DRINet for Medical Image Segmentation

被引:226
作者
Chen, Liang [1 ,2 ]
Bentley, Paul [2 ]
Mori, Kensaku [3 ]
Misawa, Kazunari [4 ]
Fujiwara, Michitaka [5 ]
Rueckert, Daniel [1 ]
机构
[1] Imperial Coll London, Dept Comp, London SW7 2AZ, England
[2] Imperial Coll London, Div Brain Sci, Dept Med, London SW7 2AZ, England
[3] Nagoya Univ, Grad Sch Informat, Nagoya, Aichi 4648603, Japan
[4] Aichi Canc Ctr, Nagoya, Aichi 4648681, Japan
[5] Nagoya Univ Hosp, Nagoya, Aichi 4668560, Japan
基金
美国国家卫生研究院;
关键词
Convolutional neural network; medical image segmentation; brain atrophy; abdominal organ segmentation; AUTOMATIC SEGMENTATION; CEREBROSPINAL-FLUID; MULTIORGAN SEGMENTATION; PROBABILISTIC ATLAS; ISCHEMIC-STROKE;
D O I
10.1109/TMI.2018.2835303
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Convolutional neural networks (CNNs) have revolutionized medical image analysis over the past few years. The U-Net architecture is one of the most well-known CNN architectures for semantic segmentation and has achieved remarkable successes in many different medical image segmentation applications. The U-Net architecture consists of standard convolution layers, pooling layers, and upsampling layers. These convolution layers learn representative features of input images and construct segmentations based on the features. However, the features learned by standard convolution layers are not distinctive when the differences among different categories are subtle in terms of intensity, location, shape, and size. In this paper, we propose a novel CNN architecture, called Dense-Res-Inception Net (DRINet), which addresses this challenging problem. The proposed DRINet consists of three blocks, namely a convolutional block with dense connections, a deconvolutional block with residual inception modules, and an unpooling block. Our proposed architecture outperforms the U-Net in three different challenging applications, namely multi-class segmentation of cerebrospinal fluid on brain CT images, multi-organ segmentation on abdominal CT images, and multi-class brain tumor segmentation on MR images.
引用
收藏
页码:2453 / 2462
页数:10
相关论文
共 46 条
[1]  
[Anonymous], 2017, IMPROVING DEEP PANCR
[2]  
[Anonymous], P IEEE C COMP VIS PA
[3]  
[Anonymous], 2015, ARXIV PREPRINT ARXIV
[4]  
[Anonymous], PROC CVPR IEEE
[5]  
[Anonymous], P ICLR
[6]  
[Anonymous], 2017, SPATIAL AGGREGATION
[7]  
[Anonymous], 2017, C COMP VIS PATT REC
[8]  
[Anonymous], 2017, Cancer Imag. Arch.
[9]  
[Anonymous], 2015, Optimization
[10]   A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI [J].
Avendi, M. R. ;
Kheradvar, Arash ;
Jafarkhani, Hamid .
MEDICAL IMAGE ANALYSIS, 2016, 30 :108-119