Kidney segmentation in ultrasound via genetic initialization and Active Shape Models with rotation correction

Carlos S. Mendoza, Xin Kang, Nabile Safdar, Emmarie Myers, Craig A Peters, Marius George Linguraru

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

7 Citations (Scopus)

Abstract

In this paper we present a segmentation method for 2D ultrasound images of the pediatric kidney. Our method relies on minimal user intervention and produces accurate segmentations thanks to a combination of improvements made to the Active Shape Model (ASM) framework. The initialization of the ASM module is based on a Covariance Matrix Adaptation Evolution Strategy (CMA-ES) genetic algorithm that optimizes the pose and the main shape variation modes of the kidney shape model. In order to account for the image formation process in ultrasound, the appearance model is obtained not according to the anatomically corresponding contour landmarks, but to those that exhibit a similar angle of incidence with respect to the wavefront traveling from the probe. The results indicate a median Dice's coefficient of 90.2% and a relative area difference of 10.8% for segmentation of a set of 80 kidney images.

Original languageEnglish (US)
Title of host publicationISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro
Pages69-72
Number of pages4
DOIs
StatePublished - Aug 22 2013
Event2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013 - San Francisco, CA, United States
Duration: Apr 7 2013Apr 11 2013

Other

Other2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013
CountryUnited States
CitySan Francisco, CA
Period4/7/134/11/13

Fingerprint

Ultrasonics
Kidney
Molecular Evolution
Pediatrics
Wavefronts
Covariance matrix
Image processing
Genetic algorithms
Incidence

Keywords

  • Active Shape Models
  • Hydronephrosis
  • Kidney
  • Segmentation
  • Ultrasound

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Mendoza, C. S., Kang, X., Safdar, N., Myers, E., Peters, C. A., & Linguraru, M. G. (2013). Kidney segmentation in ultrasound via genetic initialization and Active Shape Models with rotation correction. In ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro (pp. 69-72). [6556414] https://doi.org/10.1109/ISBI.2013.6556414

Kidney segmentation in ultrasound via genetic initialization and Active Shape Models with rotation correction. / Mendoza, Carlos S.; Kang, Xin; Safdar, Nabile; Myers, Emmarie; Peters, Craig A; Linguraru, Marius George.

ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro. 2013. p. 69-72 6556414.

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

Mendoza, CS, Kang, X, Safdar, N, Myers, E, Peters, CA & Linguraru, MG 2013, Kidney segmentation in ultrasound via genetic initialization and Active Shape Models with rotation correction. in ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro., 6556414, pp. 69-72, 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013, San Francisco, CA, United States, 4/7/13. https://doi.org/10.1109/ISBI.2013.6556414
Mendoza CS, Kang X, Safdar N, Myers E, Peters CA, Linguraru MG. Kidney segmentation in ultrasound via genetic initialization and Active Shape Models with rotation correction. In ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro. 2013. p. 69-72. 6556414 https://doi.org/10.1109/ISBI.2013.6556414
Mendoza, Carlos S. ; Kang, Xin ; Safdar, Nabile ; Myers, Emmarie ; Peters, Craig A ; Linguraru, Marius George. / Kidney segmentation in ultrasound via genetic initialization and Active Shape Models with rotation correction. ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro. 2013. pp. 69-72
@inproceedings{18c8da70178149e583807391ecc0baae,
title = "Kidney segmentation in ultrasound via genetic initialization and Active Shape Models with rotation correction",
abstract = "In this paper we present a segmentation method for 2D ultrasound images of the pediatric kidney. Our method relies on minimal user intervention and produces accurate segmentations thanks to a combination of improvements made to the Active Shape Model (ASM) framework. The initialization of the ASM module is based on a Covariance Matrix Adaptation Evolution Strategy (CMA-ES) genetic algorithm that optimizes the pose and the main shape variation modes of the kidney shape model. In order to account for the image formation process in ultrasound, the appearance model is obtained not according to the anatomically corresponding contour landmarks, but to those that exhibit a similar angle of incidence with respect to the wavefront traveling from the probe. The results indicate a median Dice's coefficient of 90.2{\%} and a relative area difference of 10.8{\%} for segmentation of a set of 80 kidney images.",
keywords = "Active Shape Models, Hydronephrosis, Kidney, Segmentation, Ultrasound",
author = "Mendoza, {Carlos S.} and Xin Kang and Nabile Safdar and Emmarie Myers and Peters, {Craig A} and Linguraru, {Marius George}",
year = "2013",
month = "8",
day = "22",
doi = "10.1109/ISBI.2013.6556414",
language = "English (US)",
isbn = "9781467364546",
pages = "69--72",
booktitle = "ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - Kidney segmentation in ultrasound via genetic initialization and Active Shape Models with rotation correction

AU - Mendoza, Carlos S.

AU - Kang, Xin

AU - Safdar, Nabile

AU - Myers, Emmarie

AU - Peters, Craig A

AU - Linguraru, Marius George

PY - 2013/8/22

Y1 - 2013/8/22

N2 - In this paper we present a segmentation method for 2D ultrasound images of the pediatric kidney. Our method relies on minimal user intervention and produces accurate segmentations thanks to a combination of improvements made to the Active Shape Model (ASM) framework. The initialization of the ASM module is based on a Covariance Matrix Adaptation Evolution Strategy (CMA-ES) genetic algorithm that optimizes the pose and the main shape variation modes of the kidney shape model. In order to account for the image formation process in ultrasound, the appearance model is obtained not according to the anatomically corresponding contour landmarks, but to those that exhibit a similar angle of incidence with respect to the wavefront traveling from the probe. The results indicate a median Dice's coefficient of 90.2% and a relative area difference of 10.8% for segmentation of a set of 80 kidney images.

AB - In this paper we present a segmentation method for 2D ultrasound images of the pediatric kidney. Our method relies on minimal user intervention and produces accurate segmentations thanks to a combination of improvements made to the Active Shape Model (ASM) framework. The initialization of the ASM module is based on a Covariance Matrix Adaptation Evolution Strategy (CMA-ES) genetic algorithm that optimizes the pose and the main shape variation modes of the kidney shape model. In order to account for the image formation process in ultrasound, the appearance model is obtained not according to the anatomically corresponding contour landmarks, but to those that exhibit a similar angle of incidence with respect to the wavefront traveling from the probe. The results indicate a median Dice's coefficient of 90.2% and a relative area difference of 10.8% for segmentation of a set of 80 kidney images.

KW - Active Shape Models

KW - Hydronephrosis

KW - Kidney

KW - Segmentation

KW - Ultrasound

UR - http://www.scopus.com/inward/record.url?scp=84881656694&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881656694&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2013.6556414

DO - 10.1109/ISBI.2013.6556414

M3 - Conference contribution

AN - SCOPUS:84881656694

SN - 9781467364546

SP - 69

EP - 72

BT - ISBI 2013 - 2013 IEEE 10th International Symposium on Biomedical Imaging

ER -