3-D multi-parametric contrast-enhanced ultrasound for the prediction of prostate cancer

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Trans-rectal ultrasound-guided 12-core systematic biopsy (SBx) is the standard diagnostic pathway for prostate cancer (PCa) because of a lack of sufficiently accurate imaging. Quantification of 3-D dynamic contrast-enhanced ultrasound (US) might open the way for a targeted procedure in which biopsies are directed at lesions suspicious on imaging. This work describes the expansion of contrast US dispersion imaging algorithms to 3-D and compares its performance against malignant and benign disease. Furthermore, we examined the feasibility of a multi-parametric approach to predict SBx-core outcomes using machine learning. An area under the receiver operating characteristic (ROC) curve of 0.76 and 0.81 was obtained for all PCa and significant PCa, respectively, an improvement over previous US methods. We found that prostatitis, in particular, was a source of false-positive readings.
LanguageEnglish
JournalUltrasound in Medicine and Biology
DOIs
StateE-pub ahead of print - 10 Jul 2019

Fingerprint

Prostatic Neoplasms
cancer
predictions
machine learning
Biopsy
lesions
Prostatitis
receivers
ROC Curve
Reading
Ultrasonography
expansion
curves

Keywords

  • Prostate cancer
  • Systematic biopsy
  • Dynamic contrast-enhanced ultrasound
  • Contrast ultrasound dispersion imaging
  • 3-D
  • Machine learning

Cite this

@article{b8ed516b20b240a58c42b6935e9daf93,
title = "3-D multi-parametric contrast-enhanced ultrasound for the prediction of prostate cancer",
abstract = "Trans-rectal ultrasound-guided 12-core systematic biopsy (SBx) is the standard diagnostic pathway for prostate cancer (PCa) because of a lack of sufficiently accurate imaging. Quantification of 3-D dynamic contrast-enhanced ultrasound (US) might open the way for a targeted procedure in which biopsies are directed at lesions suspicious on imaging. This work describes the expansion of contrast US dispersion imaging algorithms to 3-D and compares its performance against malignant and benign disease. Furthermore, we examined the feasibility of a multi-parametric approach to predict SBx-core outcomes using machine learning. An area under the receiver operating characteristic (ROC) curve of 0.76 and 0.81 was obtained for all PCa and significant PCa, respectively, an improvement over previous US methods. We found that prostatitis, in particular, was a source of false-positive readings.",
keywords = "Prostate cancer, Systematic biopsy, Dynamic contrast-enhanced ultrasound, Contrast ultrasound dispersion imaging, 3-D, Machine learning",
author = "Wildeboer, {Rogier R.} and {van Sloun}, {Ruud J.G.} and Pintong Huang and Hessel Wijkstra and Massimo Mischi",
year = "2019",
month = "7",
day = "10",
doi = "10.1016/j.ultrasmedbio.2019.05.017",
language = "English",
journal = "Ultrasound in Medicine and Biology",
issn = "0301-5629",
publisher = "Elsevier",

}

TY - JOUR

T1 - 3-D multi-parametric contrast-enhanced ultrasound for the prediction of prostate cancer

AU - Wildeboer,Rogier R.

AU - van Sloun,Ruud J.G.

AU - Huang,Pintong

AU - Wijkstra,Hessel

AU - Mischi,Massimo

PY - 2019/7/10

Y1 - 2019/7/10

N2 - Trans-rectal ultrasound-guided 12-core systematic biopsy (SBx) is the standard diagnostic pathway for prostate cancer (PCa) because of a lack of sufficiently accurate imaging. Quantification of 3-D dynamic contrast-enhanced ultrasound (US) might open the way for a targeted procedure in which biopsies are directed at lesions suspicious on imaging. This work describes the expansion of contrast US dispersion imaging algorithms to 3-D and compares its performance against malignant and benign disease. Furthermore, we examined the feasibility of a multi-parametric approach to predict SBx-core outcomes using machine learning. An area under the receiver operating characteristic (ROC) curve of 0.76 and 0.81 was obtained for all PCa and significant PCa, respectively, an improvement over previous US methods. We found that prostatitis, in particular, was a source of false-positive readings.

AB - Trans-rectal ultrasound-guided 12-core systematic biopsy (SBx) is the standard diagnostic pathway for prostate cancer (PCa) because of a lack of sufficiently accurate imaging. Quantification of 3-D dynamic contrast-enhanced ultrasound (US) might open the way for a targeted procedure in which biopsies are directed at lesions suspicious on imaging. This work describes the expansion of contrast US dispersion imaging algorithms to 3-D and compares its performance against malignant and benign disease. Furthermore, we examined the feasibility of a multi-parametric approach to predict SBx-core outcomes using machine learning. An area under the receiver operating characteristic (ROC) curve of 0.76 and 0.81 was obtained for all PCa and significant PCa, respectively, an improvement over previous US methods. We found that prostatitis, in particular, was a source of false-positive readings.

KW - Prostate cancer

KW - Systematic biopsy

KW - Dynamic contrast-enhanced ultrasound

KW - Contrast ultrasound dispersion imaging

KW - 3-D

KW - Machine learning

U2 - 10.1016/j.ultrasmedbio.2019.05.017

DO - 10.1016/j.ultrasmedbio.2019.05.017

M3 - Article

JO - Ultrasound in Medicine and Biology

T2 - Ultrasound in Medicine and Biology

JF - Ultrasound in Medicine and Biology

SN - 0301-5629

ER -