Engineering Commons^™

Breast Cancer Risk In Women With Breast Bilateral Asymmetry: Machine Learning Based Risk Analysis And Mitigation Through Developing A Framework For Customized Bra Design, Xi Feng

Electronic Thesis and Dissertation Repository

Breast cancer is the most prevalent form of cancer globally, accounting for 12.5% of all new cases annually. Research has found a significant correlation between breast bilateral asymmetry and an increased risk of cancer, with women diagnosed with breast cancer having higher levels of bilateral asymmetrical breast volume. Unfortunately, 87% of women with breast asymmetry lack adequate tools for assessing their cancer risk. Early screening using bilateral asymmetry to predict a woman's long-term risk of breast cancer can help physicians make informed decisions about whether to recommend sequential imaging and the frequency of screening. Another important factor in understanding the …

Machine Learning Classifiers For Chronic Obstructive Pulmonary Disease Assessment Using Lung Ct Data., Halimah Alsurayhi

Electronic Thesis and Dissertation Repository

Chronic Obstructive Pulmonary Disease (COPD) is a condition characterized by persistent inflammation and airflow blockages in the lungs, contributing to a significant number of deaths globally each year. To guide tailored treatment strategies and mitigate future risks, the Global Initiative for Chronic Obstructive Lung Disease (GOLD) employs a multifaceted assessment system of COPD severity, considering patient's lung function, symptoms, and exacerbation history. COPD staging systems, such as the high-resolution eight-stage COPD system and the GOLD 2023 three staging systems, have been later developed based on these factors. Lung Computed Tomography (CT) is becoming increasingly crucial in investigating COPD as it …

A Novel Method For Determining The Inherent Capabilities Of Computer And Robotic-Assisted Total Knee Arthroplasty Devices, Delaney R.G. Stevens

Electronic Thesis and Dissertation Repository

This thesis presents a method for evaluating and comparing assistive total knee arthroplasty (TKA) devices while controlling surgeon landmarking variability. To achieve consistent landmark selection by surgeons during TKA procedures, the method uses identical 3D-printed knees with indented landmarks. This method was used to compare a robotic and computer-assisted TKA device on three metrics: measurement accuracy, alignment accuracy, and cut-surface uniformity. Although both devices had considerable sagittal plane measurement errors, the robotic device had better measurement and alignment accuracy than the computer-assisted device. Furthermore, the robotic device's measuring error compensated for cutting errors, but the computer-assisted device's compounded them. However, …

Evaluating Eeg–Emg Fusion-Based Classification As A Method For Improving Control Of Wearable Robotic Devices For Upper-Limb Rehabilitation, Jacob G. Tryon

Electronic Thesis and Dissertation Repository

Musculoskeletal disorders are the biggest cause of disability worldwide, and wearable mechatronic rehabilitation devices have been proposed for treatment. However, before widespread adoption, improvements in user control and system adaptability are required. User intention should be detected intuitively, and user-induced changes in system dynamics should be unobtrusively identified and corrected. Developments often focus on model-dependent nonlinear control theory, which is challenging to implement for wearable devices.

One alternative is to incorporate bioelectrical signal-based machine learning into the system, allowing for simpler controller designs to be augmented by supplemental brain (electroencephalography/EEG) and muscle (electromyography/EMG) information. To extract user intention better, sensor …

Using Machine Learning To Assist Auditory Processing Evaluation, Hasitha Wimalarathna, Sangamanatha Veeranna, Minh Vu Duong, Chris Allan Prof, Sumit K. Agrawal, Prudence Allen, Jagath Samarabandu, Hanif M. Ladak

Electrical and Computer Engineering Publications

Introduction: Approximately 0.2–5% of school-age children complain of listening difficulties in the absence of hearing loss. These children are often referred to an audiologist for an auditory processing disorder (APD) assessment. Adequate experience and training is necessary to arrive at an accurate diagnosis due to the heterogeneity of the disorder.

Objectives: The main goal of the study was to determine if machine learning (ML) can be used to analyze data from the APD clinical test battery to accurately categorize children with suspected APD into clinical sub-groups, similar to expert labels.

