Ultrasound interactive segmentation with tensor-graph methods

Nicola Rieke, Christoph Hennersperger, Diana Mateus, Nassir Navab

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

1 Zitat (Scopus)

Abstract

We address the problem of segmenting aortic aneurysms in ultrasound images. As solution we propose a novel framework based on graph-based interactive segmentation methods, such as graph-cuts and random walks. Our main contribution is extending these approaches to handle structure tensor ultrasound images. Our hypothesis is that the structure tensor is better suited to represent the contextual information in ultrasound images than the pure b-mode intensity values. We demonstrate that this extension significantly improves the performance of both methods in clinical data.

OriginalspracheEnglisch
Titel2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten690-693
Seitenumfang4
ISBN (elektronisch)9781467319591
DOIs
PublikationsstatusVeröffentlicht - 29 Juli 2014
Veranstaltung2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 - Beijing, China
Dauer: 29 Apr. 20142 Mai 2014

Publikationsreihe

Name2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

Konferenz

Konferenz2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
Land/GebietChina
OrtBeijing
Zeitraum29/04/142/05/14

Fingerprint

Untersuchen Sie die Forschungsthemen von „Ultrasound interactive segmentation with tensor-graph methods“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren