期刊
IEEE ACCESS
卷 8, 期 -, 页码 92028-92038出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2020.2994592
关键词
Image segmentation; Teeth; Feature extraction; Biomedical imaging; Three-dimensional displays; Neural networks; Task analysis; Tooth segmentation; CBCT images; fully convolutional network; bottleneck architecture; conditional random field
资金
- Science and Technology Service Industry Demonstration Project of Sichuan [2019GFW126]
- Science and Technology Project of Sichuan [2019YFG0504]
- National Natural Science Foundation of China [61872066, U19A2078]
- Sichuan Science and Technology Innovation Project [2019006]
Accurate tooth segmentation from CBCT images is a crucial step for specialist to perform quantitative analysis, clinical diagnosis and operation. In this paper, we present a symmetric full convolutional network with residual block and Dense Conditional Random Field (DCRF), which can achieve accurate segmentation automatically for tooth images. The proposed method can not only strengthen feature propagation, but also boost feature reuse, which can be credited to the contracting path and the expanding path that extract and recover pixel cues sufficiently. To this end, we apply special deep bottleneck architectures (DBAs) and summation-based skip connection into our network to ensure accurate segmentation for much deeper neural network. Compared with previous methods which are based on conditional random field for original image intensity, our approach applies DCRF to the posterior probability generated by the proposed network. To avoid the interferences of noises around the tooth, we combine the pixel-level prediction capability of DCRF, which further enhance the segmentation performance. In the experiments, we verify the capabilities of our methods based on four evaluation indicators, which demonstrates the superiority of our method.
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