Methods: The study retrospectively collected data from 134 children referred …

Design And Evaluation Of Fabric Cooling Channels For Twisted Coiled Actuators, Alex Lizotte

Electronic Thesis and Dissertation Repository

Twisted coiled actuators (TCAs) are biomimetic and inexpensive artificial muscles. To enable their integration into soft robotics, a novel cooling apparatus was designed, consisting of a fabric channel to house the TCA and a miniature air pump for forced convection. The channel was designed to be lightweight, flexible, and easy to integrate into a soft wearable robotic device. The effect that the channel dimensions had on TCA performance (cooling time, heating time, and stroke) was investigated by testing combinations of three widths (6, 8, and 10 mm) and three heights (4, 6, and 8 mm). In general, as the channel …

Modelling And Evaluation Of Piezoelectric Actuators For Wearable Neck Rehabilitation Devices, Shaemus D. Tracey

Electronic Thesis and Dissertation Repository

Neck pain is the most common neck musculoskeletal disorder, and the fourth leading cause of healthy years lost due to disability in the world. Due to the need of hands-on physical therapy and Canada’s aging population, access to treatment will become highly constrained. Wearable devices that allow at-home rehabilitation address this future limitation. However, few have emerged from the laboratory setting because they are limited by the use of conventional actuators. An overlooked type of actuation technology is that of piezoelectric actuators, more specifically, travelling wave ultrasonic motors (TWUM).

In this work, a clear procedure that outlines how the required …

The Development Of A Motion Sensing Device For Use In A Home Setting, Jaspreet K. Kalsi

Electronic Thesis and Dissertation Repository

Parkinson's disease (PD) is the second most prevalent neurodegenerative disease, with over 10 million individuals diagnosed with PD world-wide. The most common symptom characterized by PD is tremor. Tremor is an involuntary oscillatory motion that most prominently occurs in upper limb, specifically in the hand and wrist that has a measurable frequency and amplitude. This thesis aims to evaluate the usability and functionality of a tremor sensing device designed to collect quantitative data on individuals with PD. The designed device uses 23 commercially-available inertial measuring units (IMUs) located between 21 joints: distal interphalangeal (DIP) joints, proximal interphalangeal (PIP) joints, Interphalangeal …

Automated Segmentation Of The Inner Ear And Round Window In Computed Tomography Scans Using Convolutional Neural Networks, Kyle A. Rioux

Electronic Thesis and Dissertation Repository

Computed tomography (CT) scans are acquired prior to cochlear implant (CI) surgery. Three-dimensional segmentations of the inner ear (IE) and round window (RW) based on clinical CTs can improve the CI procedure. Software pipelines are presented here which employ convolutional neural networks to automatically segment the IE and RW. The first pipeline produces high resolution segmentations of the IE and RW in tightly cropped CTs. Mean IE Dice score and RW centroid error were 0.88, 0.57mm and 0.93, 0.18mm in implanted and non-implanted samples, respectively. The second pipeline automatically segments the IE in large field of view CTs of any …

Effect Of Levodopa On Eeg Connectivity In Parkinson's Patients, Sepehr Torab Parhiz

Electronic Thesis and Dissertation Repository

Levodopa is a dopamine replacement medication administered to patients with Parkinson’s disease (PD) to alleviate their motor symptoms. However, its long-term use can cause adverse side effects, including involuntary motor movements. We studied 16 PD patients before and after taking Levodopa based on resting-state electroencephalography (EEG) recordings to determine how Levodopa affects the functional connectivity of their brain networks. We used several metrics from graph theory, in particular the minimum spanning tree (MST) metric, and analyzed how they change after subjects take Levodopa. We observed significant changes in the lower alpha band toward a more path-like and less globally efficient …

Liam Briggs 2021 Usri - Audio Testing Device, Liam Briggs

Undergraduate Student Research Internships Conference

Portable and cost-effective hearing testing device with a UI that can be accessed on a remote web server.

