For the first time, we propose using a multiple instance learning based convolution-free transformer model, called Multiple Instance Neuroimage Transformer (MINiT), for the classification of T1-weighted (T1w) MRIs. We first present several variants of transformer models adopted for neuroimages. These models extract non-overlapping 3D blocks from the input volume and perform multi-headed self-attention on a sequence of their linear projections. MINiT, on the other hand, treats each of the non-overlapping 3D blocks of the input MRI as its own instance, splitting it further into non-overlapping 3D patches, on which multi-headed self-attention is computed. As a proof-of-concept, we evaluate the efficacy of our model by training it to identify sex from T1w-MRIs of two public datasets: Adolescent Brain Cognitive Development (ABCD) and the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA). The learned attention maps highlight voxels contributing to identifying sex differences in brain morphometry.

I've never liked rushing through video games. I prefer to take my time, strolling aimlessly through the digital brush and marveling at each beautifully-realized world. There's just one problem: I don't have 100 hours to spend on Monster Hunter World or Assassin's Creed: Origins. Still, when I dive into a game I want to immerse myself and move at a speed that respects the time and effort put in by the developers. That glacial pace means I rarely play the same game twice.