Ultrasound based computer-aided-diagnosis of kidneys for pediatric hydronephrosis

Juan J. Cerrolaza, Craig A Peters, Aaron D. Martin, Emmarie Myers, Nabile Safdar, Marius G. Linguraru

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

6 Citations (Scopus)

Abstract

Ultrasound is the mainstay of imaging for pediatric hydronephrosis, though its potential as diagnostic tool is limited by its subjective assessment, and lack of correlation with renal function. Therefore, all cases showing signs of hydronephrosis undergo further invasive studies, like diuretic renogram, in order to assess the actual renal function. Under the hypothesis that renal morphology is correlated with renal function, a new ultrasound based computer-aided diagnosis (CAD) tool for pediatric hydronephrosis is presented. From 2D ultrasound, a novel set of morphological features of the renal collecting systems and the parenchyma, is automatically extracted using image analysis techniques. From the original set of features, including size, geometric and curvature descriptors, a subset of ten features are selected as predictive variables, combining a feature selection technique and area under the curve filtering. Using the washout half time (T1/2) as indicative of renal obstruction, two groups are defined. Those cases whose T1/2 is above 30 minutes are considered to be severe, while the rest would be in the safety zone, where diuretic renography could be avoided. Two different classification techniques are evaluated (logistic regression, and support vector machines). Adjusting the probability decision thresholds to operate at the point of maximum sensitivity, i.e., preventing any severe case be misclassified, specificities of 53%, and 75% are achieved, for the logistic regression and the support vector machine classifier, respectively. The proposed CAD system allows to establish a link between non-invasive non-ionizing imaging techniques and renal function, limiting the need for invasive and ionizing diuretic renography.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2014
Subtitle of host publicationComputer-Aided Diagnosis
PublisherSPIE
Volume9035
ISBN (Print)9780819498281
DOIs
StatePublished - Jan 1 2014
EventMedical Imaging 2014: Computer-Aided Diagnosis - San Diego, CA, United States
Duration: Feb 18 2014Feb 20 2014

Other

OtherMedical Imaging 2014: Computer-Aided Diagnosis
CountryUnited States
CitySan Diego, CA
Period2/18/142/20/14

Fingerprint

renal function
Computer aided diagnosis
Pediatrics
diuretics
Hydronephrosis
kidneys
Ultrasonics
Diuretics
Kidney
logistics
Support vector machines
Logistics
regression analysis
Radioisotope Renography
Imaging techniques
fallout
classifiers
image analysis
imaging techniques
Image analysis

Keywords

  • Computer-aided diagnosis
  • Hydronephrosis
  • Kidney
  • Machine learning
  • Ultrasound imaging

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Cerrolaza, J. J., Peters, C. A., Martin, A. D., Myers, E., Safdar, N., & Linguraru, M. G. (2014). Ultrasound based computer-aided-diagnosis of kidneys for pediatric hydronephrosis. In Medical Imaging 2014: Computer-Aided Diagnosis (Vol. 9035). [90352T] SPIE. https://doi.org/10.1117/12.2043072

Ultrasound based computer-aided-diagnosis of kidneys for pediatric hydronephrosis. / Cerrolaza, Juan J.; Peters, Craig A; Martin, Aaron D.; Myers, Emmarie; Safdar, Nabile; Linguraru, Marius G.

Medical Imaging 2014: Computer-Aided Diagnosis. Vol. 9035 SPIE, 2014. 90352T.

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

Cerrolaza, JJ, Peters, CA, Martin, AD, Myers, E, Safdar, N & Linguraru, MG 2014, Ultrasound based computer-aided-diagnosis of kidneys for pediatric hydronephrosis. in Medical Imaging 2014: Computer-Aided Diagnosis. vol. 9035, 90352T, SPIE, Medical Imaging 2014: Computer-Aided Diagnosis, San Diego, CA, United States, 2/18/14. https://doi.org/10.1117/12.2043072
Cerrolaza JJ, Peters CA, Martin AD, Myers E, Safdar N, Linguraru MG. Ultrasound based computer-aided-diagnosis of kidneys for pediatric hydronephrosis. In Medical Imaging 2014: Computer-Aided Diagnosis. Vol. 9035. SPIE. 2014. 90352T https://doi.org/10.1117/12.2043072
Cerrolaza, Juan J. ; Peters, Craig A ; Martin, Aaron D. ; Myers, Emmarie ; Safdar, Nabile ; Linguraru, Marius G. / Ultrasound based computer-aided-diagnosis of kidneys for pediatric hydronephrosis. Medical Imaging 2014: Computer-Aided Diagnosis. Vol. 9035 SPIE, 2014.
@inproceedings{bbb69129f7634330818e1012ef337065,
title = "Ultrasound based computer-aided-diagnosis of kidneys for pediatric hydronephrosis",
abstract = "Ultrasound is the mainstay of imaging for pediatric hydronephrosis, though its potential as diagnostic tool is limited by its subjective assessment, and lack of correlation with renal function. Therefore, all cases showing signs of hydronephrosis undergo further invasive studies, like diuretic renogram, in order to assess the actual renal function. Under the hypothesis that renal morphology is correlated with renal function, a new ultrasound based computer-aided diagnosis (CAD) tool for pediatric hydronephrosis is presented. From 2D ultrasound, a novel set of morphological features of the renal collecting systems and the parenchyma, is automatically extracted using image analysis techniques. From the original set of features, including size, geometric and curvature descriptors, a subset of ten features are selected as predictive variables, combining a feature selection technique and area under the curve filtering. Using the washout half time (T1/2) as indicative of renal obstruction, two groups are defined. Those cases whose T1/2 is above 30 minutes are considered to be severe, while the rest would be in the safety zone, where diuretic renography could be avoided. Two different classification techniques are evaluated (logistic regression, and support vector machines). Adjusting the probability decision thresholds to operate at the point of maximum sensitivity, i.e., preventing any severe case be misclassified, specificities of 53{\%}, and 75{\%} are achieved, for the logistic regression and the support vector machine classifier, respectively. The proposed CAD system allows to establish a link between non-invasive non-ionizing imaging techniques and renal function, limiting the need for invasive and ionizing diuretic renography.",
keywords = "Computer-aided diagnosis, Hydronephrosis, Kidney, Machine learning, Ultrasound imaging",
author = "Cerrolaza, {Juan J.} and Peters, {Craig A} and Martin, {Aaron D.} and Emmarie Myers and Nabile Safdar and Linguraru, {Marius G.}",
year = "2014",
month = "1",
day = "1",
doi = "10.1117/12.2043072",
language = "English (US)",
isbn = "9780819498281",
volume = "9035",
booktitle = "Medical Imaging 2014",
publisher = "SPIE",

