1857
Disentangling the heterogeneity of MCI condition by unsupervised clustering of brain measurements on ASL and T1w MR imaging
Paolo Bosco1, Laura Biagi1, Giovanni Cioni2, Michela Matteoli3, Alessandro Sale3, Nicoletta Berardi3, Michela Tosetti1, and the Train the Brain Consortium4
1FiRMLAB, IRCCS Stella Maris Foundation, Pisa, Italy, 2IRCCS Stella Maris Foundation, Pisa, Italy, 3Institute of Neuroscience of the CNR, Pisa, Italy, 4the Train the Brain Consortium, Pisa, Italy
A data-drive clustering approach on structural and perfusion brain MR imaging on a cohort of 141 MCI subjects is able to elucidate homogeneous structural and perfusion profiles with peculiar clinical features.
Figure 1: Preprocessing scheme
Figure 2: From volumetric measurements to gray matter clusters