Automatic analysis of pediatric renal ultrasound using shape, anatomical and image acquisition priors.

Xin Kang, Nabile Safdar, Emmarie Myers, Aaron D. Martin, Enrico Grisan, Craig A Peters, Marius George Linguraru

Research output: Contribution to journalArticle

Abstract

In this paper we present a segmentation method for ultrasound (US) images of the pediatric kidney, a difficult and barely studied problem. Our method segments the kidney on 2D sagittal US images and relies on minimal user intervention and a combination of improvements made to the Active Shape Model (ASM) framework. Our contributions include particle swarm initialization and profile training with rotation correction. We also introduce our methodology for segmentation of the kidney's collecting system (CS), based on graph-cuts (GC) with intensity and positional priors. Our intensity model corrects for intensity bias by comparison with other biased versions of the most similar kidneys in the training set. We prove significant improvements (p < 0.001) with respect to classic ASM and GC for kidney and CS segmentation, respectively. We use our semi-automatic method to compute the hydronephrosis index (HI) with an average error of 2.67 +/- 5.22 percentage points similar to the error of manual HI between different operators of 2.31 +/- 4.54 percentage points.

Original languageEnglish (US)
Pages (from-to)259-266
Number of pages8
JournalMedical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Volume16
Issue numberPt 3
StatePublished - Dec 1 2013

Fingerprint

Pediatrics
Kidney
Hydronephrosis

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Automatic analysis of pediatric renal ultrasound using shape, anatomical and image acquisition priors. / Kang, Xin; Safdar, Nabile; Myers, Emmarie; Martin, Aaron D.; Grisan, Enrico; Peters, Craig A; Linguraru, Marius George.

In: Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention, Vol. 16, No. Pt 3, 01.12.2013, p. 259-266.

Research output: Contribution to journalArticle

@article{d9af3f2d6edf41a19e0c174a19ca24e0,
title = "Automatic analysis of pediatric renal ultrasound using shape, anatomical and image acquisition priors.",
abstract = "In this paper we present a segmentation method for ultrasound (US) images of the pediatric kidney, a difficult and barely studied problem. Our method segments the kidney on 2D sagittal US images and relies on minimal user intervention and a combination of improvements made to the Active Shape Model (ASM) framework. Our contributions include particle swarm initialization and profile training with rotation correction. We also introduce our methodology for segmentation of the kidney's collecting system (CS), based on graph-cuts (GC) with intensity and positional priors. Our intensity model corrects for intensity bias by comparison with other biased versions of the most similar kidneys in the training set. We prove significant improvements (p < 0.001) with respect to classic ASM and GC for kidney and CS segmentation, respectively. We use our semi-automatic method to compute the hydronephrosis index (HI) with an average error of 2.67 +/- 5.22 percentage points similar to the error of manual HI between different operators of 2.31 +/- 4.54 percentage points.",
author = "Xin Kang and Nabile Safdar and Emmarie Myers and Martin, {Aaron D.} and Enrico Grisan and Peters, {Craig A} and Linguraru, {Marius George}",
year = "2013",
month = "12",
day = "1",
language = "English (US)",
volume = "16",
pages = "259--266",
journal = "Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention",
number = "Pt 3",

}

TY - JOUR

T1 - Automatic analysis of pediatric renal ultrasound using shape, anatomical and image acquisition priors.

AU - Kang, Xin

AU - Safdar, Nabile

AU - Myers, Emmarie

AU - Martin, Aaron D.

AU - Grisan, Enrico

AU - Peters, Craig A

AU - Linguraru, Marius George

PY - 2013/12/1

Y1 - 2013/12/1

N2 - In this paper we present a segmentation method for ultrasound (US) images of the pediatric kidney, a difficult and barely studied problem. Our method segments the kidney on 2D sagittal US images and relies on minimal user intervention and a combination of improvements made to the Active Shape Model (ASM) framework. Our contributions include particle swarm initialization and profile training with rotation correction. We also introduce our methodology for segmentation of the kidney's collecting system (CS), based on graph-cuts (GC) with intensity and positional priors. Our intensity model corrects for intensity bias by comparison with other biased versions of the most similar kidneys in the training set. We prove significant improvements (p < 0.001) with respect to classic ASM and GC for kidney and CS segmentation, respectively. We use our semi-automatic method to compute the hydronephrosis index (HI) with an average error of 2.67 +/- 5.22 percentage points similar to the error of manual HI between different operators of 2.31 +/- 4.54 percentage points.

AB - In this paper we present a segmentation method for ultrasound (US) images of the pediatric kidney, a difficult and barely studied problem. Our method segments the kidney on 2D sagittal US images and relies on minimal user intervention and a combination of improvements made to the Active Shape Model (ASM) framework. Our contributions include particle swarm initialization and profile training with rotation correction. We also introduce our methodology for segmentation of the kidney's collecting system (CS), based on graph-cuts (GC) with intensity and positional priors. Our intensity model corrects for intensity bias by comparison with other biased versions of the most similar kidneys in the training set. We prove significant improvements (p < 0.001) with respect to classic ASM and GC for kidney and CS segmentation, respectively. We use our semi-automatic method to compute the hydronephrosis index (HI) with an average error of 2.67 +/- 5.22 percentage points similar to the error of manual HI between different operators of 2.31 +/- 4.54 percentage points.

UR - http://www.scopus.com/inward/record.url?scp=84894629732&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84894629732&partnerID=8YFLogxK

M3 - Article

VL - 16

SP - 259

EP - 266

JO - Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention

JF - Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention

IS - Pt 3

ER -