An Integrated Approach for Perfusion Lesion Segmentation Using MR Perfusion for Acute Ischemic Stroke

Dattesh D. Shanbhag¹, Rakesh Mullick¹, Sumit K. Nath¹, Catherine Oppenheim², Marie Luby³, Katherine D. Ku³, Lawrence L. Latour³, Steven Warach³, - NINDS Natural History of Stroke Investigators³

In this work, we demonstrate a fully automated, fast and robust analysis pipeline for segmenting the perfusion lesion on different PWI maps (MTT, Tmax, TTP) and mismatch in acute ischemic stroke setting. The automatically segmented perfusion lesion and mismatch volume showed a strong correlation of 0.9 and 0.88 respectively, when compared to manually segmented PWI lesion on MTT maps. Variability for perfusion lesion volume estimates were lower compared to manual inter-rater variability, but was higher for mismatch estimates. Overall, Tmax PWI lesion had a lower volume compared to MTT PWI lesion.