Background: Pneumothorax remains one of the most common complications after computed tomography (CT)-guided lung biopsies. Radiographic features including bullae and nodule size are possible markers for post-biopsy pneumothorax. We determine whether a convolutional neural network (CNN) can accurately predict a pneumothorax after lung biopsy based on pre-operative imaging alone.
Methods: With institutional review board approval, we retrospectively evaluated 3,822 patients who underwent a CT-guided lung biopsy between 2011 to 2019. Two image sets were created with CT scout images (1300 patients, 650 pneumothoraces) and chest x-rays (CXR) taken within three months pre-procedure (884 patients, 140 pneumothoraces). Using pre-operative images, CNNs of varying layer depths were trained using transfer learning to predict the development of a pneumothorax post-biopsy. Performance against models were compared using sensitivity analysis and the McNemar's test.
Results: The CNN models trained with CT scout images performed near chance. However, the models performed better with CXR radiographs taken within three months pre-biopsy. For the anterior-posterior view, sensitivity was 0.40, specificity was 0.89, PPV was 0.43, and NPV was 0.87 (AUC = 0.67). For the lateral view, sensitivity was 0.4, specificity was 0.80, PPV was 0.32, and NPV was 0.86 (AUC = 0.65). Increasing CNN layers did not affect performance (p > 0.05).
Conclusion: Chest radiographs taken within three months of lung biopsy may provide important radiographic information for CNNs to assess pneumothorax risk in patients prior to CT-guided lung biopsies. However, more baseline and standardized CXRs before biopsies are necessary to create a robust model for clinical application.