Evaluation of techniques to improve a deep learning algorithm for the automatic detection of intracranial haemorrhage on ct head imaging

HIGHLIGHTS

• who: Melissa Yeo from the Two open-source retrospective datasets were used in this studyBoth datasets were composed of de-identified data, licensed for non-commercial and academic use. The study was approved by the local institutional ethics review board. The first dataset, the Kaggle dataset, was obtained from a , online Kaggle challenge hosted by the Radiological Society of North America [14]. This contained, NCCT slices (21, studies), collected across four research institutions (Stanford University, Thomas Jefferson University, Unity Health Toronto and Universidade Federal de Su00e3o Paulo). The data had been manually labelled by sixty radiologists from . . .
  

   

  

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

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

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