Semantic annotation system for medical images

• Κύριος συγγραφέας: Κόλιας, Βασίλειος
• Άλλοι συγγραφείς: Νικήτα, Κωνσταντίνα
• Μορφή: Thesis
• Γλώσσα: English
• Έκδοση: 2011
• Θέματα: Semantic web; Ontology; Computer aided diagnosis; Medical imaging; Web services; Σημασιολογικός ιστός; Οντολογία; Υποβοηθούμενη διάγνωση; Ιατρική απεικόνιση; Υπηρεσίες διαδικτύου; 616.075 4

Nowadays,hospitals are equipped with high resolution medical imaging systems such as MRI, CT that help the radiologists to make more accurate diagnosis. However these systems cannot give any information of the explicit content that is on the image pixels. The vast amount of images that are produced in hospitals is processed mainly by the medical domain users. Even systems such as PACS cannot retrieve images with anatomical or disease-­‐related criteria. The integrating of semantic web technologies in health care can provide a solution. The benefits for the semantic web technologies are owed to the core element of the semantic web, which is the ontology. The ontology sets strict relationships between its entities. The main goal of this thesis is to design and develop an online approach for Semantic Annotation and Retrieval of Medical Images. The architecture of the proposed system is based on a service oriented approach that enables the expandability of the system by integrating new features such as image processing algorithms to perform Computer Aided Diagnosis (CAD) tasks and to make queries with low -­‐ level image characteristics. Also the adopting of such an approach for the architecture allows to add new reference ontologies to the system without redesigning the core architecture. The ontology framework of the system includes (a) three reference ontologies, namely the Foundational Model of Anatomy (FMA) for the anatomy annotation, the International Classification of Disease (ICD-­‐10) for the disease annotation and the RadLex for the radiological findings and (b) an application ontology that connects the medical document with the concepts of the medical ontologies (FMA, ICD-­‐10, Radlex) and it also contains information about patient, hospital and image modality. Part of application ontology information is extracted from the DICOM header. In the context of the current thesis, the system was used to annotate and retrieve several medical images. The proposed online approach for annotation and retrieval of medical images system can enable the interoperability between different Health Information Systems (HIS) and can constitute a tool for discovering the hidden knowledge in medical image data.