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 …

Characterizing Endothelial Damage During Ischemic Stroke Treatment With 3d Cerebrovascular Live Cellular And Finite Element Models, Ana Regina Martinez Dehesa

Theses and Dissertations

Stent retriever mechanical thrombectomy (SRMT) is part of the clinical standard-of-care for acute ischemic stroke (AIS) patients with large vessel occlusion (LVO). Endothelial injury (EI) is widely associated with SRMT. Studies report finding EI markers in over 50% of retrieved clots, suggesting the frequency of EI in MT patients is rather common. The mechanism of EI and its contribution to MT failure and clinical outcomes remain poorly understood because of a lack of techniques to observe EI and study it in vitro. This study aims to investigate the mechanisms of EI induced by SRMT, as well as the effect stent …

Development Of A Customizable Framework For Data Driven Hemodynamic Analysis With Applications In Neurovascular And Cardiovascular Scenarios, Rachel Mae Hillner

Theses and Dissertations

Cardiovascular disease, including but not limited to heart failure and aneurysms, remain a leading cause of death worldwide. Persons over the age of 40 experience upwards of a 20% chance of developing heart failure in their lifetime. With a decrease in viable donor hearts, the reliance on mechanical heart assist devices is on the rise. However, such devices are not without their complications. Specifically, for left heart failure, a common treat, the left ventricular assist device, is characterized by clotting, stroke, and low survival rates as a result. Many studies suggest that such unfavorable results are correlated to adverse hemodynamic …

Xeno-Free Biomimetic Ecm Model For Investigation Of Matrix Properties On Astrocyte Cell Response, Bayan Saleh

Theses and Dissertations

Astrocytes are crucial in preserving the structural and functional integrity of the central nervous system (CNS). They participate in several physiological processes, such as the uptake of neurotransmitters, control of extracellular ion concentration, and preservation of the blood-brain barrier. Recent research has raised the possibility that astrocytes are also involved in the onset and development of Alzheimer's disease (AD). While the precise mechanisms underlying the development and progression of AD are not fully understood, recent research has suggested that age-related changes in the brain extracellular matrix (ECM) properties may play a critical role in the progression of the disease. Investigating …

Development Of A Pediatric Heart Assist Device Monitoring System, Natalie Hill

Theses and Dissertations

Heart failure (HF) is one of the leading causes of deaths for adults worldwide, but has disproportionately significant effects on pediatric patients that are often overshadowed. Treatment options for pediatric patients with HF are extremely limited, resulting in increased mortality rates within hospitals. Patients often depend on ventricular assist device (VAD) support as a bridge to transplant. The Berlin Heart EXCOR is the only FDA approved device for pediatric use in the US. However, many hemodynamic and neurological complications continue to arise; for instance, up to 30% of EXCOR patients suffer from stroke. Currently, there is no effective way to …

A Reduced Order Model For Estimation Of Fractional Flow Reserve (Ffr) In Coronary Artery Disease: Assessing The Impact Of Side Branches, Arber Vila

Theses and Dissertations

Coronary Artery Disease (CAD) affects millions of people worldwide and remains a leading cause of morbidity and mortality. To effectively plan treatment and risk stratification, assessing CAD severity is of paramount importance. Fractional flow reserve (FFR) is a critical clinical parameter used to evaluate CAD severity, measured by the ratio of mean distal coronary pressure to mean aortic pressure during hyperemic conditions. Although non-invasive FFR estimation methods have gained popularity, computational fluid dynamics (CFD) is impractical for routine clinical use due to the time and resources required. To address this issue, a reduced order model is proposed that accurately captures …