eduzhai > Applied Sciences > Engineering >

Deep learning Framework for Mobile Microscopy

  • king
  • (0) Download
  • 20210505
  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: Mobile microscopy is a promising technology to assist and to acceleratedisease diagnostics, with its widespread adoption being hindered by themediocre quality of acquired images. Although some paired image translation andsuper-resolution approaches for mobile microscopy have emerged, a set ofessential challenges, necessary for automating it in a high-throughput setting,still await to be addressed. The issues like in-focus out-of-focusclassification, fast scanning deblurring, focus-stacking, etc. -- all havespecific peculiarities when the data are recorded using a mobile device. Inthis work, we aspire to create a comprehensive pipeline by connecting a set ofmethods purposely tuned to mobile microscopy: (1) a CNN model for stablein-focus out-of-focus classification, (2) modified DeblurGAN architecture forimage deblurring, (3) FuseGAN model for combining in-focus parts from multipleimages to boost the detail. We discuss the limitations of the existingsolutions developed for professional clinical microscopes, proposecorresponding improvements, and compare to the other state-of-the-art mobileanalytics solutions.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×