Pneumoconiosis computer aided diagnosis system based on X-rays and deep learning

BMC Medical Imaging

Min Tang¹  Wanyin Qi¹  Jing Chen¹  Fan Yang²  Chong Yao³  Yuanyuan Yu³  Zekuan Yu⁴  Shengchun Wang⁵  Yinan Guo⁶  Zhi-Ri Tang⁷ 

[1] Department of Radiology, The Affiliated Hospital of Southwest Medical University, Taiping Street, 646000, Luzhou, Sichuan, China;Department of Radiology, The Affiliated Hospital of Southwest Medical University, Taiping Street, 646000, Luzhou, Sichuan, China;Key Laboratory of Industrial Dust Prevention and Control and Occupational Health and Safety, Ministry of Education, Huainan, China;Key Laboratory of Industrial Dust Prevention and Control and Occupational Health and Safety, Ministry of Education, Huainan, China;Academy for Engineering and Technology, Fudan University, 200433, Shanghai, China;Key Laboratory of Industrial Dust Prevention and Control and Occupational Health and Safety, Ministry of Education, Huainan, China;Department of Radiology, Huashan Hospital, Fudan University, No.12 Wulumuqi Road (Middle), 200040, Shanghai, China;Academy for Engineering and Technology, Fudan University, 200433, Shanghai, China;Guangxi Key Laboratory of Automatic Detecting Technology and Instruments (Guilin University of Electronic Technology), Guilin, China;Luzhou Center for Disease Control and Prevention, 646000, Luzhou, Sichuan, China;School of Information and Control Engineering, China University of Mining and Technology, 221116, Xuzhou, China;School of Physics and Technology, Wuhan University, 430072, Wuhan, China;Key Laboratory of Industrial Dust Prevention and Control and Occupational Health and Safety, Ministry of Education, Huainan, China;

关键词: Pneumoconiosis diagnosis;    X-rays;    Deep learning;    U-Net;    ResNet;   

DOI  :  10.1186/s12880-021-00723-z

来源: Springer

【 摘 要 】

PurposeThe objective of this study is to construct a computer aided diagnosis system for normal people and pneumoconiosis using X-raysand deep learning algorithms.Materials and methods1760 anonymous digital X-ray images of real patients between January 2017 and June 2020 were collected for this experiment. In order to concentrate the feature extraction ability of the model more on the lung region and restrain the influence of external background factors, a two-stage pipeline from coarse to fine was established. First, the U-Net model was used to extract the lung regions on each sides of the collection images. Second, the ResNet-34 model with transfer learning strategy was implemented to learn the image features extracted in the lung region to achieve accurate classification of pneumoconiosis patients and normal people.ResultsAmong the 1760 cases collected, the accuracy and the area under curve of the classification model were 92.46% and 89% respectively.ConclusionThe successful application of deep learning in the diagnosis of pneumoconiosis further demonstrates the potential of medical artificial intelligence and proves the effectiveness of our proposed algorithm. However, when we further classified pneumoconiosis patients and normal subjects into four categories, we found that the overall accuracy decreased to 70.1%. We will use the CT modality in future studies to provide more details of lung regions.

【 授权许可】

CC BY