We retrospectively applied the AI solution to all consecutive non-contrast computed tomography (CT) head scans to assess the prevalence of ICH in scans which were reported as negative for ICH. The study was performed at six imaging sites affiliated to our institution. In the 6,565 non-contrast CT head scans, which met the inclusion criteria, 5,585 scans were reported to have no ICH (“negative-by-report” cases). We applied an AI solution to these “negative-by-report” cases.
The AI solution suggested there were ICH in 28 of these scans (“negative-by-report” and “positive-by-AI solution”). After consensus review by three neuroradiologists, 16 of these scans were found to have ICH which was not reported (missed diagnosis), with false negative rate of radiologists for ICH detection at 1.6%.
Our study demonstrates that the AI solution can help radiologists to diagnose ICH and decrease error rate.