Meeting Banner
Abstract #5347

Automated Pattern Recognition Analysis of Intravoxel Incoherent Motion (IVIM)-diffusion to Segment Hypo-perfused Stroke Region

MinJung Jang1, SoHyun Han2, and HyungJoon Cho1

1Ulsan National Institute of Science and Technology, Ulsan, Republic of Korea, 2Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Cambridge, MA, United States

The variation in fitted perfusion factors (f) from different fitting models and the necessary parameter thresholdings are one of the challenges in the robust interpretation of intravoxel incoherent motion (IVIM) diffusion data [1-3]. The purpose of this study is to investigate the feasibility of applying constrained nonnegative matrix factorization (cNMF) to IVIM-diffusion data for the automatic segmentation of hypo-perfused stroke region of rat brain without any model-fittings nor thresholdings.

This abstract and the presentation materials are available to members only; a login is required.

Join Here