Automatic Detection of Free Intra-abdominal Air in Computed Tomography

Pneumoperitoneum, the presence of air within the peritoneal cavity, is a comparatively rare but potentially urgent critical finding in patients presenting with acute abdominal pain. When prior laparoscopic treatment can be ruled out as a cause, it can indicate perforation of the wall of a hollow organ, which typically necessitates immediate surgery. Computed tomography (CT) is the gold standard for detecting free intra-abdominal air, yet subtle cases are easy to miss. More crucially though, if there is no initial suspicion of pneumoperitoneum, the scans may not be read immediately as other emergency patients take precedence. Therefore, fully automatic detection would provide a direct clinical benefit. In this work, an algorithm for this purpose is proposed which follows a sliding-window approach and has a deep-learning based classifier at its core. In addition to the baseline method, variants that rely on multi-scale inputs and recurrent layers to increase robustness are presented. In a five-fold cross validation on the training data, consisting in abdominal CT scans of 110 affected patients and 29 controls, our method achieved an area under the receiver-operating characteristic curve of 89% for case-level classification. Due to its high specificity at reasonable detection rates, it shows potential for use in triage, where false alerts are considered particularly harmful as they may disrupt the clinical workflow.