Engineering Commons^™

Deep Learning And Generative Ai Approaches For Automated Diagnosis And Personalized Treatment: Bridging Machine Learning, Medicine, And Biomechanics In Predicting Tissue Mechanics And Biomaterial Properties., Yasin Shokrollahi

Theses and Dissertations

Machine learning, particularly deep neural networks, has demonstrated significant potential in predicting high-dimensional tasks across various domains. This work encompasses a detailed review of Generative AI in healthcare and three studies integrating machine learning with finite element analysis for predicting biomechanical behaviors and properties. Initially, we provide a comprehensive overview of Generative AI applications in healthcare, focusing on Transformers and Denoising Diffusion models and suggesting potential research avenues to address existing challenges.

Subsequently, we addressed soccer-related ocular injuries by combining finite element analysis and machine learning to predict retinal mechanics following a soccer ball hit rapidly. The prediction errors are …

Digital Twins Of The Living Knee: From Measurements To Model, Thor Erik Andreassen

Electronic Theses and Dissertations

Modern medicine has dramatically improved the lives of many. In orthopaedics, robotic surgery has given clinicians superior accuracy when performing interventions over conventional methods. Nevertheless, while these and many other methods are available to ensure treatments are performed successfully, far fewer methods exist to predict the proper treatment option for a given person. Clinicians are forced to categorize individuals, choosing the best treatment on “average.” However, many individuals differ significantly from the “average” person, for which many of these treatments are designed. Going forward, a method of testing, evaluating, and predicting different treatment options' short- and long-term effects on an …

Computational Methodology For Generating Patient-Specific Soft Tissue Representations, Ahilan Anantha Krishnan

Electronic Theses and Dissertations

This dissertation focused on modeling specimen-specific soft tissue structures in the context of joint replacement surgery. The research addressed four key aspects. The first study involved developing a workflow for creating finite element models of the hip capsule to replicate its torque-rotational response. Experimental data from ten cadaveric hips were used to calibrate the models, resulting in improved accuracy and relevance for surgical planning and implant design. The second study tackled the challenge of expediting the calibration of mechanical properties of the hip capsule to match patient-specific laxities. A statistical shape function model was proposed to generate patient-specific finite element …

Analysis Of Gait Parameters And Knee Angles In Ultimate Frisbee Players: Implications For Balance And Injury, Ethan Nikcevich

Master's Theses

Biomechanics research investigating gait and balance of ultimate frisbee players is an unexplored topic. Ultimate requires a wide range of motions that could improve balance and is also a sport prone to frequent injury. This study explores the impact of playing ultimate on gait parameters associated with balance and knee angles associated with joint injury. Gait trials were conducted on 8 ultimate players and 8 control participants between the ages of 18 and 23 to obtain total double support time, stance phase time, single support time, load response time, abduction-adduction (AA) angles, internal-external (IE) rotation angles, and flexion angles of …

Machine Learning Approach To Activity Categorization In Young Adults Using Biomechanical Metrics, Nathan Q. C. Holland

Mechanical & Aerospace Engineering Theses & Dissertations

Inactive adults often have decreased musculoskeletal health and increased risk factors for chronic diseases. However, there is limited data linking biomechanical measurements of generally healthy young adults to their physical activity levels assessed through questionnaires. Commonly used data collection methods in biomechanics for assessing musculoskeletal health include but are not limited to muscle quality (measured as echo intensity when using ultrasound), isokinetic (i.e., dynamic) muscle strength, muscle activations, and functional movement assessments using motion capture systems. These assessments can be time consuming for both data collection and processing. Therefore, understanding if all biomechanical assessments are necessary to classify the activity …

Detecting Lumbar Muscle Fatigue Using Nanocomposite Strain Gauges, Darci Ann Billmire

Theses and Dissertations

Introduction: Muscle fatigue can contribute to acute flare-ups of lower back pain with associated consequences such as pain, disability, lost work time, increased healthcare utilization, and increased opioid use and potential abuse. The SPINE Sense system is a wearable device with 16 high deflection nanocomposite strain gauge sensors on kinesiology tape which is adhered to the skin of the lower back. This device is used to correlate lumbar skin strains with the motion of the lumbar vertebrae and to phenotype lumbar spine motion. In this work it was hypothesized that the SPINE Sense device can be used to detect differences …

Mechanical Response Of The Craniofacial Skeleton To Subfracture Impacts In The Time And Frequency Domains, Paige Merko

