An Adaptive K-means Approach for Assessment of Ventilation Defects in Asthma and Cystic Fibrosis Using Hyperpolarized Helium-3 MRI
Wei Zha 1 , Stanley J Kruger 1 , Robert V Cadman 1 , David Mummy 2 , David J Niles 1 , Scott K Nagle 1,3 , and Sean B Fain 1,3
Department of Medical Physics, University of
Wisconsin-Madison, Madison, WI, United States,
of Biomedical Engineering, University of
Wisconsin-Madison, Madison, United States,
of Radiology, University of Wisconsin-Madison, Madison,
WI, United States
A recent study proposed K-means-based defect
segmentation (Kirby method) and evaluated its
performance on 15 subjects. In our study, 83 asthma and
8 cystic fibrosis subjects underwent spirometry and
hyperpolarized helium-3 MRI. The percent ventilation
defect (%VD) was determined using manual segmentation
and semi-automatically with the Kirby method and an
improved adaptive K-means approach. The adaptive K-means
approach corrected for B1 inhomogeneity, excluded
pulmonary vasculature and determined defects adaptively.
The %VD measured using either manual segmentation or
this improved K-means-based approach was correlated with
the spirometric measures, whereas correlation was not
observed with the Kirby method.
This abstract and the presentation materials are available to members only;
a login is required.