Anatomy

Internal medicine

Radiology

Radiography

Thorax (insect anatomy)

Surgery

Intubation

Receiver operating characteristic

Medicine

Radiology Artificial Intelligence

Purpose To develop an automated measure of COVID-19 pulmonary disease severity on chest radiographs for longitudinal disease tracking and outcome prediction. Materials and Methods A convolutional Siamese neural network–based algorithm was trained to output a measure of pulmonary disease severity on chest radiographs (pulmonary x-ray severity [PXS] score), using weakly supervised pretraining on approximately 160 000 anterior-posterior images from CheXpert and transfer learning on 314 frontal chest radiographs from patients with COVID-19. The algorithm was evaluated on internal and external test sets from different hospitals (154 and 113 chest radiographs, respectively). PXS scores were correlated with radiographic severity scores independently assigned by two thoracic radiologists and one in-training radiologist (Pearson r). For 92 internal test set patients with follow-up chest radiographs, PXS score change was compared with radiologist assessments of change (Spearman ρ). The association between PXS score and subsequent intubation or death was assessed. Bootstrap 95% CIs were calculated. Results PXS scores correlated with radiographic pulmonary disease severity scores assigned to chest radiographs in the internal and external test sets (r = 0.86 [95% CI: 0.80, 0.90] and r = 0.86 [95% CI: 0.79, 0.90], respectively). The direction of change in PXS score in follow-up chest radiographs agreed with radiologist assessment (ρ = 0.74 [95% CI: 0.63, 0.81]). In patients not intubated on the admission chest radiography, the PXS score predicted subsequent intubation or death within 3 days of hospital admission (area under the receiver operating characteristic curve = 0.80 [95% CI: 0.75, 0.85]). Conclusion A Siamese neural network–based severity score automatically measures radiographic COVID-19 pulmonary disease severity, which can be used to track disease change and predict subsequent intubation or death. Supplemental material is available for this article. © RSNA, 2020

Automated Assessment and Tracking of COVID-19 Pulmonary Disease Severity on Chest Radiographs Using Convolutional Siamese Neural Networks