1. Computer-Aided Detection of Seven Chest Pathologies on Standard Posteroanterior Chest X-Rays Compared to Radiologists Reading Dual-Energy Subtracted Radiographs
- Author
-
Katharina Martini, Alexandra De Silvestro, Mathias Müller, Thomas Frauenfelder, Gioia Fischer, University of Zurich, and Martini, Katharina
- Subjects
Lung Diseases ,Lung Neoplasms ,Rib Fractures ,Pleural effusion ,Radiography ,Cardiomegaly ,610 Medicine & health ,Sensitivity and Specificity ,McNemar's test ,Humans ,2741 Radiology, Nuclear Medicine and Imaging ,Medicine ,Radiology, Nuclear Medicine and imaging ,Retrospective Studies ,Dual energy ,Computers ,10042 Clinic for Diagnostic and Interventional Radiology ,business.industry ,Subtraction ,Pneumothorax ,Solitary Pulmonary Nodule ,Gold standard (test) ,medicine.disease ,Computer aided detection ,Pleural Effusion ,Multiple Pulmonary Nodules ,Radiographic Image Interpretation, Computer-Assisted ,Radiography, Thoracic ,business ,Nuclear medicine - Abstract
Retrospective performance evaluation of a computer-aided detection (CAD) system on standard posteroanterior (PA) chest radiographs (PA-CXR) in detection of pulmonary nodules, infectious consolidation, pneumothorax, pleural effusion, aortic calcification, cardiomegaly and rib fractures compared to radiologists analyzing PA-CXR including dual-energy subtraction radiography (further termed as DESR).PA-CXR/DESR images of 197 patients were included. All patients underwent chest CT (gold standard) within a short interval (mean 28 hours). All images were evaluated by three blinded readers for the presence of pulmonary nodules, infectious consolidation, pneumothorax, pleural effusion, aortic calcification, cardiomegaly, and rib fractures. Meanwhile PA-CXR were analyzed by a CAD software. CAD results were compared to the majority result of the three readers. Sensitivity and specificity were calculated. McNemar's test was applied to test for significant differences. Interobserver agreement was defined using Cohen's kappa (κ).Sensitivity of the CAD software was significantly higher (p0.05) for detection of infectious consolidation and pulmonary nodules (67.9% vs 26.8% and 54% vs 35.6%, respectively; p0.001) compared to radiologists analyzing DESR images. For the residual evaluated pathologies no statistical significant differences could be found. Overall, mean inter observer agreement between the three radiologists was moderate (k = 0.534). The best interobserver agreement could be reached for pneumothorax (k = 0.708) and pleural effusion (k = 0.699), while the worst was obtained for rib fractures (k = 0.412).The CAD system has the potential to improve the detection of infectious consolidation and pulmonary nodules on CXR images.
- Published
- 2022