Automating tumor classification with pixel-by-pixel contrast-enhanced ultrasound perfusion kinetics

Casey N. Ta, Yuko Kono, Christopher V. Barback, Robert F. Mattrey, Andrew C. Kummel

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Contrast-enhanced ultrasound (CEUS) enables highly specific time-resolved imaging of vasculature by intravenous injection of ∼2 μm gas filled microbubbles. To develop a quantitative automated diagnosis of breast tumors with CEUS, breast tumors were induced in rats by administration of N-ethyl-N-nitrosourea. A bolus injection of microbubbles was administered and CEUS videos of each tumor were acquired for at least 3 min. The time-intensity curve of each pixel within a region of interest (ROI) was analyzed to measure kinetic parameters associated with the wash-in, peak enhancement, and wash-out phases of microbubble bolus injections since it was expected that the aberrant vascularity of malignant tumors will result in faster and more diverse perfusion kinetics versus those of benign lesions. Parameters were classified using linear discriminant analysis to differentiate between benign and malignant tumors and improve diagnostic accuracy. Preliminary results with a small dataset (10 tumors, 19 videos) show 100 accuracy with fivefold cross-validation testing using as few as two choice variables for training and validation. Several of the parameters which provided the best differentiation between malignant and benign tumors employed comparative analysis of all the pixels in the ROI including enhancement coverage, fractional enhancement coverage times, and the standard deviation of the envelope curve difference normalized to the mean of the peak frame. Analysis of combinations of five variables demonstrated that pixel-by-pixel analysis produced the most robust information for tumor diagnostics and achieved 5 times greater separation of benign and malignant cases than ROI-based analysis.

Original languageEnglish (US)
Article number02C103
JournalJournal of Vacuum Science and Technology B:Nanotechnology and Microelectronics
Volume30
Issue number2
DOIs
StatePublished - Jan 1 2012

Fingerprint

Tumors
tumors
Ultrasonics
Pixels
pixels
Kinetics
kinetics
injection
breast
augmentation
Ethylnitrosourea
Discriminant analysis
curves
Kinetic parameters
lesions
rats
Rats
standard deviation
education
envelopes

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Instrumentation
  • Process Chemistry and Technology
  • Surfaces, Coatings and Films
  • Materials Chemistry
  • Electrical and Electronic Engineering

Cite this

Automating tumor classification with pixel-by-pixel contrast-enhanced ultrasound perfusion kinetics. / Ta, Casey N.; Kono, Yuko; Barback, Christopher V.; Mattrey, Robert F.; Kummel, Andrew C.

In: Journal of Vacuum Science and Technology B:Nanotechnology and Microelectronics, Vol. 30, No. 2, 02C103, 01.01.2012.

Research output: Contribution to journalArticle

@article{0184c874c4384f26a5669892cf0f19b7,
title = "Automating tumor classification with pixel-by-pixel contrast-enhanced ultrasound perfusion kinetics",
abstract = "Contrast-enhanced ultrasound (CEUS) enables highly specific time-resolved imaging of vasculature by intravenous injection of ∼2 μm gas filled microbubbles. To develop a quantitative automated diagnosis of breast tumors with CEUS, breast tumors were induced in rats by administration of N-ethyl-N-nitrosourea. A bolus injection of microbubbles was administered and CEUS videos of each tumor were acquired for at least 3 min. The time-intensity curve of each pixel within a region of interest (ROI) was analyzed to measure kinetic parameters associated with the wash-in, peak enhancement, and wash-out phases of microbubble bolus injections since it was expected that the aberrant vascularity of malignant tumors will result in faster and more diverse perfusion kinetics versus those of benign lesions. Parameters were classified using linear discriminant analysis to differentiate between benign and malignant tumors and improve diagnostic accuracy. Preliminary results with a small dataset (10 tumors, 19 videos) show 100 accuracy with fivefold cross-validation testing using as few as two choice variables for training and validation. Several of the parameters which provided the best differentiation between malignant and benign tumors employed comparative analysis of all the pixels in the ROI including enhancement coverage, fractional enhancement coverage times, and the standard deviation of the envelope curve difference normalized to the mean of the peak frame. Analysis of combinations of five variables demonstrated that pixel-by-pixel analysis produced the most robust information for tumor diagnostics and achieved 5 times greater separation of benign and malignant cases than ROI-based analysis.",
author = "Ta, {Casey N.} and Yuko Kono and Barback, {Christopher V.} and Mattrey, {Robert F.} and Kummel, {Andrew C.}",
year = "2012",
month = "1",
day = "1",
doi = "10.1116/1.3692962",
language = "English (US)",
volume = "30",
journal = "Journal of Vacuum Science and Technology B:Nanotechnology and Microelectronics",
issn = "2166-2746",
publisher = "AVS Science and Technology Society",
number = "2",

