Deep learning classification of active tuberculosis lung zones wise manifestations using chest x-rays: a multi label approach

HIGHLIGHTS

• who: James Devasia from the Department have published the article: Deep learning classification of active tuberculosis lung zones wise manifestations using chest X-rays: a multi label approach, in the Journal: Scientific Reports Scientific Reports
• what: The authors examine the performance of grad-CAM image to visually analyse the pathological changes in the CXR (ground truth) thereby visualizing the signals of Tuberculosis. The work shows better AUC for Cavity and Consolidation and comparable AUC for Pleural Effusion. The authors focused on the classification of active pulmonary tuberculosis manifestations both image wise and lung zone wise . . .
  

   

  

  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.