PuSH - Publikationsserver des Helmholtz Zentrums München

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
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?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Korrespondenzautor
Schlagwörter Atherosclerosis ; Carotid Artery ; Deep Learning ; Segmentation ; Ultrasound; Intima-media Complex; Segmentation; Atherosclerosis
ISSN (print) / ISBN 1948-5719
e-ISSN 1948-5727
Konferenztitel 2022 IEEE International Ultrasonics Symposium (IUS)
Konferzenzdatum 10-13 October 2022
Konferenzort Venice, Italy
Quellenangaben Band: , Heft: , Seiten: , Artikelnummer: 4 Supplement: ,
Verlag Ieee
Verlagsort 345 E 47th St, New York, Ny 10017 Usa
Nichtpatentliteratur Publikationen
Institut(e) Institute of Biological and Medical Imaging (IBMI)
Förderungen LABEX PRIMES of Universite de Lyon, within the program "Investissements d'Avenir"
via NL's doctoral grant