Ultra-short echo-time magnetic resonance imaging lung segmentation with under-Annotations and domain shift

Fumin Guo1, Dante Pi Capaldi2, David G McCormack3

  • 1Department of Medical Biophysics, University of Toronto, Toronto, ON, M4N 3M5, Canada.

Summary

A new continuous kernel k-means (CKKM) algorithm improves lung segmentation for ultra-short echo-time (UTE) MRI, enhancing lung disease phenotyping. This method achieves accuracy comparable to expert segmentation with minimal computational cost.

Related Concept Videos