National and Kapodistrian University of Athens
Η διερεύνηση της σημασίας τεχνικών τεχνητής νοημοσύνης στην αξιολόγηση της μορφομετρικής ανάλυσης επιχρισμάτων διαγνωστικής κυτταρολογίας
Abstract
dc:descriptionIn the present work incidents of benign and malignant alterations were studied for three different parts of the human body, stomach, breast and thyroid. For each part discrimination was attempted between benign and malignant alterations in the cellular level as well as in the incident level. This was done using three different statistical methods: discriminant analysis, logistic regression and dendogram. In each cell 25 variables that characterize the form, the size and the texture of the chromatin of their nucleus were measured. The results of discrimination as much in cellular as in incident level between benign alterations and malignancy showed that the statistical methods that were used in the present work can be applied as an additional tool together with the diagnosis of the physician -cytologist since: · they objectify the diagnostic method with the import of morphometric and densitometric quantitative characteristics · they improve the diagnostic precision of cytological diagnosis · they provide diagnostic help for the new cytologists that do not have the essential experience and specialisation in specific parts of human bodies, since with the help of the dendogram the probability of classification in one of the two diagnostic teams of benign and malignant is given.
Degree
thesis:*- Grantor dc:publisher
- National and Kapodistrian University of Athens
- Year dc:date
- 2009
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Megalopoulou, Tatiana-Mona
- Μεγαλοπούλου, Τατιάνα-Μόνα
Subjects
dc:subject × 22- Διαχωριστική ανάλυση
- Λογαριθμιστική παλινδρόμηση
- Δενδρόγραμμα
- Ταξινόμηση
- Καλοήθη κύτταρα
- Κακοήθη κύτταρα
- Διάγνωση
- Καρκίνος
- Στατιστική μεθοδολογία
- Discriminant analysis
- Logistic regression
- Dendogram
- Classification
- Benign cells
- Malignant cells
- Diagnosis
- Cancer
- Statistical methodology
- Ιατρική και Επιστήμες Υγείας
- Βασική Ιατρική
- Medical and Health Sciences
- Basic Medicine
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/23688