ORIOKE OLABISI OMOYEMI

Computer Science

At the Computer Science department office

Appointment on Visitation important

Topic: Medical Image Analysis:

Description: I am interested in developing image analysis techniques to analyze and solve medical problems for instant designing models to predict, diagnose or monitor cerebrovascular diseases. The research will focus on developing Machine Learning ML techniques to solve a number of diseases related to the brain. The objectives is to identify different 3D shape descriptors and magnetic resonance brain images that can be use to quantify White Matter Hyperintensities. Machine Learning Model will be developed to predict stroke.

#	Certificate	School	Year
1.	M.Sc (COMPUTER SCIENCE)	UNIVERSITY OF IBADAN	2016

DEVELOPMENT OF STROKE PREDICTION MACHINE LEARNING MODEL USING 3D SHAPE DESCRIPTORS AND BRAIN MAGNETIC RESONANCE IMAGES

INTRODUCTION: Stroke occurs when blood flow to an area in the brain is cut off and the brain can no more receive the required oxygen or nutrients, causing brain cells to die. If a stroke is not detected early it can result in permanent brain damage or death. Murphy, S.J.et al,, 2020 . Early detection of stroke can prevent such. Magnetic resonance imaging MRI is a standard tool for the diagnosis of stroke, but its manual interpretation by experts is arduous and time consuming.Visualization and quick diagnosis of white Mater Hyperintensities WMH have been made possible with emergence of various medical imaging technologies like Computed Tomography CT , Magnetic Resonance Imaging MRI , e.t.c . Czap, A.L. et al., 2021 .The presence of WMHs on MRI has been associated with stroke, itindicates damaged areas in the brain. Zhu, W., et al 2022 Thus, there is a need for computer-aided-diagnosis CAD models for characterizing stroke images in MRI. Also,WMH properties can be classified using Machine Learning ML , Deep Learning DL e.t.c.WMH on neuroimages have been proposed as biomarkers for stroke.The aim of this research is to develop a Machine Learning Model for stroke prediction using 3D shape descriptors and brain MRI. The specific objectives are: To identify strengths and weaknesses of existing machine learning algorithms used in characterizing WMH to get the gaps,to empirically identify a 3D rendering algorithm that can be used for WMH and identify 3D shape descriptors that can be used to characterize 3D WMH. Also to develop a Model for predicting stroke using shape descriptors and brain MRI and to evaluate the performance of the model using standardmetrics.

ORIOKE OMOYEMI is a Assistant Lecturer at the Department of Computer Science

ORIOKE has a M.Sc in COMPUTER SCIENCE from UNIVERSITY OF IBADAN