Isointense infant brain MRI segmentation with a dilated convolutional neural network

P. Moeskops; J.P.W. Pluim

Isointense infant brain MRI segmentation with a dilated convolutional neural network

P. Moeskops, J.P.W. Pluim

Medical Image Analysis

Research output: Contribution to conference › Paper › Academic

107 Downloads (Pure)

Abstract

Quantitative analysis of brain MRI at the age of 6 months is difficult because of the limited contrast between white matter and gray matter. In this study, we use a dilated triplanar convolutional neural network in combination with a non-dilated 3D convolutional neural network for the segmentation of white matter, gray matter and cerebrospinal fluid in infant brain MR images, as provided by the MICCAI grand challenge on 6-month infant brain MRI segmentation.

Original language	English
Publication status	Published - 9 Aug 2017
Event	MICCAI Grand Challenge on iSeg-2017 : 6-month infant brain MRI Segmentation - Quebec City, Canada Duration: 14 Sept 2017 → 14 Sept 2017 http://iseg2017.web.unc.edu/

Conference

Conference	MICCAI Grand Challenge on iSeg-2017 : 6-month infant brain MRI Segmentation
Country/Territory	Canada
City	Quebec City
Period	14/09/17 → 14/09/17
Internet address	http://iseg2017.web.unc.edu/

Access to Document

arXiv versionSubmitted manuscript, 225 KB

https://arxiv.org/pdf/1708.02757.pdf

Cite this

@conference{6bc2335828734249ab6a9bfc55ef95dc,

title = "Isointense infant brain MRI segmentation with a dilated convolutional neural network",

abstract = "Quantitative analysis of brain MRI at the age of 6 months is difficult because of the limited contrast between white matter and gray matter. In this study, we use a dilated triplanar convolutional neural network in combination with a non-dilated 3D convolutional neural network for the segmentation of white matter, gray matter and cerebrospinal fluid in infant brain MR images, as provided by the MICCAI grand challenge on 6-month infant brain MRI segmentation.",

keywords = "cs.CV",

author = "P. Moeskops and J.P.W. Pluim",

note = "MICCAI grand challenge on 6-month infant brain MRI segmentation; MICCAI Grand Challenge on iSeg-2017 : 6-month infant brain MRI Segmentation ; Conference date: 14-09-2017 Through 14-09-2017",

year = "2017",

month = aug,

day = "9",

language = "English",

url = "http://iseg2017.web.unc.edu/",

}

TY - CONF

T1 - Isointense infant brain MRI segmentation with a dilated convolutional neural network

AU - Moeskops, P.

AU - Pluim, J.P.W.

N1 - MICCAI grand challenge on 6-month infant brain MRI segmentation

PY - 2017/8/9

Y1 - 2017/8/9

N2 - Quantitative analysis of brain MRI at the age of 6 months is difficult because of the limited contrast between white matter and gray matter. In this study, we use a dilated triplanar convolutional neural network in combination with a non-dilated 3D convolutional neural network for the segmentation of white matter, gray matter and cerebrospinal fluid in infant brain MR images, as provided by the MICCAI grand challenge on 6-month infant brain MRI segmentation.

AB - Quantitative analysis of brain MRI at the age of 6 months is difficult because of the limited contrast between white matter and gray matter. In this study, we use a dilated triplanar convolutional neural network in combination with a non-dilated 3D convolutional neural network for the segmentation of white matter, gray matter and cerebrospinal fluid in infant brain MR images, as provided by the MICCAI grand challenge on 6-month infant brain MRI segmentation.

KW - cs.CV

M3 - Paper

T2 - MICCAI Grand Challenge on iSeg-2017 : 6-month infant brain MRI Segmentation

Y2 - 14 September 2017 through 14 September 2017

ER -