Graduation Semester and Year
Summer 2026
Language
English
Document Type
Dissertation
Degree Name
Doctor of Philosophy in Biomedical Engineering
Department
Bioengineering
First Advisor
Hanli Liu
Second Advisor
Lina Chalak
Third Advisor
Rong Zhang
Fourth Advisor
Srinivas Kota
Fifth Advisor
Salman Sohrabi
Abstract
Hypoxic–ischemic encephalopathy (HIE) is a neonatal brain injury caused by reduced oxygen and blood flow to the brain around the time of birth. It remains a major cause of neonatal mortality and long-term neurodevelopmental impairment worldwide. Therapeutic hypothermia is the standard treatment for moderate-to severe HIE and improves outcomes when initiated within the first six hours of life. Therefore, accurate assessment of injury severity during this period is essential. Cur rently, HIE severity is determined primarily through neurological examination and classified as mild, moderate, or severe. However, these examinations are subjective, cannot provide continuous monitoring of brain function, and may not accurately re flect the evolving nature of brain injury during the early postnatal period. These limitations highlight the need for objective and quantitative methods to evaluate brain function and identify injury severity during the critical early stages of HIE. The objective of this dissertation was to develop advanced algorithms for the quantitative assessment of brain function and injury severity in neonates with HIE. v To achieve this objective, neurovascular coupling, functional brain connectivity, and automated EEG-based classification were investigated using physiological signals ac quired during the early postnatal period. First, neurovascular coupling between neu ronal activity and cerebral oxygenation was quantified using wavelet transform coher ence (WTC). A dynamic WTC framework was developed to enable real-time assess ment of neurovascular coupling, and a complementary data-driven WTC approach was developed to quantify neurovascular coupling without relying on Monte Carlo simulations. Both approaches demonstrated reduced neurovascular coupling with in creasing HIE severity and provided objective measures of cerebral dysfunction during the early hours of life. Second, EEG-derived functional connectivity was investigated using mean phase coherence and graph theory analysis to characterize alterations in brain network organization associated with HIE severity. The results demonstrated significant differences in both global and regional network properties between mild and moderate HIE, indicating altered patterns of neural synchronization and connec tivity. Finally, a convolutional recurrent neural network was developed for automated classification of HIE severity from multichannel EEG recordings. The proposed deep learning framework achieved high classification performance and accurately differen tiated mild and moderate HIE without the need for handcrafted feature extraction. Collectively, the methods developed in this dissertation provide objective approaches for evaluating brain function in neonates with HIE and may contribute to improved assessment of injury severity during the critical early postnatal period.
Disciplines
Bioelectrical and Neuroengineering | Bioimaging and Biomedical Optics
License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Recommended Citation
Norasteh, Soheila, "EARLY DETECTION AND OBJECTIVE ASSESSMENT OF NEONATAL HYPOXIC-ISCHEMIC ENCEPHALOPATHY SEVERITY" (2026). Bioengineering Dissertations. 6.
https://mavmatrix.uta.edu/bioengineering_dissertations2/6