Predictive Modeling of the Atheromatic Plaque Growth
Φόρτωση...
Αρχεία
Ημερομηνία
Συγγραφείς
Kigka, Vassiliki
Τίτλος Εφημερίδας
Περιοδικό ISSN
Τίτλος τόμου
Εκδότης
Πανεπιστήμιο Ιωαννίνων. Πολυτεχνική Σχολή. Τμήμα Μηχανικών Επιστήμης Υλικών
Περίληψη
Τύπος
Είδος δημοσίευσης σε συνέδριο
Είδος περιοδικού
Είδος εκπαιδευτικού υλικού
Όνομα συνεδρίου
Όνομα περιοδικού
Όνομα βιβλίου
Σειρά βιβλίου
Έκδοση βιβλίου
Συμπληρωματικός/δευτερεύων τίτλος
Περιγραφή
This PhD thesis aims to develop models for the predictive modeling of atherosclerotic plaque
progression, both in coronary and carotid arteries. In this thesis, active contour models and dynamic
threshold segmentation techniques have been implemented for the segmentation of the inner wall, outer
wall, CP and NCP in coronary and carotid arteries, using computed tomography angiography images.
Additionally, through this thesis machine learning models that utilize both imaging and non-imaging
data for the prediction of coronary artery disease were developed, whereas models using only non imaging data were developed for the carotid artery disease prediction.
The first chapter presents the physiology of the cardiovascular system. More specifically, the function of
the circulatory system, the anatomy and function of the heart, the coronary and carotid arteries’ anatomy,
are presented. Then, the pathophysiology of atherosclerosis and atherosclerosis risk factors are
presented. Finally, this chapter reports the imaging modalities of atherosclerosis, both invasive and non invasive, and the advantages and the disadvantages of each technique in clinical practice.
In the second chapter of this thesis, an extensive presentation of the existing in the literature methods for
the three-dimensional reconstruction of the coronary and carotid arteries and the localization of
atherosclerotic plaques, both at an automated level and at a non-automated level, is performed. Then,
existing studies for the prediction of coronary and carotid artery disease, utilizing either standard
statistical analysis techniques or machine learning techniques, are presented. Finally, in this chapter, all
the existing biomarkers for the diagnosis and prediction of carotid disease and the mechanism by which
they participate in the pathogenesis of the disease, as well as the existing studies in the literature that
demonstrate their importance, are presented.
The third chapter describes the proposed methodology for the three-dimensional reconstruction of the
inner and outer wall of the coronary and carotid arteries and for the identification and characterization of
atherosclerotic plaques (calcified and non-calcified plaques). In addition to this, different processes for
validating the proposed methodology are presented, as well as the innovative aspect of the present
methodology compared to the existing literature.
The fourth chapter of the thesis aims to present machine learning models for the prediction of coronary
artery disease, predicting the obstructive coronary artery disease, the progression of the disease and the placement of an endovascular stent. The proposed models were trained with non-imaging and imaging
data, geometry and blood flow based data.
In the fifth chapter of this paper, machine learning models were proposed to diagnose and identify
subjects with asymptomatic carotid disease and participants with the presence of high-risk
atherosclerotic plaques, using typical medical records as input.
Finally, in the sixth chapter, the association of carotid artery disease with the presence of clinically
asymptomatic brain lesions, was presented. More specifically, the aim of this chapter is to correlate
ultrasound markers of the carotid artery, as well as characteristics of each patient (demographic, clinical,
hematological, biochemical data and risk factors) with the presence of clinically asymptomatic brain
lesions in the ipsilateral hemisphere.
The seventh and last chapter of this paper constitutes a discussion section, related to the contribution of
the proposed PhD thesis, as well as to possible future research steps.
Περιγραφή
Λέξεις-κλειδιά
atherosclerosis, coronary artery disease, carotid artery disease, risk stratification, machine learning, image processing
Θεματική κατηγορία
Παραπομπή
Σύνδεσμος
Γλώσσα
Εκδίδον τμήμα/τομέας
Πανεπιστήμιο Ιωαννίνων. Πολυτεχνική Σχολή. Τμήμα Μηχανικών Επιστήμης Υλικών
Όνομα επιβλέποντος
Fotiadis, Dimitrios
Εξεταστική επιτροπή
Gergidis, Leonidas
Michalis, Lambros
Sigala, Fragkiska
Matsopoulos, Georgios
Naka, Aikaterini
Sakellarios, Antonios
Michalis, Lambros
Sigala, Fragkiska
Matsopoulos, Georgios
Naka, Aikaterini
Sakellarios, Antonios
Γενική Περιγραφή / Σχόλια
Ίδρυμα και Σχολή/Τμήμα του υποβάλλοντος
Πανεπιστήμιο Ιωαννίνων. Πολυτεχνική Σχολή, Τμήμα Μηχανικών Επιστήμης Υλικών