prikaz prve stranice dokumenta Using DICOM Tags for Clustering Medical Radiology Images into Visually Similar Groups
  Preuzmi
PDF 709.05 KB
Znanstveni rad - Izvorni znanstveni rad s konferencije (pozvano predavanje)
Using DICOM Tags for Clustering Medical Radiology Images into Visually Similar Groups
U: Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods. Portugal: Science and Technology Publications, 2020. str. 510-517. https://doi.org/10.5220/0008973405100517
Manojlović, Teo; Ilić, Dino; Miletić, Damir; Štajduhar, Ivan

Citirajte ovaj rad

Manojlović, T., Ilić, D., Miletić, D. i Štajduhar, I. (2020). Using DICOM Tags for Clustering Medical Radiology Images into Visually Similar Groups. Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods (str. 510-517). Portugal: Science and Technology Publications. doi: 10.5220/0008973405100517

Manojlović, Teo, et al. "Using DICOM Tags for Clustering Medical Radiology Images into Visually Similar Groups." Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods, Science and Technology Publications, 2020, str. 510-517. https://urn.nsk.hr/urn:nbn:hr:184:351926

Manojlović, Teo, Dino Ilić, Damir Miletić i Ivan Štajduhar. "Using DICOM Tags for Clustering Medical Radiology Images into Visually Similar Groups." U Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods, 510-517. Portugal: Science and Technology Publications, 2020. Citirano 25.12.2024.. https://urn.nsk.hr/urn:nbn:hr:184:351926

Manojlović, T., et al. (2020) 'Using DICOM Tags for Clustering Medical Radiology Images into Visually Similar Groups', Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods, Science and Technology Publications, Portugal, str. 510-517. Preuzeto s: https://urn.nsk.hr/urn:nbn:hr:184:351926 (Datum pristupa: 25.12.2024.)

Manojlović T, Ilić D, Miletić D, Štajduhar I. Using DICOM Tags for Clustering Medical Radiology Images into Visually Similar Groups. Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods. Portugal: Science and Technology Publications; 2020. Str. 510-517. [pristupljeno 25.12.2024.] Dostupno na: https://urn.nsk.hr/urn:nbn:hr:184:351926

T. Manojlović, D. Ilić, D. Miletić i I. Štajduhar, "Using DICOM Tags for Clustering Medical Radiology Images into Visually Similar Groups", Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods Portugal: Science and Technology Publications, 2020. [Online] Dostupno na: https://urn.nsk.hr/urn:nbn:hr:184:351926 [Citirano: 25.12.2024.]

Za citiranje koristite ovu mrežnu adresu: https://urn.nsk.hr/urn:nbn:hr:184:351926
Prijavite se u repozitorij kako biste mogli spremiti objekt u svoju listu.
Podaci o radu
Naslov (engleski)Using DICOM Tags for Clustering Medical Radiology Images into Visually Similar Groups
AutorTeo Manojlović
AutorDino Ilić
AutorDamir Miletić
AutorIvan Štajduhar
Autorova ustanovaSveučilište u Rijeci
Medicinski fakultet
(Katedra za radiologiju)
Znanstveno / umjetničko
područje, polje i grana		BIOMEDICINA I ZDRAVSTVO
Kliničke medicinske znanosti
Radiologija
Znanstveno / umjetničko
područje, polje i grana		TEHNIČKE ZNANOSTI
Računarstvo
Sažetak (engleski)
The data stored in a Picture Archiving and Communication System (PACS) of a clinical centre normally consists of medical images recorded from patients using select imaging techniques, and stored metadata information concerning the details on the conducted diagnostic procedures - the latter being commonly stored using the Digital Imaging and Communications in Medicine (DICOM) standard. In this work, we explore the possibility of utilising DICOM tags for automatic annotation of PACS databases, using K-medoids clustering. We gather and analyse DICOM data of medical radiology images available as a part of the RadiologyNet database, which was built in 2017, and originates from the Clinical Hospital Centre Rijeka, Croatia. Following data preprocessing, we used K-medoids clustering for multiple values of K, and we chose the most appropriate number of clusters based on the silhouette score. Next, for evaluating the clustering performance with regard to the visual similarity of images, we trained an autoencoder from a non-overlapping set of images. That way, we estimated the visual similarity of pixel data clustered by DICOM tags. Paired t-test (p < 0.001) suggests a significant difference between the mean distance from cluster centres of images clustered by DICOM tags, and randomly-permuted cluster labels.
Ključne riječi (engleski)
Jezikengleski
Vrsta publikacijeZnanstveni rad - Izvorni znanstveni rad s konferencije (pozvano predavanje)
Status objaveObjavljen
Vrsta recenzijeNepoznato
Verzija publikacijeObjavljena verzija rada (izdavačev PDF)
Naslov zbornikaProceedings of the 9th International Conference on Pattern Recognition Applications and Methods
Brojčani podacibr. 1, str. 510-517
ISBN978-989-758-397-1
p-ISSN2184-4313
DOIhttps://doi.org/10.5220/0008973405100517
URN:NBNurn:nbn:hr:184:351926
Datum objave publikacije2020
SkupNaziv: 9th International Conference on Pattern Recognition Applications and Methods
Kratica: ICPAM 2020
Lokacija: Valletta, Malta
Datum početka: 2020-02-22
Datum završetka: 2020-02-24
Vrsta izlaganja: Predavanje
Vrsta resursaTekst
IzdavačScience and Technology Publications
Mjesto izdavanjaPortugal
Prava pristupaOtvoreni pristup
Uvjeti korištenjaIkona licence Imenovanje-Nekomercijalno-Bez prerada 4.0 međunarodna (CC BY-NC-ND 4.0)
Datum i vrijeme pohrane2020-03-29 13:45:07