Abstract #2599

Effect of ISODATA Dimensionality on Spatiotemporal Evolution of Ischemic Brain Injury in Acute Ischemic Stroke

Jerry S. Cheung¹, Enfeng Wang^1,2, Xiaoying Wang³, Phillip Zhe Sun¹

¹Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, MGH & Harvard Medical School, Charlestown, MA 02129, United States; ²Department of Radiology, 3rd Affiliated Hospital, Zhengzhou University, China, People's Republic of; ³Neuroprotection Research Laboratory, Department of Radiology & Neurology, MGH & Harvard Medical School, Charlestown, MA 02129, United States

Iterative self-organizing data analysis technique algorithm (ISODATA) has been increasingly used to classify multi-parametric data for delineation of heterogeneous ischemic damage. Our study compared two different dimensionalities (1D vs. 2D) of ISODATA signature vector in ISODATA parameter space to segment evolving PWI/DWI mismatch. We showed that accurate delineation of PWI/DWI mismatch with 1D signature vector outperformed conventional 2D analysis, and offer a useful means to identify ischemic penumbra.