Evaluating Algorithms Used For Fetal Brain Scan Segmentation, Connor Stewart Burgess

Undergraduate Student Research Internships Conference

The goal for this project was to successfully segment a fetal brain scan (fetal scan) using the algorithms provided by the program Slicer3D. To better understand the hurdles that arose when segmenting a fetal scan, we first look at the segmentation of an adult brain scan. This will allow us to see the straightforward nature of a brain segmentation when a high quality, high resolution volume with distinct structures is available. After examining the adult brain scan, attention will be moved to the segmentation of the fetal scan, where we’ll first look at the algorithms used and methods followed. Finally …

Web Application – Utilizing A Pose Estimation And Augmented Reality Api For Hand Telerehabilitation, Herbert Shin

Undergraduate Student Research Internships Conference

No abstract provided.

Development Of A Wireless Telemetry Load And Displacement Sensor For Orthopaedic Applications, William Anderson

Electronic Thesis and Dissertation Repository

Due to sensor size and supporting circuitry, in vivo load and deformation measurements are currently restricted to applications within larger orthopaedic implants. The objective of this thesis is to repurpose a commercially available low-power, miniature, wireless, telemetric, tire-pressure sensor (FXTH87) to measure load and deformation for future use in biomechanical applications. The capacitive transducer membrane of the FXTH87 was modified, and a relationship was reported between applied compressive deformation and sensor signal value. The sensor package was embedded within a deformable enclosure to illustrate potential applications of the sensor for monitoring load. Finite element analysis was an effective tool to …

Snapshot Three-Dimensional Surface Imaging With Multispectral Fringe Projection Profilometry, Parsa Omidi

Electronic Thesis and Dissertation Repository

Fringe Projection Profilometry (FPP) is a popular method for non-contact optical surface measurements, including motion tracking. The technique derives 3D surface maps from phase maps estimated from the distortions of fringe patterns projected onto the surface of an object. Estimation of phase maps is commonly performed with spatial phase retrieval algorithms that use a series of complex data processing stages. Researchers must have advanced data analysis skills to process FPP data due to a lack of availability of simple research-oriented software tools. Chapter 2 describes a comprehensive FPP software tool called PhaseWare^TM that allows novice to experienced users to …

Deep Reinforcement Learning In Medical Object Detection And Segmentation, Dong Zhang

Electronic Thesis and Dissertation Repository

Medical object detection and segmentation are crucial pre-processing steps in the clinical workflow for diagnosis and therapy planning. Although deep learning methods have achieved considerable performance in this field, they impose several shortcomings, such as computational limitations, sub-optimal parameter optimization, and weak generalization. Deep reinforcement learning as the newest artificial intelligence algorithm has great potential to address the limitation of traditional deep learning methods, as well as obtaining accurate detection and segmentation results. Deep reinforcement learning has a cognitive-like process to propose the area of desirable objects, thereby facilitating accurate object detection and segmentation. In this thesis, we deploy deep …

Automated Segmentation Of Temporal Bone Structures, Daniel Allen

Electronic Thesis and Dissertation Repository

Mastoidectomy is a challenging surgical procedure that is difficult to perform and practice. As supplementation to current training techniques, surgical simulators have been developed with the ability to visualize and operate on temporal bone anatomy. Medical image segmentation is done to create three-dimensional models of anatomical structures for simulation. Manual segmentation is an accurate but time-consuming process that requires an expert to label each structure on images. An automatic method for segmentation would allow for more practical model creation. The objective of this work was to create an automated segmentation algorithm for structures of the temporal bone relevant to mastoidectomy. …

A Heterogeneous Patient-Specific Biomechanical Model Of The Lung For Tumor Motion Compensation And Effective Lung Radiation Therapy Planning, Parya Jafari

Electronic Thesis and Dissertation Repository

Radiation therapy is a main component of treatment for many lung cancer patients. However, the respiratory motion can cause inaccuracies in radiation delivery that can lead to treatment complications. In addition, the radiation-induced damage to healthy tissue limits the effectiveness of radiation treatment. Motion management methods have been developed to increase the accuracy of radiation delivery, and functional avoidance treatment planning has emerged to help reduce the chances of radiation-induced toxicity. In this work, we have developed biomechanical model-based techniques for tumor motion estimation, as well as lung functional imaging. The proposed biomechanical model accurately estimates lung and tumor motion/deformation …

