Electronic Thesis and Dissertation Repository

Thesis Format

Integrated Article

Degree

Master of Science

Program

Neuroscience

Supervisor

Anazodo, Udunna C.

2nd Supervisor

Jurkiewicz, Michael T.

Co-Supervisor

3rd Supervisor

Slessarev, Marat

Co-Supervisor

Abstract

COVID-19 infection leading to acute respiratory distress syndrome (ARDS) has been associated with impaired neurocognitive function and is known to increase the risk for endothelial dysfunction and coagulopathy affecting the vasculature of the brain. Recent studies have reported a higher concentration of cytokine and glutamate receptors along white matter tracts which may increase susceptibility to inflammatory-induced damage, further affected by hypoxemia due to direct and indirect lung damage. We conducted a systematic review and meta-analysis which suggests that the combination of ARDS and COVID-19 doubles the risk of developing intracranial hemorrhage and increases vulnerability to cerebral white matter injury as opposed to ARDS of other causes. Given the findings of the review, we then assess image analysis methods to detect these injuries, particularly white matter hyperintensities (WMH). Although various deep learning techniques have been proposed to automatically quantify WMH, the influence of image preprocessing steps on segmentation accuracy has been underexplored. We examine the impact of five intensity normalization methods on deep learning segmentation accuracy, emphasizing the importance of careful consideration for WMH analysis in COVID-19 ARDS populations. Further exploration of intensity normalization approaches using the Neuro-SAVE ICU data is underway to determine the optimal method for WMH analysis.

Summary for Lay Audience

Acute Respiratory Distress Syndrome (ARDS) is a condition resulting from severe lung injury. The diagnostic criteria for ARDS, known as the 'Berlin definition,' include the timing of respiratory symptoms onset, low oxygen levels despite oxygen therapy, and fluid accumulation in the lungs leading to respiratory failure. This fluid buildup can damage the pulmonary surfactant, which prevents lung collapse. Inflammatory mediators called cytokines released by immune cells in the lungs can trigger a secondary inflammatory response in the brain, involving microglia activation. In some cases, this response can become excessive, damaging blood vessels and neurons, which can be observed through brain imaging techniques like MRI. COVID-19 infection is the focus of this thesis as a potential cause of ARDS. The SARS-CoV-2 virus responsible for COVID-19 enters the body through ACE-2 receptors, which are concentrated in the lungs. The virus destroys these receptors, leading to an immune response that further damages lung cells. Severe infections can result in ARDS, and there is evidence suggesting that COVID-19-related ARDS may increase the frequency of brain injuries, particularly affecting white matter. Such injuries pose a higher risk of disability and mortality for patients.

The thesis consists of two parts. The first part reviews previous research on brain injuries in ARDS, including their frequencies and associated risks. The second part focuses on analyzing MRI data, specifically when dealing with low-quality clinical data. The findings indicate that COVID-19 ARDS patients are twice as likely to experience brain hemorrhages compared to other causes of ARDS. Additionally, COVID-19 may specifically impact white matter tracts in the brain. To improve analysis efficiency and enhance understanding, the thesis proposes the use of deep learning techniques for automatic detection of white matter lesions. Further research is necessary to fully understand the impact of COVID-19 ARDS on the brain. This knowledge will be crucial for scientists and healthcare systems in developing and providing support to COVID-19 ARDS survivors.

Download

Share

COinS