National and Kapodistrian University of Athens
Ανάλυση και αναζήτηση ιατρικών μαστογραφικών εικόνων
Abstract
dc:descriptionIn this thesis two CAD systems are presented. The first system proposed is a fully automated segmentation and classification scheme for mammograms based on breast density estimation and detection of asymmetry. First, image preprocessing and segmentation techniques are applied. Features for breast density categorization are extracted and SVMs are employed for classification, achieving accuracy of up to 85.7%. Most of these properties are used to extract a new set of statistical features for each pair of breast, in order to detect breast asymmetry. The use of an one-class SVM classifier, resulted in a success rate of 84.47%. This composite methodology has been applied to the miniMIAS database. The results were evaluated and are very promising, showing equal or higher success rates compared to other related works, despite the fact that some of them used only selected portions of this specific mammographic database. The second system proposed is an experimental "morphological analysis" retrieval system for mammograms, using Relevance-Feedback techniques. The features adopted are first-order statistics of the Normalized Radial Distance, extracted from the annotated mass boundary. The system is evaluated on a dataset of 2274 masses of the DDSM database, which involves 7 distinct classes. The experiments verify that the involvement of the radiologist as part of the retrieval process improves the results, reaching the precision rate of almost 90%. Therefore, Relevance-Feedback can be employed as a useful complementary tool to a CAD system
Degree
thesis:*- Grantor dc:publisher
- National and Kapodistrian University of Athens
- Year dc:date
- 2011
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Tzikopoulos, Stylianos
- Τζικόπουλος, Στυλιανός
Subjects
dc:subject × 14- Διάγνωση μέσω Η/Υ
- Ανάκτηση εικόνων με βάση το περιεχόμενο
- Ανατροφοδότηση συνάφειας
- Μαστογραφία
- Ταξινόμηση
- Computer-aided diagnosis
- Content - based image retrieval
- Relevance feedback
- Mammography
- Classification
- Φυσικές Επιστήμες
- Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική
- Natural Sciences
- Computer and Information Sciences
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/23754