Automated interstitial lung abnormalities detection at CT: external validation and potential recognition of traction bronchiectasis/bronchiolectasis.
Authors
Affiliations (18)
Affiliations (18)
- Center for Pulmonary Functional Imaging, Department of Radiology, Brigham and Women's Hospital and Harvard Medical School, 75 Francis Street, Boston, MA, 02115, USA. [email protected].
- Department of Clinical Radiology, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan. [email protected].
- Center for Pulmonary Functional Imaging, Department of Radiology, Brigham and Women's Hospital and Harvard Medical School, 75 Francis Street, Boston, MA, 02115, USA.
- Department of Radiology, The Jikei University School of Medicine, Tokyo, Japan.
- Canon Medical Systems Corporation, Tochigi, Japan.
- Canon Inc., Tokyo, Japan.
- Department of Clinical Radiology, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan.
- Department of Radiology & Nuclear Medicine, Erasmus MC, Rotterdam, The Netherlands.
- Department of Epidemiology, Erasmus MC, Rotterdam, The Netherlands.
- Department of Respiratory Medicine, Erasmus MC, Rotterdam, The Netherlands.
- Department of Respiratory Medicine, Amphia, Breda, The Netherlands.
- Institute for Advanced Diagnosis for Rare Diseases & Conditions K.K., Tokyo, Japan.
- Faculty of Medicine, University of Iceland, Reykjavik, Iceland.
- Icelandic Heart Association, Kopavogur, Iceland.
- Department of Respiratory Medicine, Landspitali University Hospital, Reykjavik, Iceland.
- Pulmonary and Critical Care Division, Department of Medicine, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA.
- Department of Environmental Health, Harvard TH Chan School of Public Health, Boston, MA, USA.
- Pulmonary and Critical Care Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA.
Abstract
An artificial intelligence (AI) system for detecting interstitial lung abnormalities (ILA) was previously developed but requires external validation. This study aimed to examine the robustness across different populations and investigate associations between the system outputs and traction bronchiectasis/bronchiolectasis severity patterns. CT scans from population-based samples of the Rotterdam Study (2018-2019) and the Age Gene/Environment Susceptibility Reykjavik (AGES-Reykjavik) Study (baseline CT: 2002-2006, follow-up CT: 2007-2011) were used in this secondary analysis of the two cohorts. The AI system calculated ILA probability score (AI score) in the range from 0 to 1. Three experienced readers evaluated independently all CT scans for ILA, and two chest radiologists assessed traction bronchiectasis/bronchiolectasis using the 4-scale traction bronchiectasis/bronchiolectasis index (TBI) for severity by consensus. Receiver operating characteristic (ROC) analysis and Kruskal-Wallis test were used for statistical analysis. The system analyzed 932 CT scans of the Rotterdam Study (mean participant age, 79.6 years ± 4.3 (SD), 482 women) and 5242 CT scans of the AGES-Reykjavik Study (mean participant age, 76.4 years ± 5.6, 3032 women), and achieved area under the ROC curve of 0.841 (95% CI 0.804, 0.879) and 0.823 (95% CI 0.798, 0.847), respectively. AI scores correlated with readers' certainty, decreasing from unanimous ILA cases to No-ILA cases. Higher baseline AI scores correlated with greater severity of traction bronchiectasis/bronchiolectasis (TBI-3: 0.931 [IQR, 0.911-0.932], TBI-2: 0.738 [IQR, 0.406-0.880], TBI-1: 0.537 [IQR, 0.317-0.761], TBI-0: 0.250 [IQR, 0.136-0.455]). The system demonstrated robust ILA detection performance across different populations, with AI scores showing associations with traction bronchiectasis/bronchiolectasis severity.