Laine, N.* ; Zahnd, G. ; Liebgott, H.* ; Orkisz, M.*
Segmenting the carotid-artery wall in ultrasound image sequences with a dual-resolution U-net.
In: (2022 IEEE International Ultrasonics Symposium (IUS), 10-13 October 2022, Venice, Italy). 345 E 47th St, New York, Ny 10017 Usa: Ieee, 2022.:4 (IEEE International Ultrasonics Symposium, IUS)
DOI
möglich sobald bei der ZB eingereicht worden ist.
Thickening of intima-media complex in the common carotid artery is a biomarker of atherosclerosis. To automatically measure this thickness, we propose a region-based segmentation method, involving a supervised deep-learning approach based on the dilated U-net architecture, named caroSegDeep. It was trained and evaluated using 5-fold cross-validation on two open-access databases containing a total of 2676 annotated images. Compared with the methods already evaluated on these databases, caroSegDeep established a new benchmark and achieved a mean absolute error twice smaller than the inter-observer variability.
Altmetric
Weitere Metriken?
Publikationstyp
Artikel: Konferenzbeitrag
Dokumenttyp
Typ der Hochschulschrift
Herausgeber
Korrespondenzautor
Schlagwörter
Atherosclerosis ; Carotid Artery ; Deep Learning ; Segmentation ; Ultrasound; Intima-media Complex; Segmentation; Atherosclerosis
Keywords plus
ISSN (print) / ISBN
1948-5719
e-ISSN
1948-5727
ISBN
Bandtitel
Konferenztitel
2022 IEEE International Ultrasonics Symposium (IUS)
Konferzenzdatum
10-13 October 2022
Konferenzort
Venice, Italy
Konferenzband
Quellenangaben
Band: ,
Heft: ,
Seiten: ,
Artikelnummer: 4
Supplement: ,
Reihe
Verlag
Ieee
Verlagsort
345 E 47th St, New York, Ny 10017 Usa
Hochschule
Hochschulort
Fakultät
Veröffentlichungsdatum
0000-00-00
Anmeldedatum
0000-00-00
Anmelder/Inhaber
weitere Inhaber
Anmeldeland
Priorität
Begutachtungsstatus
Förderungen
LABEX PRIMES of Universite de Lyon, within the program "Investissements d'Avenir"
via NL's doctoral grant