Performance of ai to exclude normal chest radiographs to reduce radiologists’ workload

HIGHLIGHTS

• What: The aim of this study is to investigate the potential of a commercially available AI product to identify normal chest radiographs in a consecutive clinical series of radiographs from two different hospitals. This was considerably higher than the 28% in the study of Plesner et_al This may be explained by the fact that a different commercial AI system was used compared to the other studies. Another aspect to consider is that the AI system used in the study is not specifically designed to find normal radiographs, but rather to find the predefined ten distinct abnormalities seen . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.