Active learning based segmentation of Crohn's disease using principles of visual saliency

Dwarikanath Mahapatra, Peter J. Schüffler, Jeroen A.W. Tielbeek, Jesica C. Makanyanga, Jaap Stoker, Stuart A. Taylor, Franciscus M. Vos, Joachim M. Buhmann

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

11 Zitate (Scopus)

Abstract

We propose a active learning (AL) approach to segment Crohn's disease (CD) affected regions in abdominal magnetic resonance (MR) images. Our label query strategy is inspired from the principles of visual saliency which has similar considerations for choosing the most salient region. These similarities are encoded in a graph using classification maps and low level features. The most informative node is determined using random walks. Experimental results on real patient datasets show the superior performance of our approach and highlight the importance of different features to determine a region's importance.

OriginalspracheEnglisch
Titel2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten226-229
Seitenumfang4
ISBN (elektronisch)9781467319591
DOIs
PublikationsstatusVeröffentlicht - 29 Juli 2014
Extern publiziertJa
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 „Active learning based segmentation of Crohn's disease using principles of visual saliency“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren