Journal
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
Volume 54, Issue -, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.bspc.2019.101613
Keywords
Infant brain segmentation; Fully convolutional neural networks; DenseNet; skip-connection
Categories
Funding
- Basic Science Research Program through the National Research Foundation of Korea (NRF) - Ministry of Education [2017R1D1A1B03031752]
- NRF - Korea government (MSIT) [NRF-2018R1C1B6007462]
- MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program [IITP-2019-2018-0-01798]
- National Research Foundation of Korea [2017R1D1A1B03031752] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
Ask authors/readers for more resources
Automatic 6-month infant brain tissue segmentation of magnetic resonance imaging (MRI) is still less accurate owing to the low intensity contrast among tissues. To tackle the problem, we introduce an accurate segmentation method for volumetric infant brain MRI built upon a densely connected network that achieves state-of-the-art accuracy. Specifically, we carefully design a fully convolutional densely connected network with skip connections such that the information from different levels of dense blocks can be directly combined to achieve highly accurate segmentation results. The proposed network, called 3D-SkipDenseSeg, exploits the advantage of the recently DenseNet for classification task and extends this to segment the 6-month infant brain tissue segmentation of magnetic resonance imaging (MRI). Experimental results demonstrate a competitive performance with regard to both segmentation accuracy and parameter efficiency of the proposed method over the existing methods; namely, the proposed 3D-SkipDenseSeg achieved the best dice similarity coefficient (DSC) of 90.37 +/- 1.38% (WM), 92.27 +/- 0.81% (GM), and 95.79 +/- 0.54% (CSF) among the 21 participating teams in the 6-month infant brain dataset (iSeg-2017) and required only 10-30% of the parameters compared to similar deep learning-based methods. (C) 2019 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available