Lisa Y W Tang1, Harvey O Coxson2, Stephen Lam3, Jonathon Leipsic4, Roger C Tam5, Don D Sin6. 1. Data Science Institute, University of British Columbia, Vancouver, BC, Canada; Department of Radiology, University of British Columbia, Vancouver, BC, Canada; University of British Columbia Centre for Heart Lung Innovation, St Paul's Hospital, Vancouver, BC, Canada. Electronic address: lisa.tang@ubc.ca. 2. University of British Columbia Centre for Heart Lung Innovation, St Paul's Hospital, Vancouver, BC, Canada. 3. Department of Medicine, University of British Columbia, Vancouver, BC, Canada; Imaging Unit, Integrative Oncology Department, British Columbia Cancer Agency Research Centre, Vancouver, BC, Canada. 4. Department of Radiology, University of British Columbia, Vancouver, BC, Canada. 5. Department of Radiology, University of British Columbia, Vancouver, BC, Canada; School of Biomedical Engineering, University of British Columbia, Vancouver, BC, Canada. 6. Department of Medicine, University of British Columbia, Vancouver, BC, Canada; University of British Columbia Centre for Heart Lung Innovation, St Paul's Hospital, Vancouver, BC, Canada.
Abstract
BACKGROUND: Chronic obstructive pulmonary disease (COPD) is underdiagnosed in the community. Thoracic CT scans are widely used for diagnostic and screening purposes for lung cancer. In this proof-of-concept study, we aimed to evaluate a software pipeline for the automated detection of COPD, based on deep learning and a dataset of low-dose CTs that were performed for early detection of lung cancer. METHODS: We examined the use of deep residual networks, a type of artificial residual network, for the automated detection of COPD. Three versions of the residual networks were independently trained to perform COPD diagnosis using random subsets of CT scans collected from the PanCan study, which enrolled ex-smokers and current smokers at high risk of lung cancer, and evaluated the networks using three-fold cross-validation experiments. External validation was performed using 2153 CT scans acquired from a separate cohort of individuals with COPD in the ECLIPSE study. Spirometric data were used to define COPD, with stages defined according to the GOLD criteria. FINDINGS: The best performing networks achieved an area under the receiver operating characteristic curve (AUC) of 0·889 (SD 0·017) in three-fold cross-validation experiments. When the same set of networks was applied to the ECLIPSE cohort without any modifications to the trained models, they achieved an AUC of 0·886 (0·017), a positive predictive value of 0·847 (0·056), and a negative predictive value of 0·755 (0·097), which is a greater performance than the best quantitative CT measure, the percentage of lung volumes of less than or equal to -950 Hounsfield units (AUC 0·742). INTERPRETATION: Our proposed approach could identify patients with COPD among ex-smokers and current smokers without a previous diagnosis of COPD, with clinically acceptable performance. The use of deep residual networks on chest CT scans could be an effective case-finding tool for COPD detection and diagnosis, particularly in ex-smokers and current smokers who are being screened for lung cancer. FUNDING: Data Science Institute, University of British Columbia; Canadian Institutes of Health Research.
BACKGROUND:Chronic obstructive pulmonary disease (COPD) is underdiagnosed in the community. Thoracic CT scans are widely used for diagnostic and screening purposes for lung cancer. In this proof-of-concept study, we aimed to evaluate a software pipeline for the automated detection of COPD, based on deep learning and a dataset of low-dose CTs that were performed for early detection of lung cancer. METHODS: We examined the use of deep residual networks, a type of artificial residual network, for the automated detection of COPD. Three versions of the residual networks were independently trained to perform COPD diagnosis using random subsets of CT scans collected from the PanCan study, which enrolled ex-smokers and current smokers at high risk of lung cancer, and evaluated the networks using three-fold cross-validation experiments. External validation was performed using 2153 CT scans acquired from a separate cohort of individuals with COPD in the ECLIPSE study. Spirometric data were used to define COPD, with stages defined according to the GOLD criteria. FINDINGS: The best performing networks achieved an area under the receiver operating characteristic curve (AUC) of 0·889 (SD 0·017) in three-fold cross-validation experiments. When the same set of networks was applied to the ECLIPSE cohort without any modifications to the trained models, they achieved an AUC of 0·886 (0·017), a positive predictive value of 0·847 (0·056), and a negative predictive value of 0·755 (0·097), which is a greater performance than the best quantitative CT measure, the percentage of lung volumes of less than or equal to -950 Hounsfield units (AUC 0·742). INTERPRETATION: Our proposed approach could identify patients with COPD among ex-smokers and current smokers without a previous diagnosis of COPD, with clinically acceptable performance. The use of deep residual networks on chest CT scans could be an effective case-finding tool for COPD detection and diagnosis, particularly in ex-smokers and current smokers who are being screened for lung cancer. FUNDING: Data Science Institute, University of British Columbia; Canadian Institutes of Health Research.