}

TY - GEN

T1 - Ultrasound based computer-aided-diagnosis of kidneys for pediatric hydronephrosis

AU - Cerrolaza, Juan J.

AU - Peters, Craig A

AU - Martin, Aaron D.

AU - Myers, Emmarie

AU - Safdar, Nabile

AU - Linguraru, Marius G.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Ultrasound is the mainstay of imaging for pediatric hydronephrosis, though its potential as diagnostic tool is limited by its subjective assessment, and lack of correlation with renal function. Therefore, all cases showing signs of hydronephrosis undergo further invasive studies, like diuretic renogram, in order to assess the actual renal function. Under the hypothesis that renal morphology is correlated with renal function, a new ultrasound based computer-aided diagnosis (CAD) tool for pediatric hydronephrosis is presented. From 2D ultrasound, a novel set of morphological features of the renal collecting systems and the parenchyma, is automatically extracted using image analysis techniques. From the original set of features, including size, geometric and curvature descriptors, a subset of ten features are selected as predictive variables, combining a feature selection technique and area under the curve filtering. Using the washout half time (T1/2) as indicative of renal obstruction, two groups are defined. Those cases whose T1/2 is above 30 minutes are considered to be severe, while the rest would be in the safety zone, where diuretic renography could be avoided. Two different classification techniques are evaluated (logistic regression, and support vector machines). Adjusting the probability decision thresholds to operate at the point of maximum sensitivity, i.e., preventing any severe case be misclassified, specificities of 53%, and 75% are achieved, for the logistic regression and the support vector machine classifier, respectively. The proposed CAD system allows to establish a link between non-invasive non-ionizing imaging techniques and renal function, limiting the need for invasive and ionizing diuretic renography.

AB - Ultrasound is the mainstay of imaging for pediatric hydronephrosis, though its potential as diagnostic tool is limited by its subjective assessment, and lack of correlation with renal function. Therefore, all cases showing signs of hydronephrosis undergo further invasive studies, like diuretic renogram, in order to assess the actual renal function. Under the hypothesis that renal morphology is correlated with renal function, a new ultrasound based computer-aided diagnosis (CAD) tool for pediatric hydronephrosis is presented. From 2D ultrasound, a novel set of morphological features of the renal collecting systems and the parenchyma, is automatically extracted using image analysis techniques. From the original set of features, including size, geometric and curvature descriptors, a subset of ten features are selected as predictive variables, combining a feature selection technique and area under the curve filtering. Using the washout half time (T1/2) as indicative of renal obstruction, two groups are defined. Those cases whose T1/2 is above 30 minutes are considered to be severe, while the rest would be in the safety zone, where diuretic renography could be avoided. Two different classification techniques are evaluated (logistic regression, and support vector machines). Adjusting the probability decision thresholds to operate at the point of maximum sensitivity, i.e., preventing any severe case be misclassified, specificities of 53%, and 75% are achieved, for the logistic regression and the support vector machine classifier, respectively. The proposed CAD system allows to establish a link between non-invasive non-ionizing imaging techniques and renal function, limiting the need for invasive and ionizing diuretic renography.

KW - Computer-aided diagnosis

KW - Hydronephrosis

KW - Kidney

KW - Machine learning

KW - Ultrasound imaging

UR - http://www.scopus.com/inward/record.url?scp=84902108582&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902108582&partnerID=8YFLogxK

U2 - 10.1117/12.2043072

DO - 10.1117/12.2043072

M3 - Conference contribution

AN - SCOPUS:84902108582

SN - 9780819498281

VL - 9035

BT - Medical Imaging 2014

PB - SPIE

ER -