CS Other Presentations

Department of Computer Science - University of Cyprus

Besides Colloquiums, the Department of Computer Science at the University of Cyprus also holds Other Presentations (Research Seminars, PhD Defenses, Short Term Courses, Demonstrations, etc.). These presentations are given by scientists who aim to present preliminary results of their research work and/or other technical material. Other Presentations serve as a forum for educating Computer Science students and related announcements are disseminated to the Department of Computer Science (i.e., the csall list):

RSS Directions

Presentations Coordinator: Demetris Zeinalipour

PhD Defense: Explainable AI modelling in the assessment of Multiple Sclerosis using clinical data and Brain MRI lesion texture features, Andria Nicolaou (University of Cyprus, Cyprus), Monday, December 2, 2024, 08.30-09.30 EET.

The Department of Computer Science at the University of Cyprus cordially invites you to the PhD Defense entitled:

Explainable AI modelling in the assessment of Multiple Sclerosis using clinical data and Brain MRI lesion texture features

Abstract:
The complex, non-stationary nature of medical image structures necessitates the development of effective, visually understandable, and meaningful image representations. Medical image regions can often be characterized by intricate textures that are associated with specific diseases. Multiple Sclerosis (MS) is a heterogeneous disease of the central nervous system with diverse clinical manifestations and damaged tissue areas, called lesions, varying in size, location, and appearance, reflecting the underlying pathological causes. Neurological examinations and magnetic resonance imaging (MRI) assessments are inadequate in providing personalized treatment due to the complexity of the disease. The objective of this research is to develop and implement an integrated computer-aided diagnosis (CAD) system supporting explainable AI functionality to assist medical experts in the diagnosis and prognosis of MS disease. The integrated CAD system provides transparent and understandable explanations focused on brain MRI lesion characterization based on clinical data, texture and structure features, and their interrelation to disability and clinical evolution that assess MS disease progression. The modules of the integrated CAD system are MRI acquisition, preprocessing, lesion segmentation, feature extraction, classification, 3D reconstruction, decision making and explainability. Different MRI sequences were obtained from different MRI scanners at different time points. Clinical data were also investigated including demographic and neurological measurements. Texture and structure features were extracted from normalized and manually segmented brain MRI lesions. Machine learning models were developed to differentiate MS subjects with a benign course of the disease, and subjects with a progressive form of the disease where advanced accumulating disability becomes apparent. Rules were extracted and selected from the best-performed classifiers and modified as object-level arguments to develop an argumentation theory correlating the lesions’ features with the neurological disability and the clinical evolution of the patients. The findings indicated that the integrated CAD system can predict the disability status and the clinical condition of MS subjects with high accuracy and provide transparent, understandable, and explainable information with high fidelity. Future work will include further clinical data such as medications and laboratory test results. The 3D reconstruction module will be incorporated with the explainability module and will illustrate the damaged area of the brain along with the predicted diagnosis of the patient. The system should also be evaluated on more subjects.

Short Bio:
Andria Nicolaou received the BSc. degree in Computer Engineering with a minor in Biomedical Engineering from the University of Cyprus, in 2017, and the MSc. degree in Molecular and Applied Physiology from the National and Kapodistrian University of Athens, in 2019. She is currently pursuing the Ph.D. degree with the Department of Computer Science, University of Cyprus under the supervision of Prof. Constantinos Pattichis. She is a Research Associate with the HealthXR and VIDEOMICS groups in CYENS Centre of Excellence. She is also a Member of IEEE, and her interests lie in the field of Biomedical Engineering.

	Other Presentations Web: https://www.cs.ucy.ac.cy/colloquium/presentations.php
	Colloquia Web: https://www.cs.ucy.ac.cy/colloquium/
	Calendar: https://www.cs.ucy.ac.cy/colloquium/schedule/cs.ucy.pres.2024.nicolaou.ics