Pregled bibliografske jedinice broj: 1085078
Centerline Tracking of the Single Coronary Artery from X-ray Angiograms
Centerline Tracking of the Single Coronary Artery from X-ray Angiograms // 2020 International Symposium ELMAR
Zadar: Institute of Electrical and Electronics Engineers (IEEE), 2020. str. 117-122 doi:10.1109/elmar49956.2020.9219025 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 1085078 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Centerline Tracking of the Single Coronary Artery from X-ray Angiograms
Autori
Habijan, Marija ; Babin, Danilo ; Galic, Irena ; Leventic, Hrvoje ; Velicki, Lazar ; Cankovic, Milenko
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
2020 International Symposium ELMAR
/ - Zadar : Institute of Electrical and Electronics Engineers (IEEE), 2020, 117-122
ISBN
978-1-7281-5973-7
Skup
62nd International Symposium ELMAR-2020
Mjesto i datum
Zadar, Hrvatska, 14.09.2020. - 15.09.2020
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
coronary artery segmentation, coronary artery tracking, medical imaging, x-ray angiogram
Sažetak
Accurate determination of physiology and morphology of individual coronary artery is a prerequisite for its quantification as well as for planning procedures such as angioplasty. Therefore, in this paper, we propose a semi-automatic method for centerline extraction and tracking of the single coronary artery. Our approach is based on ridge edge detection and thresholding, after which the centerline of a vessel tree is extracted using skeletonization. After that, we manually select two points: at the start and the end of the single coronary artery. Finding the shortest path between selected points is used for single coronary centerline extraction. Finally, the template matching of selected points allows centerline tracking through the whole sequence. Obtained results show successful centerline extraction and tracking with satisfactory accuracy, precision, sensitivity and F1-score, of 81%, 79%, 81% and 0.76, respectively.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Projekti:
UIP-2017-05-4968 - Metode za interpretaciju medicinskih snimki za detaljnu analizu zdravlja srca (IMAGINEHEART) (Galić, Irena, HRZZ - 2017-05) ( CroRIS)
Ustanove:
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek