Artificial intelligence (AI)-derived computer-aided detection (CAD) software for detecting and measuring lung nodules in CT scan images

Research is recommended on the prevalence of lung nodules in people who have a chest CT scan because of signs or symptoms that suggest lung cancer.

Research in, and outside of, targeted lung cancer screening is recommended on:

• the accuracy of AI-Rad Companion Chest CT, AVIEW LCS+, ClearRead CT, contextflow SEARCH Lung CT, InferRead CT Lung, Lung AI, qCT‑Lung, SenseCare‑Lung Pro, Veolity, Veye Lung Nodules, and VUNO Med-LungCT AI plus clinician review compared with clinician review alone to detect, measure and assess the growth of lung nodules

• the effect of using the software on clinical decision making

• the effect of using the software on scan review and reporting time.
  
  Studies should ideally compare more than 1 software and should report per-person results. They should also consider reporting data separately for subgroups, if using the technologies may be particularly useful or less effective for those subgroups. For example:

• people with underlying lung conditions, and people whose family background means they are more likely to have subsolid nodules

• scans reviewed by more experienced and less experienced reviewers

• outside of targeted screening, people who had CT scans:

  • with contrast

  • without contrast.