Multi-Atlas Segmentation Of The Facial Nerve, Bradley M. Gare

Electronic Thesis and Dissertation Repository

Medical image segmentation is an important step to identify the shape and position of patient anatomy prior to surgical simulation, surgical rehearsal, and surgical planning. It is crucial that the facial nerve (FN) is segmented accurately as damage to this nerve can severely impact facial expression, speech, and taste. Manual segmentation provides accurate results but is time-consuming and labor-intensive; semi-automatic methods of segmentation are more feasible in a clinical setting and can provide accurate results with minimal user involvement. The objective of this work was to create a novel, open-source, multi-atlas based segmentation algorithm of the entire FN requiring minimal …

Intraoperative Localization Of Subthalamic Nucleus During Deep Brain Stimulation Surgery Using Machine Learning Algorithms, Mahsa Khosravi

Electronic Thesis and Dissertation Repository

This thesis presents a novel technique for localizing the Subthalamic Nucleus (STN) during Deep Brain Stimulation (DBS) surgery. DBS is an accepted treatment for individuals living with Parkinson's Disease (PD). This surgery involves implantation of a permanent electrode inside the STN to deliver electrical current. The STN is a small grey matter structure within the brain, which makes accurate placement a challenging task for the surgical team. Prior to placement of the permanent electrode, intraoperative microelectrode recordings (MERs) of neural activity are used to localize the STN. The placement of the permanent electrode and the success of the stimulation therapy …

A Biomechanical And Physiological Signal Monitoring System For Four Degrees Of Upper Limb Movement, Allison R. Goldman

Electronic Thesis and Dissertation Repository

A lack of adherence to prescribed physical therapy regimens in improper healing results in poor outcomes for those affected by musculoskeletal disorders (MSDs) of the upper limb. Societal and psychological barriers to proper adherence can be addressed through the system presented in this work consisting of the following components: an ambulatory biosignal acquisition sleeve, an electromyography (EMG) based motion repetition detection algorithm, and the design of a compatible capacitive EMG acquisition module.

The biosignal acquisition sleeve was untethered, unobtrusive to motion, contained only modular components, and collected biomechanical and physiological sensor data to form full motion profiles of the following …

Development Of Image-Based Surgical Planning Software For Bone-Conduction Implants, Carlos D. Salgado

Electronic Thesis and Dissertation Repository

The BONEBRIDGE bone-conduction device is used to treat conductive and mixed hearing losses. The size of its floating mass transducer (FMT) can preclude implantation in certain anatomies, necessitating comprehensive surgical planning. Current techniques are time consuming and difficult to transfer to the operating room. The objective of this thesis was to develop software for calculating skull thickness to the dura mater to find locations for the FMT and to the first air cells which guarantee sufficient bone for the implant screws to grasp. Temporal bone computed tomography (CT) images were segmented and processed and custom Matlab code was written to …

Development Of An Emg-Based Muscle Health Model For Elbow Trauma Patients, Emma Farago

Electronic Thesis and Dissertation Repository

Musculoskeletal (MSK) conditions are a leading cause of pain and disability worldwide. Rehabilitation is critical for recovery from these conditions and for the prevention of long-term disability. Robot-assisted therapy has been demonstrated to provide improvements to stroke rehabilitation in terms of efficiency and patient adherence. However, there are no wearable robot-assisted solutions for patients with MSK injuries. One of the limiting factors is the lack of appropriate models that allow the use of biosignals as an interface input. Furthermore, there are no models to discern the health of MSK patients as they progress through their therapy.

This thesis describes the …

Augmented Reality Ultrasound Guidance In Anesthesiology, Golafsoun Ameri

Electronic Thesis and Dissertation Repository

Real-time ultrasound has become a mainstay in many image-guided interventions and increasingly popular in several percutaneous procedures in anesthesiology. One of the main constraints of ultrasound-guided needle interventions is identifying and distinguishing the needle tip from needle shaft in the image. Augmented reality (AR) environments have been employed to address challenges surrounding surgical tool visualization, navigation, and positioning in many image-guided interventions. The motivation behind this work was to explore the feasibility and utility of such visualization techniques in anesthesiology to address some of the specific limitations of ultrasound-guided needle interventions. This thesis brings together the goals, guidelines, and best …

Optimal Decomposition Strategy For Tree Edit Distance, Shaofeng Jiang

Electronic Thesis and Dissertation Repository

An ordered labeled tree is a tree where the left-to-right order among siblings is significant. Given two ordered labeled trees, the edit distance between them is the minimum cost edit operations that convert one tree to the other.

