Detection and staging of chronic obstructive pulmonary disease using a computed tomography–based weakly supervised deep learning approach

Abstract

BackgroundChronic obstructive pulmonary disease (COPD) remains underdiagnosed globally. The coronavirus disease 2019 pandemic has also severely restricted spirometry, the primary tool used for COPD diagnosis and severity evaluation, due to concerns of virus transmission. Computed tomography (CT)-based deep learning (DL) approaches have been suggested as a cost-effective alternative for COPD identi cation within smokers. The present study aims to develop weakly supervised DL models that utilize CT image data for the automated detection and staging of spirometry-de ned COPD among natural population. MethodsA large, highly heterogenous dataset was established comprising 1393 participants recruited from outpatient, inpatient and physical examination center settings of 4 large public hospitals in China. CT scans, spirometry data, demographic data, and clinical information of each participant were collected for the purpose of model development and evaluation. An attention-based multi-instance learning (MIL) model for COPD detection was trained using CT scans from 837 participants and evaluated using a test set comprised of data from 278 non-overlapping participants. External validation of the COPD detection was performed with 620 low-dose CT (LDCT) scans acquired from the National Lung Screening Trial (NLST) cohort. A multi-channel 3D residual network was further developed to categorize GOLD stages among con rmed COPD patients and evaluated using 5-fold cross validation. Spirometry tests were used to diagnose COPD, with stages de ned according to the GOLD criteria. ResultsThe attention-based MIL model used for COPD detection achieved an area under the receiver operating characteristic curve (AUC) of 0.934 on the test set and 0.866 on the LDCT subset acquired from NLST.The model exhibited high generalizability across distinct scanning devices and slice thicknesses, with an AUC above 0.90. The multi-channel 3D residual network was able to correctly grade 76.4% of COPD patients in the test set (423/553) using the GOLD scale, with a Cohen's weighted Kappa of 0.619 for the assessment of GOLD categorization . ConclusionThe proposed chest CT-DL approach can automatically identify spirometry-de ned COPD and categorize patients according to the GOLD scale, with clinically acceptable performance. As such, this approach may be a powerful novel tool for COPD diagnosis and staging at the population level. BackgroundChronic obstructive pulmonary disease (COPD) is a worldwide public health challenge, due to its high prevalence and long-term effects on related disabilities and mortality (1, 2). The accurate diagnosis of

Digital health in chronic obstructive pulmonary disease

“…Tang et al proposed a novel residual network that achieved clinically acceptable performance with an area under the receiver operating characteristic (AUC‐ROC) curve of over 88% for identifying patients with COPD using low‐dose CT among ex‐smokers and current smokers without a prior diagnosis 73 . Sun et al developed and validated a CT method using ML for detecting and staging spirometry‐defined COPD based on the Chinese population, providing clinicians with valuable indicators and relevant findings to improve patient management and treatment 74 …”

Artificial Intelligence Techniques to Predict the Airway Disorders Illness: A Systematic Review

“…One advantage of employing AI to interpret diagnostic exams such as imaging is the ability to evaluate tests done in geographically isolated or underserved places [147]. This may result in a more early and accurate diagnosis, as well as a referral to expert treatment at an earlier stage of the disease, potentially influencing the prognosis Radiographs from these centers, on the other hand, can be remotely submitted and analyzed by a single central system using AI [148]. In Fig.…”

Thoracic Imaging in China

“…The AI research currently conducted for COPD is focused on: imaging biomarkers in high risk COPD populations, screening COPD, severity assessment, and predicting the progress of the disease. 66 , 67 The parameter response mapping derived from chest CT images uses machine learning to predict pulmonary function test results, and has shown good performance in Shanghai, China. Moreover, a one-stop thoracic CT to evaluate lung cancer and COPD has been developed and validated with a deep-learning based automatic algorithm used to generate a quantitative analysis and structure report for NELCIN-B3 in Shanghai, China.…”

“…COPD is a heterogeneous disease that begins with the remodeling of small airways and small vessels, eventually leading to the destruction of pulmonary parenchyma and formation of emphysema. The AI research currently conducted for COPD is focused on: imaging biomarkers in high risk COPD populations, screening COPD, severity assessment, and predicting the progress of the disease 66,67. The parameter response mapping derived from chest CT images uses machine learning to predict pulmonary function test results, and has shown good performance in Shanghai, China.…”