期刊
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
卷 108, 期 -, 页码 613-623出版社
ELSEVIER
DOI: 10.1016/j.future.2019.11.021
关键词
MRI; CNN; Infant brain segmentation; Densely connected blocks; Residual inception block
资金
- National Natural Science Foundation of China [61672250]
- Hubei Provincial Development and Reform Commission Project in China
Magnetic Resonance Imaging (MRI) is dominant modality for infant brain analysis. Segmenting the whole infant MRI brain into number of tissues such as Cerebrospinal fluid (CSF), White matter (WM), and Gray Matter (GM) are highly desirable in the clinical environment. However, traditional methods tend to be degrading due to low contrast between GM and WM in isointense phase (about 6-8 months of early life). Recently, Convolutional Neural Network (CNN) emerged as a robust intelligent approach to examine medical image. The UNet model is among the preferred CNN models that have been widely used for medical imaging applications and achieved excellent results. The UNet architecture is a combination of convolutional, pooling, and up-sampling layers. Recently, 3D-UNet architecture used to exploit 3D-contextual information of volumetric data in many applications. However, CNN faces challenge to distinguish the similar brain tissues. In this paper, we present a variant of 3D-UNet to extract the volumetric contextual information of medical data. We propose a novel combined architecture of dense connection, residual connection, and inception module. The proposed architecture contains three stages, namely the densely connected stage, a residual inception stage, and an upsampling stage. Our proposed approach provides state-of-art results in comparison to other existing approaches. This suggested approach achieves dice scores of 0.95, 0.905, and 0.92 in CSF, WM, and GM tissues respectively. (C) 2019 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据