Anomaly detection in medical imaging with deep perceptual autoencoders

HIGHLIGHTS

• who: . and colleagues from the Philips Research, Moscow, Russia Goethe University Frankfurt, Frankfurt, Germany have published the article: Anomaly Detection in Medical Imaging with Deep Perceptual Autoencoders, in the Journal: (JOURNAL)
• what: The authors propose to relax this unrealistic assumption by using a very small number of anomalies of confined variability merely to initiate the search of hyperparameters of the model. The authors evaluate the solution on two medical datasets containing radiology digital pathology images where the state-of-the-art anomaly detection models originally devised for natural image benchmarks fail to perform sufficiently well . . .
  

   

  

  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.