}

TY - JOUR

T1 - Automating tumor classification with pixel-by-pixel contrast-enhanced ultrasound perfusion kinetics

AU - Ta, Casey N.

AU - Kono, Yuko

AU - Barback, Christopher V.

AU - Mattrey, Robert F.

AU - Kummel, Andrew C.

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Contrast-enhanced ultrasound (CEUS) enables highly specific time-resolved imaging of vasculature by intravenous injection of ∼2 μm gas filled microbubbles. To develop a quantitative automated diagnosis of breast tumors with CEUS, breast tumors were induced in rats by administration of N-ethyl-N-nitrosourea. A bolus injection of microbubbles was administered and CEUS videos of each tumor were acquired for at least 3 min. The time-intensity curve of each pixel within a region of interest (ROI) was analyzed to measure kinetic parameters associated with the wash-in, peak enhancement, and wash-out phases of microbubble bolus injections since it was expected that the aberrant vascularity of malignant tumors will result in faster and more diverse perfusion kinetics versus those of benign lesions. Parameters were classified using linear discriminant analysis to differentiate between benign and malignant tumors and improve diagnostic accuracy. Preliminary results with a small dataset (10 tumors, 19 videos) show 100 accuracy with fivefold cross-validation testing using as few as two choice variables for training and validation. Several of the parameters which provided the best differentiation between malignant and benign tumors employed comparative analysis of all the pixels in the ROI including enhancement coverage, fractional enhancement coverage times, and the standard deviation of the envelope curve difference normalized to the mean of the peak frame. Analysis of combinations of five variables demonstrated that pixel-by-pixel analysis produced the most robust information for tumor diagnostics and achieved 5 times greater separation of benign and malignant cases than ROI-based analysis.

AB - Contrast-enhanced ultrasound (CEUS) enables highly specific time-resolved imaging of vasculature by intravenous injection of ∼2 μm gas filled microbubbles. To develop a quantitative automated diagnosis of breast tumors with CEUS, breast tumors were induced in rats by administration of N-ethyl-N-nitrosourea. A bolus injection of microbubbles was administered and CEUS videos of each tumor were acquired for at least 3 min. The time-intensity curve of each pixel within a region of interest (ROI) was analyzed to measure kinetic parameters associated with the wash-in, peak enhancement, and wash-out phases of microbubble bolus injections since it was expected that the aberrant vascularity of malignant tumors will result in faster and more diverse perfusion kinetics versus those of benign lesions. Parameters were classified using linear discriminant analysis to differentiate between benign and malignant tumors and improve diagnostic accuracy. Preliminary results with a small dataset (10 tumors, 19 videos) show 100 accuracy with fivefold cross-validation testing using as few as two choice variables for training and validation. Several of the parameters which provided the best differentiation between malignant and benign tumors employed comparative analysis of all the pixels in the ROI including enhancement coverage, fractional enhancement coverage times, and the standard deviation of the envelope curve difference normalized to the mean of the peak frame. Analysis of combinations of five variables demonstrated that pixel-by-pixel analysis produced the most robust information for tumor diagnostics and achieved 5 times greater separation of benign and malignant cases than ROI-based analysis.

UR - http://www.scopus.com/inward/record.url?scp=84861580869&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861580869&partnerID=8YFLogxK

U2 - 10.1116/1.3692962

DO - 10.1116/1.3692962

M3 - Article

C2 - 23616934

AN - SCOPUS:84861580869

VL - 30

JO - Journal of Vacuum Science and Technology B:Nanotechnology and Microelectronics

JF - Journal of Vacuum Science and Technology B:Nanotechnology and Microelectronics

SN - 2166-2746

IS - 2

M1 - 02C103

ER -