Electronic Thesis and Dissertation Repository

Resonant frequencies have been suggested as a mechanism of brain injury since these vibrations can transfer energy into the brain. Study of the vibrational response of the craniofacial skeleton to impact is limited in literature. In this research, four cadaver specimens were impacted at five locations on the craniofacial skeleton. The mechanical response to each impact was compared in the time and frequency domains. Impacts to the maxilla and its associated soft tissues tended to be attenuated, while impacts to the cranial vault, specifically to the occipital, produced the most severe response. Results suggest that the facial skeleton and its …

Patient Movement Monitoring Based On Imu And Deep Learning, Mohsen Sharifi Renani

Electronic Theses and Dissertations

Osteoarthritis (OA) is the leading cause of disability among the aging population in the United States and is frequently treated by replacing deteriorated joints with metal and plastic components. Developing better quantitative measures of movement quality to track patients longitudinally in their own homes would enable personalized treatment plans and hasten the advancement of promising new interventions. Wearable sensors and machine learning used to quantify patient movement could revolutionize the diagnosis and treatment of movement disorders. The purpose of this dissertation was to overcome technical challenges associated with the use of wearable sensors, specifically Inertial Measurement Units (IMUs), as a …

Effect Of Amputation On Muscle Structure Properties In A Rabbit Model, Roy Caleb Stubbs

Masters Theses

After amputation, muscles in the residual limb are detached from their insertion points and no longer span the missing joints. Our objective was to quantify the effect of amputation-induced disuse on residual muscle structure, an indirect indicator of muscle force-generating capacity. One hind paw was surgically removed at the ankle joint of ten rabbits. At two weeks (n=5) and 4 weeks (n=5) post-amputation and for select muscles (gastrocnemius, soleus, tibialis cranialis, extensor digitorum, and flexor digitorum superficialis), we measured and computed several muscle structure properties. Additionally, we qualitatively assessed the muscle fiber appearance of histological samples at each timepoint. At …

Mitral Valve Imaging And Biomechanics: A Workflow Towards Computational Modeling And Validation, Sam Stephens

Graduate Theses and Dissertations

The mitral valve serves a critical role in healthy cardiac function by ensuring the unidirectional flow of oxygenated blood from the left atrium into the left ventricle. It experiences the highest pressures found within the heart and its closure is the result of a complex interaction of several different structures that, furthermore, are unique to each individual. Despite the valve’s vital role however, the specific function of these constituent structures is not fully understood. This, confounded by its asymmetric, personalized nature, make surgical interventions for the mitral valve far less effective than for its neighboring aortic valve. Efforts to overcome …

Amphisbaenian Head Movement And Burrowing Forces In Damp Granular Media, Jacob Newell

Williams Honors College, Honors Research Projects

Damp granular media is a difficult environment to study because it is both practically complex and it lacks equations which fully describe its behavior. In this study, an oscillatory lateral head movement and its effects while penetrating damp granular media were tested using a robophysical model. This experimental research was inspired by the burrowing behavior of the clade Amphisbaenia, a group of usually limbless squamates that employ a variety of different burrowing behaviors, but it can apply to a wide range of burrowers. This research could help with both human burrowing technologies and the further investigation of animal behaviors.

Quantifying Fibronectin Mechanical Properties Using Antibody-Mediated Optical Tweezing (Amot), Caleb Dalton

Theses and Dissertations

Despite decades of investigations into fibronectin (FN) fibrillogenesis, fibril mechanics remain unclear. One of the most important roles for FN fibrils is in the arena of cellular mechanotransduction. Numerous studies have demonstrated that cells sense and respond to the mechanical properties of their surroundings; since FN fibrils are a major constituent of the ECM that links cells to their surroundings, mechanotransduction cannot be fully understood without understanding the mechanical properties of FN fibrils. In this proposal, a novel biomechanical assay is developed to probe isolated FN fibrils and quantify their response to specific loading conditions. This will be accomplished by …

Making Sense Of Big (Kinematic) Data: A Comprehensive Analysis Of Movement Parameters In A Diverse Population, Naomi Wilma Nunis

University of the Pacific Theses and Dissertations

OBJECTIVE

The purpose of this study was to determine how kinematic, big data can be evaluated using computational, comprehensive analysis of movement parameters in a diverse population.

METHODS

Retrospective data was collected, cleaned, and reviewed for further analysis of biomechanical movement in an active population using 3D collinear resistance loads. The active sample of the population involved in the study ranged from age 7 to 82 years old and respectively identified as active in 13 different sports. Moreover, a series of exercises were conducted by each participant across multiple sessions. Exercises were measured and recorded based on 6 distinct biometric …