Application of a light-weighted convolutional neural network for automatic recognition of coal workers' pneumoconiosis in the early stage.
10.3760/cma.j.cn121094-20220111-00011
- Author:
Feng Tao CUI
1
;
Yan WANG
2
;
Xin Ping DING
3
;
Yu Long YAO
3
;
Bing LI
4
;
Fu Hai SHEN
5
Author Information
1. Occupational Health Care Management Center, Occupational Disease Prevention and Control Institute, Huaibei Mining Co., Ltd., Huaibei 235000, China.
2. Department of Biomedical Engineering, School of Intelligent Medicine, China Medical University, Shenyang 110122, China.
3. Department of Radiology, Occupational Disease Prevention and Control Institute, Huaibei Mining Co., Ltd., Huaibei 235000, China.
4. Environment and Non-Communicable Disease Research Center, School of Public Health, China Medical University, Shenyang 110122, China.
5. School of Public Health, North China University of Science and Technology, Tangshan 063210, China.
- Publication Type:Journal Article
- Keywords:
Artificial intelligence;
Coal workers' pneumoconiosis;
Deep learning;
Diagnosis, computer-assisted;
Early screening;
Pneumoconiosis;
ShuffleNet
- MeSH:
Humans;
Retrospective Studies;
Anthracosis/diagnostic imaging*;
Pneumoconiosis/diagnostic imaging*;
Coal Mining;
Neural Networks, Computer;
Coal
- From:
Chinese Journal of Industrial Hygiene and Occupational Diseases
2023;41(3):177-182
- CountryChina
- Language:Chinese
-
Abstract:
Objective: To construct and verify a light-weighted convolutional neural network (CNN), and explore its application value for screening the early stage (subcategory 0/1 and stage Ⅰ of pneumoconiosis) of coal workers' pneumoconiosis (CWP) from digital chest radiography (DR) . Methods: A total of 1225 DR images of coal workers who were examined at an Occupational Disease Prevention and Control Institute in Anhui Province from October 2018 to March 2021 were retrospectively collected. All DR images were collectively diagnosed by 3 radiologists with diagnostic qualifications and gave diagnostic results. There were 692 DR images with small opacity profusion 0/- or 0/0 and 533 DR images with small opacity profusion 0/1 to stage Ⅲ of pneumoconiosis. The original chest radiographs were preprocessed differently to generate four datasets, namely 16-bit grayscale original image set (Origin16), 8-bit grayscale original image set (Origin 8), 16-bit grayscale histogram equalized image set (HE16) and 8-bit grayscale histogram equalized image set (HE8). The light-weighted CNN, ShuffleNet, was applied to train the generated prediction model on the four datasets separately. The performance of the four models for pneumoconiosis prediction was evaluated on a test set containing 130 DR images using measures such as the receiver operating characteristic (ROC) curve, accuracy, sensitivity, specificity, and Youden index. The Kappa consistency test was used to compare the agreement between the model predictions and the physician diagnosed pneumoconiosis results. Results: Origin16 model achieved the highest ROC area under the curve (AUC=0.958), accuracy (92.3%), specificity (92.9%), and Youden index (0.8452) for predicting pneumoconiosis, with a sensitivity of 91.7%. And the highest consistency between identification and physician diagnosis was observed for Origin16 model (Kappa value was 0.845, 95%CI: 0.753-0.937, P<0.001). HE16 model had the highest sensitivity (98.3%) . Conclusion: The light-weighted CNN ShuffleNet model can efficiently identify the early stages of CWP, and its application in the early screening of CWP can effectively improve physicians' work efficiency.
