Skip to main content
. 2021 May 22;21:88. doi: 10.1186/s12880-021-00620-5

Fig. 4.

Fig. 4

T-distributed stochastic neighbor embedding clustering for all segmentations: these figures demonstrate strong clustering of the data under a T-SNE algorithm, and this allows apparently perfectly discrimination between lesions and non-lesions with T1 (a) T2 (b) and combining the two properties (c) features. NAWM: frontal normal appearing white matter; MS: Multiple Sclerosis. The data depicted in circles refers to patients with MS and the data on square to controls