Transformer-Based Recognition Model for Ground-Glass Nodules from the View of Global 3D Asymmetry Feature Representation
Ground-glass nodules (GGN) are the main manifestation of early lung cancer, and accurate and efficient identification of ground-glass pulmonary nodules is of great significance for the treatment of lung diseases. In response to the problem of traditional machine learning requiring manual feature ext...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/15/12/2192 |
| _version_ | 1797379266221965312 |
|---|---|
| author | Jun Miao Maoxuan Zhang Yiru Chang Yuanhua Qiao |
| author_facet | Jun Miao Maoxuan Zhang Yiru Chang Yuanhua Qiao |
| author_sort | Jun Miao |
| collection | DOAJ |
| description | Ground-glass nodules (GGN) are the main manifestation of early lung cancer, and accurate and efficient identification of ground-glass pulmonary nodules is of great significance for the treatment of lung diseases. In response to the problem of traditional machine learning requiring manual feature extraction, and most deep learning models applied to 2D image classification, this paper proposes a Transformer-based recognition model for ground-glass nodules from the view of global 3D asymmetry feature representation. Firstly, a 3D convolutional neural network is used as the backbone to extract the features of the three-dimensional CT-image block of pulmonary nodules automatically; secondly, positional encoding information is added to the extracted feature map and input into the Transformer encoder layer for further extraction of global 3D asymmetry features, which can preserve more spatial information and obtain higher-order asymmetry feature representation; finally, the extracted asymmetry features are entered into a support vector machine or ELM-KNN model to further improve the recognition ability of the model. The experimental results show that the recognition accuracy of the proposed method reaches 95.89%, which is 4.79, 2.05, 4.11, and 2.74 percentage points higher than the common deep learning models of AlexNet, DenseNet121, GoogLeNet, and VGG19, respectively; compared with the latest models proposed in the field of pulmonary nodule classification, the accuracy has been improved by 2.05, 2.05, and 0.68 percentage points, respectively, which can effectively improve the recognition accuracy of ground-glass nodules. |
| first_indexed | 2024-03-08T20:19:41Z |
| format | Article |
| id | doaj.art-0a30ed8cfafa4f48aba995d1c8128913 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-08T20:19:41Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-0a30ed8cfafa4f48aba995d1c81289132023-12-22T14:45:22ZengMDPI AGSymmetry2073-89942023-12-011512219210.3390/sym15122192Transformer-Based Recognition Model for Ground-Glass Nodules from the View of Global 3D Asymmetry Feature RepresentationJun Miao0Maoxuan Zhang1Yiru Chang2Yuanhua Qiao3School of Computer Science, Beijing Information Science and Technology University, Beijing 100101, ChinaSchool of Computer Science, Beijing Information Science and Technology University, Beijing 100101, ChinaSchool of Computer Science, Beijing Information Science and Technology University, Beijing 100101, ChinaCollege of Applied Sciences, Beijing University of Technology, Beijing 100124, ChinaGround-glass nodules (GGN) are the main manifestation of early lung cancer, and accurate and efficient identification of ground-glass pulmonary nodules is of great significance for the treatment of lung diseases. In response to the problem of traditional machine learning requiring manual feature extraction, and most deep learning models applied to 2D image classification, this paper proposes a Transformer-based recognition model for ground-glass nodules from the view of global 3D asymmetry feature representation. Firstly, a 3D convolutional neural network is used as the backbone to extract the features of the three-dimensional CT-image block of pulmonary nodules automatically; secondly, positional encoding information is added to the extracted feature map and input into the Transformer encoder layer for further extraction of global 3D asymmetry features, which can preserve more spatial information and obtain higher-order asymmetry feature representation; finally, the extracted asymmetry features are entered into a support vector machine or ELM-KNN model to further improve the recognition ability of the model. The experimental results show that the recognition accuracy of the proposed method reaches 95.89%, which is 4.79, 2.05, 4.11, and 2.74 percentage points higher than the common deep learning models of AlexNet, DenseNet121, GoogLeNet, and VGG19, respectively; compared with the latest models proposed in the field of pulmonary nodule classification, the accuracy has been improved by 2.05, 2.05, and 0.68 percentage points, respectively, which can effectively improve the recognition accuracy of ground-glass nodules.https://www.mdpi.com/2073-8994/15/12/2192ground-glass nodules3D ResNettransformersupport vector machineELM-KNN |
| spellingShingle | Jun Miao Maoxuan Zhang Yiru Chang Yuanhua Qiao Transformer-Based Recognition Model for Ground-Glass Nodules from the View of Global 3D Asymmetry Feature Representation Symmetry ground-glass nodules 3D ResNet transformer support vector machine ELM-KNN |
| title | Transformer-Based Recognition Model for Ground-Glass Nodules from the View of Global 3D Asymmetry Feature Representation |
| title_full | Transformer-Based Recognition Model for Ground-Glass Nodules from the View of Global 3D Asymmetry Feature Representation |
| title_fullStr | Transformer-Based Recognition Model for Ground-Glass Nodules from the View of Global 3D Asymmetry Feature Representation |
| title_full_unstemmed | Transformer-Based Recognition Model for Ground-Glass Nodules from the View of Global 3D Asymmetry Feature Representation |
| title_short | Transformer-Based Recognition Model for Ground-Glass Nodules from the View of Global 3D Asymmetry Feature Representation |
| title_sort | transformer based recognition model for ground glass nodules from the view of global 3d asymmetry feature representation |
| topic | ground-glass nodules 3D ResNet transformer support vector machine ELM-KNN |
| url | https://www.mdpi.com/2073-8994/15/12/2192 |
| work_keys_str_mv | AT junmiao transformerbasedrecognitionmodelforgroundglassnodulesfromtheviewofglobal3dasymmetryfeaturerepresentation AT maoxuanzhang transformerbasedrecognitionmodelforgroundglassnodulesfromtheviewofglobal3dasymmetryfeaturerepresentation AT yiruchang transformerbasedrecognitionmodelforgroundglassnodulesfromtheviewofglobal3dasymmetryfeaturerepresentation AT yuanhuaqiao transformerbasedrecognitionmodelforgroundglassnodulesfromtheviewofglobal3dasymmetryfeaturerepresentation |