HIGHLIGHTS
- who: Vu00edctor M. Campello from the Institut University Heart Research UK, London, UK have published the article: Minimising multi-centre radiomics variability through image normalisation: a pilot study, in the Journal: Scientific Reports Scientific Reports
- what: This study showed that centre-related information removal does not imply good generalisation ability for classification.
- how: In this work a multi-centre cardiac MRI dataset was considered to analyse the effect of several imageand feature-based normalisation techniques over radiomic features variability and model generalisation across institutions.
- future: Studies with a larger sample size . . .
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.