A multitask deep learning approach for pulmonary embolism detection and identification

HIGHLIGHTS

• who: Xiaotian Ma from the SchoolThe University have published the research: A multitask deep learning approach for pulmonary embolism detection and identification, in the Journal: Scientific Reports Scientific Reports
• what: The authors focus on the position of the present PE and show selected samples of the true-positive and falsenegative results according to the probability thresholds determined in Table 2. To select the best model on validation set, the authors compare the loss in each epoch with the minimum one in all previous epochs, and save the model if the loss in the current epoch . . .
  

   

  

  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.