Optimal input configuration of dynamic contrast enhanced MRI in convolutional neural networks for liver segmentation

Marielle J.A. Jansen, Hugo J. Kuijf, Josien P. W. Pluim

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Most MRI liver segmentation methods use a structural 3D scan as input, such as a T1 or T2 weighted scan. Segmentation performance may be improved by utilizing both structural and functional information, as contained in dynamic contrast enhanced (DCE) MR series. Dynamic information can be incorporated in a segmentation method based on convolutional neural networks in a number of ways. In this study, the optimal input configuration of DCE MR images for convolutional neural networks (CNNs) is studied. The performance of three different input configurations for CNNs is studied for a liver segmentation task. The three configurations are I) one phase image of the DCE-MR series as input image; II) the separate phases of the DCE-MR as input images; and III) the separate phases of the DCE-MR as channels of one input image. The three input configurations are fed into a dilated fully convolutional network and into a small U-net. The CNNs were trained using 19 annotated DCE-MR series and tested on another 19 annotated DCE-MR series. The performance of the three input configurations for both networks is evaluated against manual annotations. The results show that both neural networks perform better when the separate phases of the DCE-MR series are used as channels of an input image in comparison to one phase as input image or the separate phases as input images. No significant difference between the performances of the two network architectures was found for the separate phases as channels of an input image.
Original languageEnglish
Article number109491V
Number of pages8
JournalProceedings of SPIE
Volume10949
DOIs
Publication statusPublished - 2019

Keywords

  • Dynamic contrast enhanced MRI
  • liver
  • segmentation
  • deep learning

Cite this

@article{f6c753bb6e7d405d97e361961f0128d7,
title = "Optimal input configuration of dynamic contrast enhanced MRI in convolutional neural networks for liver segmentation",
abstract = "Most MRI liver segmentation methods use a structural 3D scan as input, such as a T1 or T2 weighted scan. Segmentation performance may be improved by utilizing both structural and functional information, as contained in dynamic contrast enhanced (DCE) MR series. Dynamic information can be incorporated in a segmentation method based on convolutional neural networks in a number of ways. In this study, the optimal input configuration of DCE MR images for convolutional neural networks (CNNs) is studied. The performance of three different input configurations for CNNs is studied for a liver segmentation task. The three configurations are I) one phase image of the DCE-MR series as input image; II) the separate phases of the DCE-MR as input images; and III) the separate phases of the DCE-MR as channels of one input image. The three input configurations are fed into a dilated fully convolutional network and into a small U-net. The CNNs were trained using 19 annotated DCE-MR series and tested on another 19 annotated DCE-MR series. The performance of the three input configurations for both networks is evaluated against manual annotations. The results show that both neural networks perform better when the separate phases of the DCE-MR series are used as channels of an input image in comparison to one phase as input image or the separate phases as input images. No significant difference between the performances of the two network architectures was found for the separate phases as channels of an input image.",
keywords = "Dynamic contrast enhanced MRI, liver, segmentation, deep learning",
author = "Jansen, {Marielle J.A.} and Kuijf, {Hugo J.} and Pluim, {Josien P. W.}",
year = "2019",
doi = "10.1117/12.2506770",
language = "English",
volume = "10949",
journal = "Proceedings of SPIE",
issn = "0277-786X",
publisher = "SPIE",

}

Optimal input configuration of dynamic contrast enhanced MRI in convolutional neural networks for liver segmentation. / Jansen, Marielle J.A.; Kuijf, Hugo J.; Pluim, Josien P. W.

In: Proceedings of SPIE, Vol. 10949, 109491V, 2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Optimal input configuration of dynamic contrast enhanced MRI in convolutional neural networks for liver segmentation

AU - Jansen, Marielle J.A.

AU - Kuijf, Hugo J.

AU - Pluim, Josien P. W.

PY - 2019

Y1 - 2019

N2 - Most MRI liver segmentation methods use a structural 3D scan as input, such as a T1 or T2 weighted scan. Segmentation performance may be improved by utilizing both structural and functional information, as contained in dynamic contrast enhanced (DCE) MR series. Dynamic information can be incorporated in a segmentation method based on convolutional neural networks in a number of ways. In this study, the optimal input configuration of DCE MR images for convolutional neural networks (CNNs) is studied. The performance of three different input configurations for CNNs is studied for a liver segmentation task. The three configurations are I) one phase image of the DCE-MR series as input image; II) the separate phases of the DCE-MR as input images; and III) the separate phases of the DCE-MR as channels of one input image. The three input configurations are fed into a dilated fully convolutional network and into a small U-net. The CNNs were trained using 19 annotated DCE-MR series and tested on another 19 annotated DCE-MR series. The performance of the three input configurations for both networks is evaluated against manual annotations. The results show that both neural networks perform better when the separate phases of the DCE-MR series are used as channels of an input image in comparison to one phase as input image or the separate phases as input images. No significant difference between the performances of the two network architectures was found for the separate phases as channels of an input image.

AB - Most MRI liver segmentation methods use a structural 3D scan as input, such as a T1 or T2 weighted scan. Segmentation performance may be improved by utilizing both structural and functional information, as contained in dynamic contrast enhanced (DCE) MR series. Dynamic information can be incorporated in a segmentation method based on convolutional neural networks in a number of ways. In this study, the optimal input configuration of DCE MR images for convolutional neural networks (CNNs) is studied. The performance of three different input configurations for CNNs is studied for a liver segmentation task. The three configurations are I) one phase image of the DCE-MR series as input image; II) the separate phases of the DCE-MR as input images; and III) the separate phases of the DCE-MR as channels of one input image. The three input configurations are fed into a dilated fully convolutional network and into a small U-net. The CNNs were trained using 19 annotated DCE-MR series and tested on another 19 annotated DCE-MR series. The performance of the three input configurations for both networks is evaluated against manual annotations. The results show that both neural networks perform better when the separate phases of the DCE-MR series are used as channels of an input image in comparison to one phase as input image or the separate phases as input images. No significant difference between the performances of the two network architectures was found for the separate phases as channels of an input image.

KW - Dynamic contrast enhanced MRI

KW - liver

KW - segmentation

KW - deep learning

U2 - 10.1117/12.2506770

DO - 10.1117/12.2506770

M3 - Article

VL - 10949

JO - Proceedings of SPIE

JF - Proceedings of SPIE

SN - 0277-786X

M1 - 109491V

ER -