Segmentation of kidney in 3D-ultrasound images using gabor-based appearance models

Juan J. Cerrolaza, Nabile Safdar, Craig A Peters, Emmarie Myers, James Jago, Marius George Linguraru

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

13 Citations (Scopus)

Abstract

This paper presents a new segmentation method for 3D ultrasound images of the pediatric kidney. Based on the popular active shape models, the algorithm is tailored to deal with the particular challenges raised by US images. First, a weighted statistical shape model allows to compensate the image variation with the propagation direction of the US wavefront. Second, an orientation correction approach is used to create a Gabor-based appearance model for each landmark at different scales. This multiscale characteristic is incorporated into the segmentation algorithm, creating a hierarchical approach where different appearance models are considered as the segmentation process evolves. The performance of the algorithm was evaluated on a dataset of 14 cases, both healthy and pathological, obtaining an average Dice's coefficient of 0.85, an average point-to-point distance of 4.07 mm, and 0.12 average relative volume difference.

Original languageEnglish (US)
Title of host publication2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages633-636
Number of pages4
ISBN (Electronic)9781467319591
StatePublished - Jan 1 2014
Event2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 - Beijing, China
Duration: Apr 29 2014May 2 2014

Other

Other2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
CountryChina
CityBeijing
Period4/29/145/2/14

Fingerprint

Ultrasonics
Kidney
Statistical Models
Pediatrics
Wavefronts
Datasets
Direction compound

Keywords

  • Hydronephrosis
  • Kidney
  • Segmentation
  • Statistical shape model
  • Ultrasound

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Cerrolaza, J. J., Safdar, N., Peters, C. A., Myers, E., Jago, J., & Linguraru, M. G. (2014). Segmentation of kidney in 3D-ultrasound images using gabor-based appearance models. In 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 (pp. 633-636). [6867950] Institute of Electrical and Electronics Engineers Inc..

Segmentation of kidney in 3D-ultrasound images using gabor-based appearance models. / Cerrolaza, Juan J.; Safdar, Nabile; Peters, Craig A; Myers, Emmarie; Jago, James; Linguraru, Marius George.

2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 633-636 6867950.

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

Cerrolaza, JJ, Safdar, N, Peters, CA, Myers, E, Jago, J & Linguraru, MG 2014, Segmentation of kidney in 3D-ultrasound images using gabor-based appearance models. in 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014., 6867950, Institute of Electrical and Electronics Engineers Inc., pp. 633-636, 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014, Beijing, China, 4/29/14.
Cerrolaza JJ, Safdar N, Peters CA, Myers E, Jago J, Linguraru MG. Segmentation of kidney in 3D-ultrasound images using gabor-based appearance models. In 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 633-636. 6867950
Cerrolaza, Juan J. ; Safdar, Nabile ; Peters, Craig A ; Myers, Emmarie ; Jago, James ; Linguraru, Marius George. / Segmentation of kidney in 3D-ultrasound images using gabor-based appearance models. 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 633-636
@inproceedings{b9edf52a225c44e5bd03a30d7c03849a,
title = "Segmentation of kidney in 3D-ultrasound images using gabor-based appearance models",
abstract = "This paper presents a new segmentation method for 3D ultrasound images of the pediatric kidney. Based on the popular active shape models, the algorithm is tailored to deal with the particular challenges raised by US images. First, a weighted statistical shape model allows to compensate the image variation with the propagation direction of the US wavefront. Second, an orientation correction approach is used to create a Gabor-based appearance model for each landmark at different scales. This multiscale characteristic is incorporated into the segmentation algorithm, creating a hierarchical approach where different appearance models are considered as the segmentation process evolves. The performance of the algorithm was evaluated on a dataset of 14 cases, both healthy and pathological, obtaining an average Dice's coefficient of 0.85, an average point-to-point distance of 4.07 mm, and 0.12 average relative volume difference.",
keywords = "Hydronephrosis, Kidney, Segmentation, Statistical shape model, Ultrasound",
author = "Cerrolaza, {Juan J.} and Nabile Safdar and Peters, {Craig A} and Emmarie Myers and James Jago and Linguraru, {Marius George}",
year = "2014",
month = "1",
day = "1",
language = "English (US)",
pages = "633--636",
booktitle = "2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Segmentation of kidney in 3D-ultrasound images using gabor-based appearance models

AU - Cerrolaza, Juan J.

AU - Safdar, Nabile

AU - Peters, Craig A

AU - Myers, Emmarie

AU - Jago, James

AU - Linguraru, Marius George

PY - 2014/1/1

Y1 - 2014/1/1

N2 - This paper presents a new segmentation method for 3D ultrasound images of the pediatric kidney. Based on the popular active shape models, the algorithm is tailored to deal with the particular challenges raised by US images. First, a weighted statistical shape model allows to compensate the image variation with the propagation direction of the US wavefront. Second, an orientation correction approach is used to create a Gabor-based appearance model for each landmark at different scales. This multiscale characteristic is incorporated into the segmentation algorithm, creating a hierarchical approach where different appearance models are considered as the segmentation process evolves. The performance of the algorithm was evaluated on a dataset of 14 cases, both healthy and pathological, obtaining an average Dice's coefficient of 0.85, an average point-to-point distance of 4.07 mm, and 0.12 average relative volume difference.

AB - This paper presents a new segmentation method for 3D ultrasound images of the pediatric kidney. Based on the popular active shape models, the algorithm is tailored to deal with the particular challenges raised by US images. First, a weighted statistical shape model allows to compensate the image variation with the propagation direction of the US wavefront. Second, an orientation correction approach is used to create a Gabor-based appearance model for each landmark at different scales. This multiscale characteristic is incorporated into the segmentation algorithm, creating a hierarchical approach where different appearance models are considered as the segmentation process evolves. The performance of the algorithm was evaluated on a dataset of 14 cases, both healthy and pathological, obtaining an average Dice's coefficient of 0.85, an average point-to-point distance of 4.07 mm, and 0.12 average relative volume difference.

KW - Hydronephrosis

KW - Kidney

KW - Segmentation

KW - Statistical shape model

KW - Ultrasound

UR - http://www.scopus.com/inward/record.url?scp=84927924624&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84927924624&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84927924624

SP - 633

EP - 636

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

PB - Institute of Electrical and Electronics Engineers Inc.

ER -