An Early Diagnosis of Oral Cancer based on Three-Dimensional Convolutional Neural Networks
Three-dimensional convolutional neural networks (3DCNNs), a rapidly evolving modality of deep learning, has gained popularity in many fields. For oral cancers, CT images are traditionally processed using two-dimensional input, without considering information between lesion slices. In this paper, we...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8887444/ |
| id |
doaj-2b05116158114300800476d5d8c7ccfe |
|---|---|
| record_format |
Article |
| spelling |
doaj-2b05116158114300800476d5d8c7ccfe2021-04-05T17:32:10ZengIEEEIEEE Access2169-35362019-01-01715860315861110.1109/ACCESS.2019.29502868887444An Early Diagnosis of Oral Cancer based on Three-Dimensional Convolutional Neural NetworksShipu Xu0https://orcid.org/0000-0003-4721-0905Chang Liu1https://orcid.org/0000-0002-1213-9814Yongshuo Zong2Sirui Chen3Yiwen Lu4Longzhi Yang5https://orcid.org/0000-0003-2115-4909Eddie Y. K. Ng6Yongtong Wang7Yunsheng Wang8Yong Liu9Wenwen Hu10Chenxi Zhang11https://orcid.org/0000-0002-1336-9451Department of Software Engineering, Tongji University, Shanghai, ChinaSchool of Information Engineering, Nanchang Hangkong University, Nanchang, ChinaDepartment of Computer Science, Tongji University, Shanghai, ChinaDepartment of Computer Science, Tongji University, Shanghai, ChinaDepartment of Computer Science, Tongji University, Shanghai, ChinaDepartment of Computer and Information Sciences, Northumbria University, Newcastle upon Tyne, U.K.School of Mechanical and Aerospace Engineering, Nanyang Technological University, SingaporeDepartment of Computer Science, Tongji University, Shanghai, ChinaAgricultural Information Institute of Science and Technology, Shanghai Academy of Agricultural Sciences, Shanghai, ChinaAgricultural Information Institute of Science and Technology, Shanghai Academy of Agricultural Sciences, Shanghai, ChinaAgricultural Information Institute of Science and Technology, Shanghai Academy of Agricultural Sciences, Shanghai, ChinaDepartment of Software Engineering, Tongji University, Shanghai, ChinaThree-dimensional convolutional neural networks (3DCNNs), a rapidly evolving modality of deep learning, has gained popularity in many fields. For oral cancers, CT images are traditionally processed using two-dimensional input, without considering information between lesion slices. In this paper, we established a 3DCNNs-based image processing algorithm for the early diagnosis of oral cancers, which was compared with a 2DCNNs-based algorithm. The 3D and 2D CNNs were constructed using the same hierarchical structure to profile oral tumors as benign or malignant. Our results showed that 3DCNNs with dynamic characteristics of the enhancement rate image performed better than 2DCNNS with single enhancement sequence for the discrimination of oral cancer lesions. Our data indicate that spatial features and spatial dynamics extracted from 3DCNNs may inform future design of CT-assisted diagnosis system.https://ieeexplore.ieee.org/document/8887444/2DCNNs3DCNNsCT imagesspatial featuresspatial dynamics extracted |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Shipu Xu Chang Liu Yongshuo Zong Sirui Chen Yiwen Lu Longzhi Yang Eddie Y. K. Ng Yongtong Wang Yunsheng Wang Yong Liu Wenwen Hu Chenxi Zhang |
| spellingShingle |
Shipu Xu Chang Liu Yongshuo Zong Sirui Chen Yiwen Lu Longzhi Yang Eddie Y. K. Ng Yongtong Wang Yunsheng Wang Yong Liu Wenwen Hu Chenxi Zhang An Early Diagnosis of Oral Cancer based on Three-Dimensional Convolutional Neural Networks IEEE Access 2DCNNs 3DCNNs CT images spatial features spatial dynamics extracted |
| author_facet |
Shipu Xu Chang Liu Yongshuo Zong Sirui Chen Yiwen Lu Longzhi Yang Eddie Y. K. Ng Yongtong Wang Yunsheng Wang Yong Liu Wenwen Hu Chenxi Zhang |
| author_sort |
Shipu Xu |
| title |
An Early Diagnosis of Oral Cancer based on Three-Dimensional Convolutional Neural Networks |
| title_short |
An Early Diagnosis of Oral Cancer based on Three-Dimensional Convolutional Neural Networks |
| title_full |
An Early Diagnosis of Oral Cancer based on Three-Dimensional Convolutional Neural Networks |
| title_fullStr |
An Early Diagnosis of Oral Cancer based on Three-Dimensional Convolutional Neural Networks |
| title_full_unstemmed |
An Early Diagnosis of Oral Cancer based on Three-Dimensional Convolutional Neural Networks |
| title_sort |
early diagnosis of oral cancer based on three-dimensional convolutional neural networks |
| publisher |
IEEE |
| series |
IEEE Access |
| issn |
2169-3536 |
| publishDate |
2019-01-01 |
| description |
Three-dimensional convolutional neural networks (3DCNNs), a rapidly evolving modality of deep learning, has gained popularity in many fields. For oral cancers, CT images are traditionally processed using two-dimensional input, without considering information between lesion slices. In this paper, we established a 3DCNNs-based image processing algorithm for the early diagnosis of oral cancers, which was compared with a 2DCNNs-based algorithm. The 3D and 2D CNNs were constructed using the same hierarchical structure to profile oral tumors as benign or malignant. Our results showed that 3DCNNs with dynamic characteristics of the enhancement rate image performed better than 2DCNNS with single enhancement sequence for the discrimination of oral cancer lesions. Our data indicate that spatial features and spatial dynamics extracted from 3DCNNs may inform future design of CT-assisted diagnosis system. |
| topic |
2DCNNs 3DCNNs CT images spatial features spatial dynamics extracted |
| url |
https://ieeexplore.ieee.org/document/8887444/ |
| work_keys_str_mv |
AT shipuxu anearlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT changliu anearlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT yongshuozong anearlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT siruichen anearlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT yiwenlu anearlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT longzhiyang anearlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT eddieykng anearlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT yongtongwang anearlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT yunshengwang anearlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT yongliu anearlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT wenwenhu anearlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT chenxizhang anearlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT shipuxu earlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT changliu earlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT yongshuozong earlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT siruichen earlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT yiwenlu earlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT longzhiyang earlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT eddieykng earlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT yongtongwang earlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT yunshengwang earlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT yongliu earlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT wenwenhu earlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks AT chenxizhang earlydiagnosisoforalcancerbasedonthreedimensionalconvolutionalneuralnetworks |
| _version_ |
1721539391456804864 |