Abstract #1020

Validation of Automatic Segmentation Algorithms of DWI in Acute Stroke Patients in Independent Data

Steven Mocking¹,², Raquel Bezerra¹, Elissa McIntosh¹, Izzudin Diwan¹, Priya Garg¹, William Taylor Kimberly³, Ethem Murat Arseva¹, Hakan Ay¹, Aneesh B. Singhal³, William A. Copen⁴, Pamela Schaefer⁴, Ona Wu¹

¹Athinoula A. Martinos Center for Biomedical Imaging, Dept. of Radiology, MGH, Charlestown, MA, United States; ²Image Sciences Institute, University Medical Center Utrecht, Utrecht, Netherlands; ³Dept. of Neurology, MGH, Boston, MA; ⁴Dept. of Radiology, MGH, Boston, MA

We validated five algorithms for segmenting DWI lesions in acute ischemic stroke on an independent dataset and investigated the proportion of acutely misclassified tissue with follow-up manual outlines. Performance of the algorithms on the validation dataset was comparable to results on the training dataset, with the naive Bayes approach providing best sensitivity and Dice similarity coefficient. In many cases, several voxels classified as lesion or normal by the automatic algorithms but not by the manual outliner were found respectively to be infarcted or normal on follow-up imaging. Consequently, apparent misclassification may partially be a result of reader variation.