A Symmetric Fully Convolutional Residual Network With DCRF for Accurate Tooth Segmentation
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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9093915/ |
| _version_ | 1818445549489094656 |
|---|---|
| author | Yunbo Rao Yilin Wang Fanman Meng Jiansu Pu Jihong Sun Qifei Wang |
| author_facet | Yunbo Rao Yilin Wang Fanman Meng Jiansu Pu Jihong Sun Qifei Wang |
| author_sort | Yunbo Rao |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-14T19:33:36Z |
| format | Article |
| id | doaj.art-29f037feff304e2c99470079b8899d3d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T19:33:36Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-29f037feff304e2c99470079b8899d3d2022-12-21T22:50:00ZengIEEEIEEE Access2169-35362020-01-018920289203810.1109/ACCESS.2020.29945929093915A Symmetric Fully Convolutional Residual Network With DCRF for Accurate Tooth SegmentationYunbo Rao0https://orcid.org/0000-0001-5433-7379Yilin Wang1https://orcid.org/0000-0001-6816-3808Fanman Meng2https://orcid.org/0000-0002-3016-2567Jiansu Pu3Jihong Sun4Qifei Wang5School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Electronic Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Medicine, Zhejiang University, Zhejiang, ChinaDepartment of Electrical Engineering and Computer Sciences (EECS), University of California at Berkeley, Berkeley, CA, USAAccurate 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.https://ieeexplore.ieee.org/document/9093915/Tooth segmentationCBCT imagesfully convolutional networkbottleneck architectureconditional random field |
| spellingShingle | Yunbo Rao Yilin Wang Fanman Meng Jiansu Pu Jihong Sun Qifei Wang A Symmetric Fully Convolutional Residual Network With DCRF for Accurate Tooth Segmentation IEEE Access Tooth segmentation CBCT images fully convolutional network bottleneck architecture conditional random field |
| title | A Symmetric Fully Convolutional Residual Network With DCRF for Accurate Tooth Segmentation |
| title_full | A Symmetric Fully Convolutional Residual Network With DCRF for Accurate Tooth Segmentation |
| title_fullStr | A Symmetric Fully Convolutional Residual Network With DCRF for Accurate Tooth Segmentation |
| title_full_unstemmed | A Symmetric Fully Convolutional Residual Network With DCRF for Accurate Tooth Segmentation |
| title_short | A Symmetric Fully Convolutional Residual Network With DCRF for Accurate Tooth Segmentation |
| title_sort | symmetric fully convolutional residual network with dcrf for accurate tooth segmentation |
| topic | Tooth segmentation CBCT images fully convolutional network bottleneck architecture conditional random field |
| url | https://ieeexplore.ieee.org/document/9093915/ |
| work_keys_str_mv | AT yunborao asymmetricfullyconvolutionalresidualnetworkwithdcrfforaccuratetoothsegmentation AT yilinwang asymmetricfullyconvolutionalresidualnetworkwithdcrfforaccuratetoothsegmentation AT fanmanmeng asymmetricfullyconvolutionalresidualnetworkwithdcrfforaccuratetoothsegmentation AT jiansupu asymmetricfullyconvolutionalresidualnetworkwithdcrfforaccuratetoothsegmentation AT jihongsun asymmetricfullyconvolutionalresidualnetworkwithdcrfforaccuratetoothsegmentation AT qifeiwang asymmetricfullyconvolutionalresidualnetworkwithdcrfforaccuratetoothsegmentation AT yunborao symmetricfullyconvolutionalresidualnetworkwithdcrfforaccuratetoothsegmentation AT yilinwang symmetricfullyconvolutionalresidualnetworkwithdcrfforaccuratetoothsegmentation AT fanmanmeng symmetricfullyconvolutionalresidualnetworkwithdcrfforaccuratetoothsegmentation AT jiansupu symmetricfullyconvolutionalresidualnetworkwithdcrfforaccuratetoothsegmentation AT jihongsun symmetricfullyconvolutionalresidualnetworkwithdcrfforaccuratetoothsegmentation AT qifeiwang symmetricfullyconvolutionalresidualnetworkwithdcrfforaccuratetoothsegmentation |