Performance and Predictive Value of a User-Independent Platform for CT Perfusion Analysis: Threshold-Derived Automated Systems Outperform Examiner-Driven Approaches in Outcome Prediction of Acute Ischemic Stroke

^aFrom the Departments of Radiology and Imaging Sciences (S.D., L.S.A., J.W.A., D.Q.)
^bNeurology (S.R., M.J.W., F.N.), Emory University Hospital, Atlanta, Georgia
^cDepartment of Radiology (R.B.), Stanford University Hospital, Stanford, California
^dInstitut für Radiologie und Nuklearmedizin (M.S.), Kantonsspital Winterthur, Winterthur, Switzerland
^eDepartment of Neurology (O.K.-H.), Catholic Health System, Buffalo, New York.

Please address correspondence to Roland Bammer, PhD, Radiologic Sciences Lab, Department of Radiology, Stanford University Hospital, Lucas Center P271, 1201 Welch Rd, Stanford, CA 94305; e-mail: rbammer{at}stanford.edu; and Seena Dehkharghani, MD, Neuroradiology Division; Attention: Mary Davis, Department of Radiology and Imaging Sciences, Emory University Hospital, 1364 Clifton Rd NE, Atlanta, GA 30322; e-mail: seena.dehkharghani{at}emory.edu