Meeting Banner
Abstract #3729

Unsupervised Reconstruction for Ungated Ghost Angiography by Clustering of Image Features

Sotirios A. Tsaftaris1,2, Erik Offerman3, Robert R. Edelman3, Ioannis Koktzoglou3

1Electrical Engineering and Computer Science, Northwestern University, Evanston, IL, United States; 2Radiology, Northwestern University, Chicago, IL, United States; 3Radiology, NorthShore University HealthSystem, Evanston, IL, United States


Ghost magnetic resonance angiography (MRA) has been proposed as an unenhanced and ungated method for angiography. The method requires manual post-processing to identify suitable slices in a large stack from which to create an interpretable angiogram. To maximize the contrast of the final angiogram it is necessary to eliminate slices located within the body and to carefully select the slices that contain conspicuous ghost artifacts. This time-consuming process can also introduce unwanted inter- and intra- observer variability. The purpose of this work was to completely automate the reconstruction process during ungated and non-contrast-enhanced Ghost MRA using image analysis and clustering.