomography Imaging, Diksha Gandhi

Master's Theses (2009 -)

The purpose of this thesis was to quantify dose and noise performance of organ-dose-based tube current modulation (ODM) through experimental studies with an anthropomorphic phantom and simulations with a voxelized phantom library. Tube current modulation is a dose reduction technique that modulates radiation dose in angular and/or slice directions based on patient attenuation. ODM technique proposed by GE Healthcare further reduces tube current for anterior source positions, without increasing current for posterior positions. Axial CT scans at 120 kV were performed on head and chest phantoms (Rando Alderson Research Laboratories, Stanford, CA) on an ODM-equipped scanner (Optima CT660, GE Healthcare, …

The Design And Validation Of A Computational Model Of The Human Wrist Joint, Afsarul Mir

Theses and Dissertations

Advancements in computational capabilities have allowed researchers to turn towards modeling as an efficient tool to replicate and predict outcomes of complex systems. Computational models of the musculoskeletal system have gone through various iterations with early versions employing dramatic simplifications. In this work, a three-dimensional computational model of the wrist joint was developed. It accurately recreated the skeletal structures of the hand and wrist and represented the constraints imposed by soft tissue structures like ligaments, tendons, and other surrounding tissues. It was developed to function as a tool to investigate the biomechanical contributions of structures and the kinematic response of …

Reducing The Radiation Dose To Women Receiving Cardiac Ct Scans, Michael Hoppe

Master's Theses (2009 -)

This thesis aims to quantify the reduction in radiation dose deposited in glandular breast tissue achieved by using tilted gantry acquisition during cardiac CT scans. Previous work by Halpern et al. suggested using tilted acquisition parallel to the long axis of the patient’s heart. However, for a larger portion of the population this is not feasible due to the design of current scanners (which are limited to maximum tilt angles of 30 degrees). This study investigated the potential dose reduction and image quality effects at commercially available tilt angles between 0-30 degrees through simulation and experimental studies.

Upon IRB approval, …

A Non-Rigid Registration Method For Analyzing Myocardial Wall Motion For Cardiac Ct Images, Elizabeth B. Philps

Master's Theses (2009 -)

Cardiac resynchronization therapy (CRT) has a high percentage of non-responders. Successfully locating the optimal location for CRT lead placement on a priori images can increase efficiency in procedural preparation and execution and could potentially increase the rate of CRT responders.

Registration has been used in the past to assess the motion of medical images. Specifically, one method of non-rigid registration has been utilized to assess the motion of left ventricular MR cardiac images. As CT imaging is often performed as part of resynchronization treatment planning and is a fast and accessible means of imaging, extending this registration method to assessing …

Iterative Methods For The Reconstruction Of Tomographic Images With Unconventional Source-Detector Configurations, Abey Mukkananchery

Theses and Dissertations

X-ray computed tomography (CT) holds a critical role in current medical practice for the evaluation of patients, particularly in the emergency department and intensive care units. Expensive high resolution stationary scanners are available in radiology departments of most hospitals. In many situations however, a small, inexpensive, portable CT unit would be of significant value. Several mobile or miniature CT scanners are available, but none of these systems have the range, flexibility or overall physical characteristics of a truly portable device. The main challenge is the design of a geometry that optimally trades image quality for system size. The goal of …