Back to search

Aristotle University Of Thessaloniki (AUTH)

Επεξεργασία σημασιολογική αναπαράσταση και διαχείριση δεδομένων γλαυκωματικών ασθενών

Abstract

dc:description

This thesis presents the original research focused in the data management, semantic representation of glaucomatous patients’ data and also in the extraction of new features by processing of optic nerve head images. In the chapter of data processing and feature extraction for the first time the shape of the contour of the 2-D surface of the optic disc cupping was assessed. In the data management chapter of this thesis a data management system flexible and scalable tested on multi-centric studies in the domain of glaucoma is presented in detail. In the chapter of semantic representation of the glaucoma domain for the first time an attempt to map domain entities to international terminologies is presented and assessed. The first chapter of this thesis assesses the special features of the management of medical data from glaucomatous patients. An information system was introduced for the management of clinical trial data in the glaucoma domain fulfilling additional requirements that are presented by multi-centric studies in the same domain. The presented system has distinct layer architecture it is user friendly, easy to maintain and secure in storing and exchanging data. Main features of the system are the reusable database schema that enables the use of the same database schema to store data from different studies and also the dual role of the database which is designed to store not only the study data but also the contents of the empty data collection form. The latter makes changes in the data collection form easy to apply without the need of modifications in the system’s application. The second chapter of this thesis explores new features of the optic nerve head morphology using the Heidelberg Retina Tomograph (HRT) also assesses their discriminating power between glaucomatous patients and normal subjects. For the first time the contour of the 2-D surface of the optic cup was examined regarding its shape. HRT reports, exported as TIFF images, from 97 Normal subjects and 97 Primary Open Angle Glaucoma (POAG) patients were used. For each image the contour of the dominant region of the optic disc cupping surface (dROCS) was transformed into a data-series by calculating the distance of each contour pixel from the centroid. The standard deviation of contour (SDC), the dROCS area divided by the Disk Area in pixels along with the standard deviation of the partial differential of the timeseries of the distances of the contour points from the centroid(SDdJ) were assessed as the novel parameters with the higher combined discrimination power with 82.5% correct classification. The last chapter presents the attempt of the semantic representation of the glaucomatous patients’ data via semi-automatic mapping of the glaucoma domain terms described in EGS GlaucoGENE to standard terminologies LOINC, MeSH and SNOMED CT. The semi-automatic mapping was performed in two stages once using the original text of the data collection form and again with improved text to increase matching possibility the results were 24% and 82% of the terms mapped correspondingly. Using the semantic mapping of the terms from the previous step an additional module was created in the information system in order to export the subject data in a semantically enriched newly defined XML format. This attempt pointed out the difficulties that arise in the mapping of data collection form terms to standard terminologies without taking into account the terminologies while designing the data collection forms.

Degree

thesis:*
Grantor dc:publisher
Aristotle University Of Thessaloniki (AUTH)
Year dc:date
2012

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Kilintzis, Vasilios
  • Κιλίντζης, Βασίλειος

Subjects

dc:subject × 24

Rights

Language dc:language
gre

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/27620

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Kilintzis, Vasilios; Κιλίντζης, Βασίλειος. Επεξεργασία σημασιολογική αναπαράσταση και διαχείριση δεδομένων γλαυκωματικών ασθενών. Aristotle University Of Thessaloniki (AUTH), 2012. http://hdl.handle.net/10442/hedi/27620