False Positive Reduction of Pulmonary Nodules Based on Mixed Attentional Mechanism
In order to solve the problem of high false positives in the candidate detection stage of pulmonary nodules CAD system, this paper proposes a method to reduce false positives of pulmonary nodules based on mixed attention mechanism. The method can be used as an alternative to the most commonly used 3...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Editorial Office of Computerized Tomography Theory and Application
2022-02-01
|
| Series: | CT Lilun yu yingyong yanjiu |
| Subjects: | |
| Online Access: | https://www.cttacn.org.cn/cn/article/doi/10.15953/j.ctta.2021.002 |
| _version_ | 1797696330100899840 |
|---|---|
| author | Binghang TANG Yanfang WANG Li MA Qingwu CHEN Liwei SHAO Dehuang HUANG |
| author_facet | Binghang TANG Yanfang WANG Li MA Qingwu CHEN Liwei SHAO Dehuang HUANG |
| author_sort | Binghang TANG |
| collection | DOAJ |
| description | In order to solve the problem of high false positives in the candidate detection stage of pulmonary nodules CAD system, this paper proposes a method to reduce false positives of pulmonary nodules based on mixed attention mechanism. The method can be used as an alternative to the most commonly used 3D CNN classification model at the stage of false positive reduction. It can effectively avoid the problems of large number of parameters and computation in 3D CNN model. In this method, the 3D candidate nodule data is viewed as a slice sequence, and the temporal segment networks model is used in combination with the improved 2D ResNet-18 backbone network which contains mixed attention modules. On the basis of using 2D CNN, the spatial and temporal characteristics of the 3D slice data are effectively studied. Compared with the 3D CNN structure model for pulmonary nodules classification，the method proposed in this paper not only improves the accuracy of nodules classification but also reduces the number of model parameters and the inference time. |
| first_indexed | 2024-03-12T03:24:49Z |
| format | Article |
| id | doaj.art-38cc93025d8a410fa46274c52c0ef561 |
| institution | Directory Open Access Journal |
| issn | 1004-4140 |
| language | English |
| last_indexed | 2024-03-12T03:24:49Z |
| publishDate | 2022-02-01 |
| publisher | Editorial Office of Computerized Tomography Theory and Application |
| record_format | Article |
| series | CT Lilun yu yingyong yanjiu |
| spelling | doaj.art-38cc93025d8a410fa46274c52c0ef5612023-09-03T13:40:16ZengEditorial Office of Computerized Tomography Theory and ApplicationCT Lilun yu yingyong yanjiu1004-41402022-02-01311637210.15953/j.ctta.2021.0022021-002False Positive Reduction of Pulmonary Nodules Based on Mixed Attentional MechanismBinghang TANG0Yanfang WANG1Li MA2Qingwu CHEN3Liwei SHAO4Dehuang HUANG5Zhongshan City People’s Hospital, Zhongshan 528404, ChinaZhongshan Yangshi Technology Co., Ltd, Zhongshan 528400, ChinaZhongshan Yangshi Technology Co., Ltd, Zhongshan 528400, ChinaZhongshan Yangshi Technology Co., Ltd, Zhongshan 528400, ChinaZhongshan Research Institute, Beijing Institute of Technology, Zhongshan 528405, ChinaZhongshan Research Institute, Beijing Institute of Technology, Zhongshan 528405, ChinaIn order to solve the problem of high false positives in the candidate detection stage of pulmonary nodules CAD system, this paper proposes a method to reduce false positives of pulmonary nodules based on mixed attention mechanism. The method can be used as an alternative to the most commonly used 3D CNN classification model at the stage of false positive reduction. It can effectively avoid the problems of large number of parameters and computation in 3D CNN model. In this method, the 3D candidate nodule data is viewed as a slice sequence, and the temporal segment networks model is used in combination with the improved 2D ResNet-18 backbone network which contains mixed attention modules. On the basis of using 2D CNN, the spatial and temporal characteristics of the 3D slice data are effectively studied. Compared with the 3D CNN structure model for pulmonary nodules classification，the method proposed in this paper not only improves the accuracy of nodules classification but also reduces the number of model parameters and the inference time.https://www.cttacn.org.cn/cn/article/doi/10.15953/j.ctta.2021.002temporal segment networksmixed attentionpulmonary nodules |
| spellingShingle | Binghang TANG Yanfang WANG Li MA Qingwu CHEN Liwei SHAO Dehuang HUANG False Positive Reduction of Pulmonary Nodules Based on Mixed Attentional Mechanism CT Lilun yu yingyong yanjiu temporal segment networks mixed attention pulmonary nodules |
| title | False Positive Reduction of Pulmonary Nodules Based on Mixed Attentional Mechanism |
| title_full | False Positive Reduction of Pulmonary Nodules Based on Mixed Attentional Mechanism |
| title_fullStr | False Positive Reduction of Pulmonary Nodules Based on Mixed Attentional Mechanism |
| title_full_unstemmed | False Positive Reduction of Pulmonary Nodules Based on Mixed Attentional Mechanism |
| title_short | False Positive Reduction of Pulmonary Nodules Based on Mixed Attentional Mechanism |
| title_sort | false positive reduction of pulmonary nodules based on mixed attentional mechanism |
| topic | temporal segment networks mixed attention pulmonary nodules |
| url | https://www.cttacn.org.cn/cn/article/doi/10.15953/j.ctta.2021.002 |
| work_keys_str_mv | AT binghangtang falsepositivereductionofpulmonarynodulesbasedonmixedattentionalmechanism AT yanfangwang falsepositivereductionofpulmonarynodulesbasedonmixedattentionalmechanism AT lima falsepositivereductionofpulmonarynodulesbasedonmixedattentionalmechanism AT qingwuchen falsepositivereductionofpulmonarynodulesbasedonmixedattentionalmechanism AT liweishao falsepositivereductionofpulmonarynodulesbasedonmixedattentionalmechanism AT dehuanghuang falsepositivereductionofpulmonarynodulesbasedonmixedattentionalmechanism |