A large, curated, open-source stroke neuroimaging dataset to improve lesion segmentation algorithms

HIGHLIGHTS

• who: Sook-Lei Liew from the Methods for Automated Lesion Segmentation Using ATLAS v12. A summary of published automated lesion segmentation methods that were trained from ATLAS v1.2, with brief summaries of their method, validation method, and reported Dice coefficient. Blue rows indicate methods using cross-validation. Yellow rows indicate methods using one hold-out. *Indicates an out-of-distribution method that is trained only on non-lesioned images and detects outliers that possibly represent stroke lesions. **Indicates an incorrect equation for the Dice index computation have published the article: A large, curated, open-source stroke . . .
  

   

  

  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.