Automatic volumetric localization of the liver in abdominal CT scans using low level processing and shape priors

Omar Ibrahim Al Irr, Ashrani Aizzuddin Abd Rahni

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

In this paper we present an automatic volumetric liver localization method as an approach for liver segmentation. In the proposed method the aim is to localise a mean shape model of the liver in the target CT scan. The framework consists of three main steps: shape model construction, low level processing and shape model registration. We evaluated our method on the MICCAI 2007 liver segmentation challenge dataset. The Leave-one-out validation results demonstrate the effectiveness of the proposed method. The average volume overlap between our method and the ground truth, using the Jaccard index, is 0.64±0.11 which is acceptable for an initial localisation of the liver prior to further refinement.

Original languageEnglish
Title of host publicationIEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages434-438
Number of pages5
ISBN (Electronic)9781479989966
DOIs
Publication statusPublished - 17 Feb 2016
Event4th IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Kuala Lumpur, Malaysia
Duration: 19 Oct 201521 Oct 2015

Other

Other4th IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2015
CountryMalaysia
CityKuala Lumpur
Period19/10/1521/10/15

Fingerprint

Computerized tomography
Liver
Processing

Keywords

  • Abdominal CT
  • Automated Localisation
  • Intensity Based Registration
  • Liver Segmentation
  • Low Level Processing
  • Mutual Information
  • Shape Model
  • Volumetric

ASJC Scopus subject areas

  • Computer Science Applications
  • Signal Processing

Cite this

Irr, O. I. A., & Abd Rahni, A. A. (2016). Automatic volumetric localization of the liver in abdominal CT scans using low level processing and shape priors. In IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings (pp. 434-438). [7412230] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSIPA.2015.7412230

Automatic volumetric localization of the liver in abdominal CT scans using low level processing and shape priors. / Irr, Omar Ibrahim Al; Abd Rahni, Ashrani Aizzuddin.

IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. p. 434-438 7412230.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Irr, OIA & Abd Rahni, AA 2016, Automatic volumetric localization of the liver in abdominal CT scans using low level processing and shape priors. in IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings., 7412230, Institute of Electrical and Electronics Engineers Inc., pp. 434-438, 4th IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2015, Kuala Lumpur, Malaysia, 19/10/15. https://doi.org/10.1109/ICSIPA.2015.7412230
Irr OIA, Abd Rahni AA. Automatic volumetric localization of the liver in abdominal CT scans using low level processing and shape priors. In IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. p. 434-438. 7412230 https://doi.org/10.1109/ICSIPA.2015.7412230
Irr, Omar Ibrahim Al ; Abd Rahni, Ashrani Aizzuddin. / Automatic volumetric localization of the liver in abdominal CT scans using low level processing and shape priors. IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 434-438
@inproceedings{23b90ad11ec9487faeb916037b3b8109,
title = "Automatic volumetric localization of the liver in abdominal CT scans using low level processing and shape priors",
abstract = "In this paper we present an automatic volumetric liver localization method as an approach for liver segmentation. In the proposed method the aim is to localise a mean shape model of the liver in the target CT scan. The framework consists of three main steps: shape model construction, low level processing and shape model registration. We evaluated our method on the MICCAI 2007 liver segmentation challenge dataset. The Leave-one-out validation results demonstrate the effectiveness of the proposed method. The average volume overlap between our method and the ground truth, using the Jaccard index, is 0.64±0.11 which is acceptable for an initial localisation of the liver prior to further refinement.",
keywords = "Abdominal CT, Automated Localisation, Intensity Based Registration, Liver Segmentation, Low Level Processing, Mutual Information, Shape Model, Volumetric",
author = "Irr, {Omar Ibrahim Al} and {Abd Rahni}, {Ashrani Aizzuddin}",
year = "2016",
month = "2",
day = "17",
doi = "10.1109/ICSIPA.2015.7412230",
language = "English",
pages = "434--438",
booktitle = "IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Automatic volumetric localization of the liver in abdominal CT scans using low level processing and shape priors

AU - Irr, Omar Ibrahim Al

AU - Abd Rahni, Ashrani Aizzuddin

PY - 2016/2/17

Y1 - 2016/2/17

N2 - In this paper we present an automatic volumetric liver localization method as an approach for liver segmentation. In the proposed method the aim is to localise a mean shape model of the liver in the target CT scan. The framework consists of three main steps: shape model construction, low level processing and shape model registration. We evaluated our method on the MICCAI 2007 liver segmentation challenge dataset. The Leave-one-out validation results demonstrate the effectiveness of the proposed method. The average volume overlap between our method and the ground truth, using the Jaccard index, is 0.64±0.11 which is acceptable for an initial localisation of the liver prior to further refinement.

AB - In this paper we present an automatic volumetric liver localization method as an approach for liver segmentation. In the proposed method the aim is to localise a mean shape model of the liver in the target CT scan. The framework consists of three main steps: shape model construction, low level processing and shape model registration. We evaluated our method on the MICCAI 2007 liver segmentation challenge dataset. The Leave-one-out validation results demonstrate the effectiveness of the proposed method. The average volume overlap between our method and the ground truth, using the Jaccard index, is 0.64±0.11 which is acceptable for an initial localisation of the liver prior to further refinement.

KW - Abdominal CT

KW - Automated Localisation

KW - Intensity Based Registration

KW - Liver Segmentation

KW - Low Level Processing

KW - Mutual Information

KW - Shape Model

KW - Volumetric

UR - http://www.scopus.com/inward/record.url?scp=84971597373&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84971597373&partnerID=8YFLogxK

U2 - 10.1109/ICSIPA.2015.7412230

DO - 10.1109/ICSIPA.2015.7412230

M3 - Conference contribution

AN - SCOPUS:84971597373

SP - 434

EP - 438

BT - IEEE 2015 International Conference on Signal and Image Processing Applications, ICSIPA 2015 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -