%0 Journal Article
%@ 1053-1807
%A Tsaftaris, Sotirios A.
%A Offerman, Erik
%A Edelman, Robert R.
%A Koktzoglou, Ioannis
%C Department of Electrical Engineering and Computer Science, Northwestern University, Evanston, Illinois, USA; Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Illinois, USA; Department of Radiology, NorthShore Universi
%D 2010
%F eprints:798
%I Wiley-Blackwell
%J Journal of magnetic resonance imaging
%K Ghost angiography; Image reconstruction; Cluster analysis
%N 3
%P 655-662
%T Fully automated reconstruction of ungated ghost magnetic resonance angiograms
%U http://eprints.imtlucca.it/798/
%V 31
%X To completely automate the reconstruction process during noncardiac-gated unenhanced ghost magnetic resonance angiography (MRA).Ungated unenhanced ghost MRA of the calf was performed in 16 volunteers. K-means and fuzzy c-means (FCM) clustering algorithms using prominent image features were applied to automatically create angiograms of the calf in volunteers undergoing ungated ghost MRA. Ghost angiograms reconstructed automatically were compared to those created manually on the basis of diagnostic image quality and apparent arterial-to-background contrast-to-noise ratio (CNR). Images were also ranked by an expert user in their order of preference using an ordinal scale.Compared with the ghost angiograms created manually, ghost angiograms reconstructed automatically with the use of clustering analysis provided similar arterial-to-background CNR values. No differences in diagnostic quality or preference were identified between images reconstructed manually and automatically.We present fully automated image reconstruction algorithms for use with ungated and unenhanced ghost MRA. These automated algorithms, based on the use of k-means or FCM clustering, can be used to eliminate manual postprocessing that is time-consuming and subject to variability.