Use data augmentation for a deep learning classification model with chest X-ray clinical imaging featuring coal workers' pneumoconiosis
Abstract Purpose This paper aims to develop a successful deep learning model with data augmentation technique to discover the clinical uniqueness of chest X-ray imaging features of coal workers' pneumoconiosis (CWP). Patients and methods We enrolled 149 CWP patients and 68 dust-exposure workers...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-07-01
|
| Series: | BMC Pulmonary Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12890-022-02068-x |
| _version_ | 1811294547713458176 |
|---|---|
| author | Hantian Dong Biaokai Zhu Xinri Zhang Xiaomei Kong |
| author_facet | Hantian Dong Biaokai Zhu Xinri Zhang Xiaomei Kong |
| author_sort | Hantian Dong |
| collection | DOAJ |
| description | Abstract Purpose This paper aims to develop a successful deep learning model with data augmentation technique to discover the clinical uniqueness of chest X-ray imaging features of coal workers' pneumoconiosis (CWP). Patients and methods We enrolled 149 CWP patients and 68 dust-exposure workers for a prospective cohort observational study between August 2021 and December 2021 at First Hospital of Shanxi Medical University. Two hundred seventeen chest X-ray images were collected for this study, obtaining reliable diagnostic results through the radiologists' team, and confirming clinical imaging features. We segmented regions of interest with diagnosis reports, then classified them into three categories. To identify these clinical features, we developed a deep learning model (ShuffleNet V2-ECA Net) with data augmentation through performances of different deep learning models by assessment with Receiver Operation Characteristics (ROC) curve and area under the curve (AUC), accuracy (ACC), and Loss curves. Results We selected the ShuffleNet V2-ECA Net as the optimal model. The average AUC of this model was 0.98, and all classifications of clinical imaging features had an AUC above 0.95. Conclusion We performed a study on a small dataset to classify the chest X-ray clinical imaging features of pneumoconiosis using a deep learning technique. A deep learning model of ShuffleNet V2 and ECA-Net was successfully constructed using data augmentation, which achieved an average accuracy of 98%. This method uncovered the uniqueness of the chest X-ray imaging features of CWP, thus supplying additional reference material for clinical application. |
| first_indexed | 2024-04-13T05:19:08Z |
| format | Article |
| id | doaj.art-4efbb6c466664313a26372dac0f101ab |
| institution | Directory Open Access Journal |
| issn | 1471-2466 |
| language | English |
| last_indexed | 2024-04-13T05:19:08Z |
| publishDate | 2022-07-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Pulmonary Medicine |
| spelling | doaj.art-4efbb6c466664313a26372dac0f101ab2022-12-22T03:00:48ZengBMCBMC Pulmonary Medicine1471-24662022-07-0122111410.1186/s12890-022-02068-xUse data augmentation for a deep learning classification model with chest X-ray clinical imaging featuring coal workers' pneumoconiosisHantian Dong0Biaokai Zhu1Xinri Zhang2Xiaomei Kong3The First College for Clinical Medicine, Shanxi Medical UniversityNetwork Security Department, Shanxi Police CollegeNational Health Commission Key Laboratory of Pneumoconiosis, Shanxi Key Laboratory of Respiratory Diseases, Department of Respiratory and Critical Care Medicine, First Hospital of Shanxi Medical UniversityNational Health Commission Key Laboratory of Pneumoconiosis, Shanxi Key Laboratory of Respiratory Diseases, Department of Respiratory and Critical Care Medicine, First Hospital of Shanxi Medical UniversityAbstract Purpose This paper aims to develop a successful deep learning model with data augmentation technique to discover the clinical uniqueness of chest X-ray imaging features of coal workers' pneumoconiosis (CWP). Patients and methods We enrolled 149 CWP patients and 68 dust-exposure workers for a prospective cohort observational study between August 2021 and December 2021 at First Hospital of Shanxi Medical University. Two hundred seventeen chest X-ray images were collected for this study, obtaining reliable diagnostic results through the radiologists' team, and confirming clinical imaging features. We segmented regions of interest with diagnosis reports, then classified them into three categories. To identify these clinical features, we developed a deep learning model (ShuffleNet V2-ECA Net) with data augmentation through performances of different deep learning models by assessment with Receiver Operation Characteristics (ROC) curve and area under the curve (AUC), accuracy (ACC), and Loss curves. Results We selected the ShuffleNet V2-ECA Net as the optimal model. The average AUC of this model was 0.98, and all classifications of clinical imaging features had an AUC above 0.95. Conclusion We performed a study on a small dataset to classify the chest X-ray clinical imaging features of pneumoconiosis using a deep learning technique. A deep learning model of ShuffleNet V2 and ECA-Net was successfully constructed using data augmentation, which achieved an average accuracy of 98%. This method uncovered the uniqueness of the chest X-ray imaging features of CWP, thus supplying additional reference material for clinical application.https://doi.org/10.1186/s12890-022-02068-xCoal workers' pneumoconiosis classificationChest X-rayDeep learningShuffleNetECA-NetData augmentation |
| spellingShingle | Hantian Dong Biaokai Zhu Xinri Zhang Xiaomei Kong Use data augmentation for a deep learning classification model with chest X-ray clinical imaging featuring coal workers' pneumoconiosis BMC Pulmonary Medicine Coal workers' pneumoconiosis classification Chest X-ray Deep learning ShuffleNet ECA-Net Data augmentation |
| title | Use data augmentation for a deep learning classification model with chest X-ray clinical imaging featuring coal workers' pneumoconiosis |
| title_full | Use data augmentation for a deep learning classification model with chest X-ray clinical imaging featuring coal workers' pneumoconiosis |
| title_fullStr | Use data augmentation for a deep learning classification model with chest X-ray clinical imaging featuring coal workers' pneumoconiosis |
| title_full_unstemmed | Use data augmentation for a deep learning classification model with chest X-ray clinical imaging featuring coal workers' pneumoconiosis |
| title_short | Use data augmentation for a deep learning classification model with chest X-ray clinical imaging featuring coal workers' pneumoconiosis |
| title_sort | use data augmentation for a deep learning classification model with chest x ray clinical imaging featuring coal workers pneumoconiosis |
| topic | Coal workers' pneumoconiosis classification Chest X-ray Deep learning ShuffleNet ECA-Net Data augmentation |
| url | https://doi.org/10.1186/s12890-022-02068-x |
| work_keys_str_mv | AT hantiandong usedataaugmentationforadeeplearningclassificationmodelwithchestxrayclinicalimagingfeaturingcoalworkerspneumoconiosis AT biaokaizhu usedataaugmentationforadeeplearningclassificationmodelwithchestxrayclinicalimagingfeaturingcoalworkerspneumoconiosis AT xinrizhang usedataaugmentationforadeeplearningclassificationmodelwithchestxrayclinicalimagingfeaturingcoalworkerspneumoconiosis AT xiaomeikong usedataaugmentationforadeeplearningclassificationmodelwithchestxrayclinicalimagingfeaturingcoalworkerspneumoconiosis |