Artificial intelligence – aided automatic detection of unexpected and abnormal findings in head MRI

Author(s): Professor Sotirios Bisdas

Hospital: University College London Hospitals NHS Foundation Trust, University College London

Reference: RAD Magazine, 46, 543, 11-12


The NHS spends around £2 billion per annum delivering imaging services. The ageing population and new treatments that have rendered previously devastating neurological diseases into chronic entities constantly increase the number of brain MRI scans (approximately 63k/month with 20% annual increase since 2015) with only 33% of the examinations reported on the same day. With rising activity this level of service is not likely to be sustainable. In addition, surveys have shown significant nationwide variation in workforce skill mix and roles. It is increasingly difficult for trusts to find independent cost-effective companies to report specialised examinations resulting in backlogs and unreported examinations, posing a patient safety issue. Notably, the clinical appropriateness for outsourcing reports in terms of confidence in the quality and consistency of reports is questioned and, not uncommonly, this may lead to misdiagnosis, errors and misses or delays in reporting that will cause legal claims.

This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read more