Completing complex tasks requires flexible integration of functions across brain regions. While studies have shown that functional networks are altered across tasks, recent work highlights that brain networks exhibit substantial individual differences. Here we asked whether individual differences are important for predicting brain network interactions across cognitive states. We trained classifiers to decode state using data from single person "precision" fMRI datasets across 5 diverse cognitive states. Classifiers were then tested on either independent sessions from the same person or new individuals. Classifiers were able to decode task states in both the same and new participants above chance. However, classification performance was significantly higher within a person, a pattern consistent across model types, datasets, tasks, and feature subsets. This suggests that individualized approaches can uncover robust features of brain states, including features obscured in cross-subject analyses. Individualized approaches have potential to deepen our understanding of brain interactions during complex cognition.

The striatum is interconnected with the cerebral cortex via multiple recurrent loops that play a major role in many neuropsychiatric conditions. Primate cortico-striatal connections can be precisely mapped using invasive tract-tracing. However, noninvasive human research has not mapped these connections with anatomical precision, limited by the practice of averaging neuroimaging data across individuals. Here we utilized highly-sampled resting-state functional connectivity MRI for individually-specific precision functional mapping of cortico-striatal connections. We identified ten discrete, individual-specific subnetworks linking cortex-predominately frontal cortex-to striatum. These subnetworks included previously unknown striatal connections to the human language network. The discrete subnetworks formed a stepped rostral-caudal gradient progressing from nucleus accumbens to posterior putamen; this organization was strongest for projections from medial frontal cortex. The stepped gradient organization fit patterns of fronto striatal connections better than a smooth, continuous gradient. Thus, precision subnetworks identify detailed, individual-specific stepped gradients of cortico-striatal connectivity that include human specific language networks.