In this thesis, we present an algorithm for the tree edit distance problem by using the optimal tree decomposition strategy. By combining the vertical compression of trees with optimal decomposition we can significantly reduce the running time of the algorithm. We compare our method with other methods both theoretically and experimentally. The test results show that our strategies on compressed trees are …

Skills Assessment In Arthroscopic Surgery By Processing Kinematic, Force, And Bio-Signal Data, Behnaz Poursartip

Electronic Thesis and Dissertation Repository

Arthroscopic surgery is a type of Minimally Invasive Surgery (MIS) performed in human joints, which can be used for diagnostic or treatment purposes. The nature of this type of surgery makes it such that surgeons require extensive training to become experts at performing surgical tasks in tight environments and with reduced force feedback. MIS increases the possibility of erroneous actions, which could result in injury to the patient. Many of these injuries can be prevented by implementing appropriate training and skills assessment methods.

Various performance methods, including Global Rating Scales and technical measures, have been proposed in the literature. However, …

Design And Evaluation Of Neurosurgical Training Simulator, Trinette L. Wright

Electronic Thesis and Dissertation Repository

Surgical simulators are becoming more important in surgical training. Consumer smartphone technology has improved to allow deployment of VR applications and are now being targeted for medical training simulators. A surgical simulator has been designed using a smartphone, Google cardboard 3D glasses, and the Leap Motion (LM) hand controller. Two expert and 16 novice users were tasked with completing the same pointing tasks using both the LM and the medical simulator NeuroTouch. The novice users had an accuracy of 0.2717 bits (SD 0.3899) and the experts had an accuracy of 0.0925 bits (SD 0.1210) while using the NeuroTouch. Novices and …

Force Sensing Surgical Grasper With Folding Capacitive Sensor, Dave Bp Tripp

Electronic Thesis and Dissertation Repository

Minimally-invasive surgery (MIS) has brought many benefits to the operating room, however, MIS procedures result in an absence of force feedback, and surgeons cannot as accurately feel the tissue they are working on, or the forces that they are applying. One of the barriers to introducing MIS instruments with force feedback systems is the high cost of manufacturing and assembly. Instruments must also be sterilized before every use, a process that can destroy embedded sensing systems. An instrument that can be disposed of after a single use and produced in bulk at a low cost is desirable. Printed circuit micro-electro-mechanical …

Pulmonary Image Segmentation And Registration Algorithms: Towards Regional Evaluation Of Obstructive Lung Disease, Fumin Guo

Electronic Thesis and Dissertation Repository

Pulmonary imaging, including pulmonary magnetic resonance imaging (MRI) and computed tomography (CT), provides a way to sensitively and regionally measure spatially heterogeneous lung structural-functional abnormalities. These unique imaging biomarkers offer the potential for better understanding pulmonary disease mechanisms, monitoring disease progression and response to therapy, and developing novel treatments for improved patient care. To generate these regional lung structure-function measurements and enable broad clinical applications of quantitative pulmonary MRI and CT biomarkers, as a first step, accurate, reproducible and rapid lung segmentation and registration methods are required. In this regard, we first developed a 1H MRI lung segmentation algorithm that …

Interactive Visualization Of Multimodal Brain Connectivity: Applications In Clinical And Cognitive Neuroscience, Saeed Mahdizadeh Bakhshmand

Electronic Thesis and Dissertation Repository

Magnetic resonance imaging (MRI) has become a readily available prognostic and diagnostic method, providing invaluable information for the clinical treatment of neurological diseases. Multimodal neuroimaging allows integration of complementary data from various aspects such as functional and anatomical properties; thus, it has the potential to overcome the limitations of each individual modality. Specifically, functional and diffusion MRI are two non-invasive neuroimaging techniques customized to capture brain activity and microstructural properties, respectively. Data from these two modalities is inherently complex, and interactive visualization can assist with data comprehension.

The current thesis presents the design, development, and validation of visualization and computation …