Automated Radiology Alert System for Pneumothorax Detection on Chest Radiographs Improves Efficiency and Diagnostic Performance
Cheng-Yi Kao,
Chiao-Yun Lin,
Cheng-Chen Chao,
Han-Sheng Huang,
Hsing-Yu Lee,
Chia-Ming Chang,
Kang Sung,
Ting-Rong Chen,
Po-Chang Chiang,
Li-Ting Huang,
Bow Wang,
Yi-Sheng Liu,
Jung-Hsien Chiang,
Chien-Kuo Wang,
Yi-Shan Tsai
Affiliations
Cheng-Yi Kao
Department of Medical Imaging, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, No. 1 University Road, Tainan 704, Taiwan
Chiao-Yun Lin
Department of Medical Imaging, E-DA Hospital, I-Shou University, No. 1 Yida Road, Jiaosu Village, Yanchao District, Kaohsiung 824, Taiwan
Cheng-Chen Chao
Department of Medical Imaging, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, No. 1 University Road, Tainan 704, Taiwan
Han-Sheng Huang
Department of Medical Imaging, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, No. 1 University Road, Tainan 704, Taiwan
Hsing-Yu Lee
Department of Medical Imaging, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, No. 1 University Road, Tainan 704, Taiwan
Chia-Ming Chang
Department of Medical Imaging, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, No. 1 University Road, Tainan 704, Taiwan
Kang Sung
Department of Medical Imaging, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, No. 1 University Road, Tainan 704, Taiwan
Ting-Rong Chen
Department of Medical Imaging, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, No. 1 University Road, Tainan 704, Taiwan
Po-Chang Chiang
Department of Medical Imaging, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, No. 1 University Road, Tainan 704, Taiwan
Li-Ting Huang
Department of Medical Imaging, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, No. 1 University Road, Tainan 704, Taiwan
Bow Wang
Department of Medical Imaging, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, No. 1 University Road, Tainan 704, Taiwan
Yi-Sheng Liu
Department of Medical Imaging, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, No. 1 University Road, Tainan 704, Taiwan
Jung-Hsien Chiang
Department of Computer Science and Information Engineering, College of Electrical Engineering and Computer Science, National Cheng Kung University, No. 1 University Road, Tainan 704, Taiwan
Chien-Kuo Wang
Department of Medical Imaging, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, No. 1 University Road, Tainan 704, Taiwan
Yi-Shan Tsai
Department of Medical Imaging, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, No. 1 University Road, Tainan 704, Taiwan
We aimed to set up an Automated Radiology Alert System (ARAS) for the detection of pneumothorax in chest radiographs by a deep learning model, and to compare its efficiency and diagnostic performance with the existing Manual Radiology Alert System (MRAS) at the tertiary medical center. This study retrospectively collected 1235 chest radiographs with pneumothorax labeling from 2013 to 2019, and 337 chest radiographs with negative findings in 2019 were separated into training and validation datasets for the deep learning model of ARAS. The efficiency before and after using the model was compared in terms of alert time and report time. During parallel running of the two systems from September to October 2020, chest radiographs prospectively acquired in the emergency department with age more than 6 years served as the testing dataset for comparison of diagnostic performance. The efficiency was improved after using the model, with mean alert time improving from 8.45 min to 0.69 min and the mean report time from 2.81 days to 1.59 days. The comparison of the diagnostic performance of both systems using 3739 chest radiographs acquired during parallel running showed that the ARAS was better than the MRAS as assessed in terms of sensitivity (recall), area under receiver operating characteristic curve, and F1 score (0.837 vs. 0.256, 0.914 vs. 0.628, and 0.754 vs. 0.407, respectively), but worse in terms of positive predictive value (PPV) (precision) (0.686 vs. 1.000). This study had successfully designed a deep learning model for pneumothorax detection on chest radiographs and set up an ARAS with improved efficiency and overall diagnostic performance.
