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

doi:10.1109/isbi.2014.6867850

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

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

11 Scopus citations

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.

Original language	English
Title of host publication	2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	226-229
Number of pages	4
ISBN (Electronic)	9781467319591
DOIs	https://doi.org/10.1109/isbi.2014.6867850
State	Published - 29 Jul 2014
Externally published	Yes
Event	2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 - Beijing, China Duration: 29 Apr 2014 → 2 May 2014

Publication series

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

Conference

Conference	2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
Country/Territory	China
City	Beijing
Period	29/04/14 → 2/05/14

Keywords

Active learning
Crohn disease
Random forests
Random walks
Saliency
Segmentation

Access to Document

10.1109/isbi.2014.6867850

Cite this

Mahapatra, D., Schüffler, P. J., Tielbeek, J. A. W., Makanyanga, J. C., Stoker, J., Taylor, S. A., Vos, F. M., & Buhmann, J. M. (2014). Active learning based segmentation of Crohn's disease using principles of visual saliency. In 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 (pp. 226-229). Article 6867850 (2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/isbi.2014.6867850

Mahapatra, Dwarikanath ; Schüffler, Peter J. ; Tielbeek, Jeroen A.W. et al. / Active learning based segmentation of Crohn's disease using principles of visual saliency. 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 226-229 (2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014).

@inproceedings{12ecf80a0bfb46a7b72d55203c6f2af0,

title = "Active learning based segmentation of Crohn's disease using principles of visual saliency",

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.",

keywords = "Active learning, Crohn disease, Random forests, Random walks, Saliency, Segmentation",

author = "Dwarikanath Mahapatra and Sch{\"u}ffler, {Peter J.} and Tielbeek, {Jeroen A.W.} and Makanyanga, {Jesica C.} and Jaap Stoker and Taylor, {Stuart A.} and Vos, {Franciscus M.} and Buhmann, {Joachim M.}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 ; Conference date: 29-04-2014 Through 02-05-2014",

year = "2014",

month = jul,

day = "29",

doi = "10.1109/isbi.2014.6867850",

language = "English",

series = "2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "226--229",

booktitle = "2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014",

}

Mahapatra, D, Schüffler, PJ, Tielbeek, JAW, Makanyanga, JC, Stoker, J, Taylor, SA, Vos, FM & Buhmann, JM 2014, Active learning based segmentation of Crohn's disease using principles of visual saliency. in 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014., 6867850, 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014, Institute of Electrical and Electronics Engineers Inc., pp. 226-229, 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014, Beijing, China, 29/04/14. https://doi.org/10.1109/isbi.2014.6867850

Active learning based segmentation of Crohn's disease using principles of visual saliency. / Mahapatra, Dwarikanath; Schüffler, Peter J.; Tielbeek, Jeroen A.W. et al.
2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 226-229 6867850 (2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Active learning based segmentation of Crohn's disease using principles of visual saliency

AU - Mahapatra, Dwarikanath

AU - Schüffler, Peter J.

AU - Tielbeek, Jeroen A.W.

AU - Makanyanga, Jesica C.

AU - Stoker, Jaap

AU - Taylor, Stuart A.

AU - Vos, Franciscus M.

AU - Buhmann, Joachim M.

PY - 2014/7/29

Y1 - 2014/7/29

N2 - 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.

AB - 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.

KW - Active learning

KW - Crohn disease

KW - Random forests

KW - Random walks

KW - Saliency

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=84927923487&partnerID=8YFLogxK

U2 - 10.1109/isbi.2014.6867850

DO - 10.1109/isbi.2014.6867850

M3 - Conference contribution

AN - SCOPUS:84927923487

T3 - 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

SP - 226

EP - 229

BT - 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

Y2 - 29 April 2014 through 2 May 2014

ER -

Mahapatra D, Schüffler PJ, Tielbeek JAW, Makanyanga JC, Stoker J, Taylor SA et al. Active learning based segmentation of Crohn's disease using principles of visual saliency. In 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 226-229. 6867850. (2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014). doi: 10.1109/isbi.2014.6867850

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

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this