CX-Net: an efficient ensemble semantic deep neural network for ROI identification from chest-x-ray images for COPD diagnosis
Automatic identification of salient features in large medical datasets, particularly in chest x-ray (CXR) images, is a crucial research area. Accurately detecting critical findings such as emphysema, pneumothorax, and chronic bronchitis can aid radiologists in prioritizing time-sensitive cases and s...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/acd2a5 |
| _version_ | 1797824023262920704 |
|---|---|
| author | Agughasi Victor Ikechukwu Murali S |
| author_facet | Agughasi Victor Ikechukwu Murali S |
| author_sort | Agughasi Victor Ikechukwu |
| collection | DOAJ |
| description | Automatic identification of salient features in large medical datasets, particularly in chest x-ray (CXR) images, is a crucial research area. Accurately detecting critical findings such as emphysema, pneumothorax, and chronic bronchitis can aid radiologists in prioritizing time-sensitive cases and screening for abnormalities. However, traditional deep neural network approaches often require bounding box annotations, which can be time-consuming and challenging to obtain. This study proposes an explainable ensemble learning approach, CX-Net, for lung segmentation and diagnosing lung disorders using CXR images. We compare four state-of-the-art convolutional neural network models, including feature pyramid network, U-Net, LinkNet, and a customized U-Net model with ImageNet feature extraction, data augmentation, and dropout regularizations. All models are trained on the Montgomery and VinDR-CXR datasets with and without segmented ground-truth masks. To achieve model explainability, we integrate SHapley Additive exPlanations (SHAP) and gradient-weighted class activation mapping (Grad-CAM) techniques, which enable a better understanding of the decision-making process and provide visual explanations of critical regions within the CXR images. By employing ensembling, our outlier-resistant CX-Net achieves superior performance in lung segmentation, with Jaccard overlap similarity of 0.992, Dice coefficients of 0.994, precision of 0.993, recall of 0.980, and accuracy of 0.976. The proposed approach demonstrates strong generalization capabilities on the VinDr-CXR dataset and is the first study to use these datasets for semantic lung segmentation with semi-supervised localization. In conclusion, this paper presents an explainable ensemble learning approach for lung segmentation and diagnosing lung disorders using CXR images. Extensive experimental results show that our method efficiently and accurately extracts regions of interest in CXR images from publicly available datasets, indicating its potential for integration into clinical decision support systems. Furthermore, incorporating SHAP and Grad-CAM techniques further enhances the interpretability and trustworthiness of the AI-driven diagnostic system. |
| first_indexed | 2024-03-13T10:32:49Z |
| format | Article |
| id | doaj.art-36ce72f4d8bf49e78d1c2ac2d6e563ba |
| institution | Directory Open Access Journal |
| issn | 2632-2153 |
| language | English |
| last_indexed | 2024-03-13T10:32:49Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj.art-36ce72f4d8bf49e78d1c2ac2d6e563ba2023-05-18T12:58:14ZengIOP PublishingMachine Learning: Science and Technology2632-21532023-01-014202502110.1088/2632-2153/acd2a5CX-Net: an efficient ensemble semantic deep neural network for ROI identification from chest-x-ray images for COPD diagnosisAgughasi Victor Ikechukwu0https://orcid.org/0000-0002-1175-3089Murali S1Department of CSE, Maharaja Institute of Technology Mysore , 571477 Karnataka, IndiaDepartment of CSE, Maharaja Institute of Technology Mysore , 571477 Karnataka, IndiaAutomatic identification of salient features in large medical datasets, particularly in chest x-ray (CXR) images, is a crucial research area. Accurately detecting critical findings such as emphysema, pneumothorax, and chronic bronchitis can aid radiologists in prioritizing time-sensitive cases and screening for abnormalities. However, traditional deep neural network approaches often require bounding box annotations, which can be time-consuming and challenging to obtain. This study proposes an explainable ensemble learning approach, CX-Net, for lung segmentation and diagnosing lung disorders using CXR images. We compare four state-of-the-art convolutional neural network models, including feature pyramid network, U-Net, LinkNet, and a customized U-Net model with ImageNet feature extraction, data augmentation, and dropout regularizations. All models are trained on the Montgomery and VinDR-CXR datasets with and without segmented ground-truth masks. To achieve model explainability, we integrate SHapley Additive exPlanations (SHAP) and gradient-weighted class activation mapping (Grad-CAM) techniques, which enable a better understanding of the decision-making process and provide visual explanations of critical regions within the CXR images. By employing ensembling, our outlier-resistant CX-Net achieves superior performance in lung segmentation, with Jaccard overlap similarity of 0.992, Dice coefficients of 0.994, precision of 0.993, recall of 0.980, and accuracy of 0.976. The proposed approach demonstrates strong generalization capabilities on the VinDr-CXR dataset and is the first study to use these datasets for semantic lung segmentation with semi-supervised localization. In conclusion, this paper presents an explainable ensemble learning approach for lung segmentation and diagnosing lung disorders using CXR images. Extensive experimental results show that our method efficiently and accurately extracts regions of interest in CXR images from publicly available datasets, indicating its potential for integration into clinical decision support systems. Furthermore, incorporating SHAP and Grad-CAM techniques further enhances the interpretability and trustworthiness of the AI-driven diagnostic system.https://doi.org/10.1088/2632-2153/acd2a5chest x-rayCOPDCX-Netensemble learningSHAP and Grad-CAMVinDR-chest x-ray |
| spellingShingle | Agughasi Victor Ikechukwu Murali S CX-Net: an efficient ensemble semantic deep neural network for ROI identification from chest-x-ray images for COPD diagnosis Machine Learning: Science and Technology chest x-ray COPD CX-Net ensemble learning SHAP and Grad-CAM VinDR-chest x-ray |
| title | CX-Net: an efficient ensemble semantic deep neural network for ROI identification from chest-x-ray images for COPD diagnosis |
| title_full | CX-Net: an efficient ensemble semantic deep neural network for ROI identification from chest-x-ray images for COPD diagnosis |
| title_fullStr | CX-Net: an efficient ensemble semantic deep neural network for ROI identification from chest-x-ray images for COPD diagnosis |
| title_full_unstemmed | CX-Net: an efficient ensemble semantic deep neural network for ROI identification from chest-x-ray images for COPD diagnosis |
| title_short | CX-Net: an efficient ensemble semantic deep neural network for ROI identification from chest-x-ray images for COPD diagnosis |
| title_sort | cx net an efficient ensemble semantic deep neural network for roi identification from chest x ray images for copd diagnosis |
| topic | chest x-ray COPD CX-Net ensemble learning SHAP and Grad-CAM VinDR-chest x-ray |
| url | https://doi.org/10.1088/2632-2153/acd2a5 |
| work_keys_str_mv | AT agughasivictorikechukwu cxnetanefficientensemblesemanticdeepneuralnetworkforroiidentificationfromchestxrayimagesforcopddiagnosis AT muralis cxnetanefficientensemblesemanticdeepneuralnetworkforroiidentificationfromchestxrayimagesforcopddiagnosis |