Faster and Better: How Anomaly Detection Can Accelerate and Improve Reporting of Head Computed Tomography

Abstract

Background: Most artificial intelligence (AI) systems are restricted to solving a pre-defined task, thus limiting their generalizability to unselected datasets. Anomaly detection relieves this shortfall by flagging all pathologies as deviations from a learned norm. Here, we investigate whether diagnostic accuracy and reporting times can be improved by an anomaly detection tool for head computed tomography (CT), tailored to provide patient-level triage and voxel-based highlighting of pathologies. Methods: Four neuroradiologists with 1–10 years of experience each investigated a set of 80 routinely acquired head CTs containing 40 normal scans and 40 scans with common pathologies. In a random order, scans were investigated with and without AI-predictions. A 4-week wash-out period between runs was included to prevent a reminiscence effect. Performance metrics for identifying pathologies, reporting times, and subjectively assessed diagnostic confidence were determined for both runs. Results: AI-support significantly increased the share of correctly classified scans (normal/pathological) from 309/320 scans to 317/320 scans (p = 0.0045), with a corresponding sensitivity, specificity, negative- and positive- predictive value of 100%, 98.1%, 98.2% and 100%, respectively. Further, reporting was significantly accelerated with AI-support, as evidenced by the 15.7% reduction in reporting times (65.1 ± 8.9 s vs. 54.9 ± 7.1 s; p < 0.0001). Diagnostic confidence was similar in both runs. Conclusion: Our study shows that AI-based triage of CTs can improve the diagnostic accuracy and accelerate reporting for experienced and inexperienced radiologists alike. Through ad hoc identification of normal CTs, anomaly detection promises to guide clinicians towards scans requiring urgent attention.

AI assisted reader evaluation in acute CT head interpretation (AI-REACT): protocol for a multireader multicase study

“…Few studies have directly evaluated the impact of AI assistance in improving the accuracy of general radiologists in NCCTH interpretation, 12 18 19 and fewer have evaluated its impact on reporter speed and confidence. 18 Other professional groups who may use AI include EM clinicians, who commonly review CT scans prior to radiology reports becoming available, in order to expedite patient management. 20 21 To our knowledge, only one previous study has evaluated the impact of AI assistance with other groups of healthcare professionals who regularly review or act on NCCTH interpretations, such as EM clinicians and radiographers.…”