eduzhai > Applied Sciences > Engineering >

X-Ray bone abnormalities detection using MURA dataset

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 12 pages

Abstract: We introduce the deep network trained on the MURA dataset from the StanfordUniversity released in 2017. Our system is able to detect bone abnormalities onthe radiographs and visualise such zones. We found that our solution has theaccuracy comparable to the best results that have been achieved by otherdevelopment teams that used MURA dataset, in particular the overall Kappa scorethat was achieved by our team is about 0.942 on the wrist, 0.862 on the handand o.735 on the shoulder (compared to the best available results to thismoment on the official web-site 0.931, 0.851 and 0.729 accordingly). However,despite the good results there are a lot of directions for the futureenhancement of the proposed technology. We see a big potential in the furtherdevelopment computer aided systems (CAD) for the radiographs as the one thatwill help practical specialists diagnose bone fractures as well as boneoncology cases faster and with the higher accuracy.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×