eduzhai > Applied Sciences > Engineering >

Measure Anatomical Thickness from Cardiac MRI with Deep Neural Networks

  • king
  • (0) Download
  • 20210507
  • Save

... pages left unread,continue reading

Document pages: 12 pages

Abstract: Accurate estimation of shape thickness from medical images is crucial inclinical applications. For example, the thickness of myocardium is one of thekey to cardiac disease diagnosis. While mathematical models are available toobtain accurate dense thickness estimation, they suffer from heavycomputational overhead due to iterative solvers. To this end, we propose novelmethods for dense thickness estimation, including a fast solver that estimatesthickness from binary annular shapes and an end-to-end network that estimatesthickness directly from raw cardiac images.We test the proposed models on threecardiac datasets and one synthetic dataset, achieving impressive results andgeneralizability on all. Thickness estimation is performed without iterativesolvers or manual correction, which is 100 times faster than the mathematicalmodel. We also analyze thickness patterns on different cardiac pathologies witha standard clinical model and the results demonstrate the potential clinicalvalue of our method for thickness based cardiac disease diagnosis.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×