eduzhai > Applied Sciences > Engineering >

Parkinsons Disease Detection with Ensemble Architectures based on ILSVRC Models

  • king
  • (0) Download
  • 20210505
  • Save

... pages left unread,continue reading

Document pages: 7 pages

Abstract: In this work, we explore various neural network architectures using MagneticResonance (MR) T1 images of the brain to identify Parkinson s Disease (PD),which is one of the most common neurodegenerative and movement disorders. Wepropose three ensemble architectures combining some winning ConvolutionalNeural Network models of ImageNet Large Scale Visual Recognition Challenge(ILSVRC). All of our proposed architectures outperform existing approaches todetect PD from MR images, achieving upto 95 detection accuracy. We also findthat when we construct our ensemble architecture using models pretrained on theImageNet dataset unrelated to PD, the detection performance is significantlybetter compared to models without any prior training. Our finding suggests apromising direction when no or insufficient training data is available.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×