Isointense infant brain MRI segmentation with a dilated convolutional neural network

P. Moeskops, J.P.W. Pluim

Research output: Contribution to conferencePaperAcademic

82 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 languageEnglish
Publication statusPublished - 9 Aug 2017
EventMICCAI Grand Challenge on iSeg-2017 : 6-month infant brain MRI Segmentation - Quebec City, Canada
Duration: 14 Sep 201714 Sep 2017
http://iseg2017.web.unc.edu/

Conference

ConferenceMICCAI Grand Challenge on iSeg-2017 : 6-month infant brain MRI Segmentation
CountryCanada
CityQuebec City
Period14/09/1714/09/17
Internet address

Cite this

Moeskops, P., & Pluim, J. P. W. (2017). Isointense infant brain MRI segmentation with a dilated convolutional neural network. Paper presented at MICCAI Grand Challenge on iSeg-2017 : 6-month infant brain MRI Segmentation, Quebec City, Canada. https://arxiv.org/pdf/1708.02757.pdf