RT Journal Article
SR Electronic
T1 Differentiating COPD and Asthma using Quantitative CT Imaging and Machine Learning
JF European Respiratory Journal
JO Eur Respir J
FD European Respiratory Society
SP 2103078
DO 10.1183/13993003.03078-2021
A1 Amir Moslemi
A1 Konstantina Kontogianni
A1 Judith Brock
A1 Susan Wood
A1 Felix Herth
A1 Miranda Kirby
YR 2022
UL http://erj.ersjournals.com/content/early/2022/02/10/13993003.03078-2021.abstract
AB There are similarities and differences between chronic obstructive pulmonary disease (COPD) and asthma patients in terms of computed tomography (CT) disease-related features. Our objective was to determine the optimal subset of CT imaging features for differentiating COPD and asthma using machine learning.COPD and asthma patients were recruited from Heidelberg University Hospital. CT was acquired and 93 features were extracted (VIDA Diagnostics): percentage of low-attenuating-areas below −950HU (LAA950), LAA950 hole count, estimated airway-wall-thickness for a 10 mm internal perimeter airway (Pi10), total-airway-count (TAC), as well as inner/outer perimeter/areas and wall thickness for each of five segmental airways, and the average of those five airways. Hybrid feature selection was used to select the optimum number of features, and support vector machine was used to classify COPD and asthma.Ninety-five participants were included (n=48 COPD; n=47 asthma); there were no differences between COPD and asthma for age (p=0.25) or FEV1 (p=0.31). In a model including all CT features, the accuracy and F1-score was 80% and 81%, respectively. The top features were: LAA950, LAA950 hole count, average outer and inner airway perimeter, outer and inner airway area RB1, and TAC. In the model with only airway features, the accuracy and F1-score were 66% and 68%, respectively. The top features were: inner area RB1, wall thickness RB1, outer area LB1, TAC LB10, average outer/inner perimeter, Pi10, and TAC.In conclusions, COPD and asthma can be differentiated using machine learning with moderate-high accuracy by a subset of only 7 CT features.FootnotesThis manuscript has recently been accepted for publication in the European Respiratory Journal. It is published here in its accepted form prior to copyediting and typesetting by our production team. After these production processes are complete and the authors have approved the resulting proofs, the article will move to the latest issue of the ERJ online. Please open or download the PDF to view this article.Conflict of interest: Dr. Wood is a CEO and shareholder of VIDA Diagnostics, a company commercializing lung image analysis software.Conflict of interest: Dr. Herth is affiliated with, or has received grants or research support from the German Federal Ministry of Education and Research (BMBF), BMG Pharma, Broncus-Uptake Medical, Deutsche Forschungsgemeinschaft (DFG), the European Union (EU), Klaus Tschirra Stiftung, Olympus Medical Systems, Pulmonx, and Roche Diagnostics; honoraria or consulting fees from AstraZeneca, Berlin-Chemie, Boehringer Ingelheim, Chiesi Farmaceutici S.p.A., Erbe China, Novartis, MedUpdates, Pulmonx, Roche Diagnostics, Uptake Medical, Boston Scientific, Broncus-Uptake Medical, Dinova Pharmaceutical Inc, Erbe Medical, Free Flow Medical, Johnson & Johnson, Karger Publishers, LAK Medical, Nanovation, and Olympus Medical.Conflict of interest: Dr. Moslemi has nothing to disclose.Conflict of interest: Dr. Kontogianni has nothing to disclose.Conflict of interest: Dr. Brock has nothing to disclose.Conflict of interest: Dr. Kirby has nothing to disclose.