Unit:
Κατεύθυνση Επεμβατική ΑκτινολογίαLibrary of the School of Health Sciences
Author:
Παπαμιχαήλ Δημήτρης
Supervisors info:
Ε. Ευσταθόπουλος, Καθηγητής Ιατρικής Φυσικής- Ακτινοφυσικής
Original Title:
Αυτοματοποιημένη εξαγωγή μεταδεδομένων από πολλαπλές ιατρικές εικόνες μέσω τοπικού δικτύου
Translated title:
Automated metadata extraction from multiple medical images over a local network
Summary:
Explosive growth in the number of biomedical images in recent years
requires
new techniques to manage the information collected. Additional scan-related
information, such as the acquisition parameters and filtration, is stored in
DICOM
metadata, while additional patient-related information, such as medical history
or
symptoms, is usually stored in a separated Database Management System (DBMS).
Picture archiving and communication systems (PACS) can address the image data
management issue, but PACS generally lack any methods for searching images and
querying the metadata based on DBMS records. The objective of this study is to
develop an automated method to address the problem of requiring biomedical
image metadata from PACS over local network.
A client application has been designed to make requests to the database of
the
remote server. Algorithms have been developed to query the remote PACS server
for
the specified DICOM files and extract all metadata. The application allows
users to
enter queries and store the results in a Microsoft Excel spreadsheet. This
project has
placed increasing emphasis on the security aspect of the patient’s personal
data. The
extracted information is automatically formatted and presented to the authorized
end user as a Microsoft Excel file for data and trend analysis. The integrity
and time
efficacy of the method has been evaluated with a test sample of 171 DICOM files,
while the accuracy of the data has been manually validated.
Keywords:
Medical image, Metadata, Database, DICOM
