Summary

Summary

  • The technologies described in this briefing are artificial intelligence (AI) technologies for chest CT. They are used for assisting with triaging, reporting, and identifying abnormalities.

  • The innovative aspects are that the software helps radiologists and radiographers detect abnormalities in chest CT images.

  • The intended place in therapy would be to support radiologists and radiographers when reviewing chest CT images in secondary care for people who have been referred for chest CT.

  • The main points from the evidence summarised in this briefing are from 2 retrospective studies. The best quality evidence came from 1 UK study showing that Veye Chest (Aidence) performed similarly to chest radiologists for lung nodule segmentation growth assessment. The studies were limited in quality and no studies were published in full.

  • Key uncertainties around the evidence for CT AI are that more published evidence is needed to show how the technologies perform compared with radiologists, and how they impact clinical management and outcomes in CT reporting. Generalisability may also be limited if the AI algorithm is trained on a non-local population. The technology will not be used instead of a radiologist but as a tool to aid faster diagnosis. Further research is needed to understand the risks of AI automation.

  • The cost of the technologies varies significantly. icolung is offered pro bono as part of the icovid.ai initiative. Veye Chest costs between £5 and £7.50 per output (depending on selected features and volume of scans). Veolity (MeVis) offers a perpetual licence for £44,000 with no per scan costs. The 2019/20 national tariff for a CT scan of 1 area is £69 for people aged over 18 and £73 for people aged between 6 and 18. The cost of reporting is £20 for all ages. The use of AI technologies has the potential to reduce resource use by helping reduce the workload of staff reading CT images.