Multi-Branch Ensemble Learning Architecture Based on 3D CNN for False Positive Reduction in Lung Nodule Detection
It is critical to have accurate detection of lung nodules in CT images for the early diagnosis of lung cancer. In order to achieve this, it is necessary to reduce the false positive rate of detection. Due to the heterogeneity of lung nodules and their similarity to the background, it is difficult to...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8669681/ |
| _version_ | 1818412499993624576 |
|---|---|
| author | Haichao Cao Hong Liu Enmin Song Guangzhi Ma Xiangyang Xu Renchao Jin Tengying Liu Chih-Cheng Hung |
| author_facet | Haichao Cao Hong Liu Enmin Song Guangzhi Ma Xiangyang Xu Renchao Jin Tengying Liu Chih-Cheng Hung |
| author_sort | Haichao Cao |
| collection | DOAJ |
| description | It is critical to have accurate detection of lung nodules in CT images for the early diagnosis of lung cancer. In order to achieve this, it is necessary to reduce the false positive rate of detection. Due to the heterogeneity of lung nodules and their similarity to the background, it is difficult to distinguish true lung nodules from numerous candidate nodules. In this paper, in order to solve this challenging problem, we propose a Multi-Branch Ensemble Learning architecture based on the three-dimensional (3D) convolutional neural networks (MBEL-3D-CNN). The method combines three key ideas: 1) constructing a 3D-CNN to make the maximum utilization of spatial information of lung nodules in the 3D space; 2) embedding a multi-branch network architecture in the 3D-CNN that is well adapted to the heterogeneity of lung nodules, and; 3) using ensemble learning to effectively improve the generalization performance of the 3D-CNN model. In addition, we use offline hard mining operations to make the network capable of handling those indistinguishable positive and negative samples. The proposed method was tested on the dataset LUNA16 in our experiments. The experimental results show that MBEL-3D-CNN architecture can achieve better screening results. |
| first_indexed | 2024-12-14T10:48:17Z |
| format | Article |
| id | doaj.art-4e96665f01364ab19c14c94708b0b32c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T10:48:17Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4e96665f01364ab19c14c94708b0b32c2022-12-21T23:05:21ZengIEEEIEEE Access2169-35362019-01-017673806739110.1109/ACCESS.2019.29061168669681Multi-Branch Ensemble Learning Architecture Based on 3D CNN for False Positive Reduction in Lung Nodule DetectionHaichao Cao0Hong Liu1https://orcid.org/0000-0001-8252-5131Enmin Song2Guangzhi Ma3Xiangyang Xu4Renchao Jin5Tengying Liu6Chih-Cheng Hung7School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, ChinaSchool of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, ChinaSchool of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, ChinaSchool of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, ChinaSchool of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, ChinaSchool of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, ChinaSchool of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, ChinaLaboratory for Machine Vision and Security Research, Kennesaw State University, Kennesaw, GA, USAIt is critical to have accurate detection of lung nodules in CT images for the early diagnosis of lung cancer. In order to achieve this, it is necessary to reduce the false positive rate of detection. Due to the heterogeneity of lung nodules and their similarity to the background, it is difficult to distinguish true lung nodules from numerous candidate nodules. In this paper, in order to solve this challenging problem, we propose a Multi-Branch Ensemble Learning architecture based on the three-dimensional (3D) convolutional neural networks (MBEL-3D-CNN). The method combines three key ideas: 1) constructing a 3D-CNN to make the maximum utilization of spatial information of lung nodules in the 3D space; 2) embedding a multi-branch network architecture in the 3D-CNN that is well adapted to the heterogeneity of lung nodules, and; 3) using ensemble learning to effectively improve the generalization performance of the 3D-CNN model. In addition, we use offline hard mining operations to make the network capable of handling those indistinguishable positive and negative samples. The proposed method was tested on the dataset LUNA16 in our experiments. The experimental results show that MBEL-3D-CNN architecture can achieve better screening results.https://ieeexplore.ieee.org/document/8669681/Computer-aided diagnosisensemble learningfalse positive reductionoffline hard mining3D CNN |
| spellingShingle | Haichao Cao Hong Liu Enmin Song Guangzhi Ma Xiangyang Xu Renchao Jin Tengying Liu Chih-Cheng Hung Multi-Branch Ensemble Learning Architecture Based on 3D CNN for False Positive Reduction in Lung Nodule Detection IEEE Access Computer-aided diagnosis ensemble learning false positive reduction offline hard mining 3D CNN |
| title | Multi-Branch Ensemble Learning Architecture Based on 3D CNN for False Positive Reduction in Lung Nodule Detection |
| title_full | Multi-Branch Ensemble Learning Architecture Based on 3D CNN for False Positive Reduction in Lung Nodule Detection |
| title_fullStr | Multi-Branch Ensemble Learning Architecture Based on 3D CNN for False Positive Reduction in Lung Nodule Detection |
| title_full_unstemmed | Multi-Branch Ensemble Learning Architecture Based on 3D CNN for False Positive Reduction in Lung Nodule Detection |
| title_short | Multi-Branch Ensemble Learning Architecture Based on 3D CNN for False Positive Reduction in Lung Nodule Detection |
| title_sort | multi branch ensemble learning architecture based on 3d cnn for false positive reduction in lung nodule detection |
| topic | Computer-aided diagnosis ensemble learning false positive reduction offline hard mining 3D CNN |
| url | https://ieeexplore.ieee.org/document/8669681/ |
| work_keys_str_mv | AT haichaocao multibranchensemblelearningarchitecturebasedon3dcnnforfalsepositivereductioninlungnoduledetection AT hongliu multibranchensemblelearningarchitecturebasedon3dcnnforfalsepositivereductioninlungnoduledetection AT enminsong multibranchensemblelearningarchitecturebasedon3dcnnforfalsepositivereductioninlungnoduledetection AT guangzhima multibranchensemblelearningarchitecturebasedon3dcnnforfalsepositivereductioninlungnoduledetection AT xiangyangxu multibranchensemblelearningarchitecturebasedon3dcnnforfalsepositivereductioninlungnoduledetection AT renchaojin multibranchensemblelearningarchitecturebasedon3dcnnforfalsepositivereductioninlungnoduledetection AT tengyingliu multibranchensemblelearningarchitecturebasedon3dcnnforfalsepositivereductioninlungnoduledetection AT chihchenghung multibranchensemblelearningarchitecturebasedon3dcnnforfalsepositivereductioninlungnoduledetection |