Identification of texture mri brain abnormalities on first-episode psychosis and clinical high-risk subjects using explainable artificial intelligence

HIGHLIGHTS

SUMMARY

    The authors examined potential differences between FEP, CHR with later transition to psychosis (CHR_T), CHR with no transition to psychosis (CHR_NT), and HC, by employing six texture feature maps extracted from non-segmented MR images and feeding into a deep neural_network binary classification schema. Instead of applying conventional methods which show greater performance than deep neural_networks, the authors employed an innovative approach that addresses a frequent concern about artificial_intelligence methods, i.e., the explainability of results. The goal is to gain insights into the examined disorders using radiomics texture features and explainable AI which . . .

     

    Logo ScioWire Beta black

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

    Thanks :)

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

     

Scroll to Top

Add A Knowledge Base Question !

+ = Verify Human or Spambot ?