Hierarchical brain parcellation with uncertainty
This addresses the need for more accurate and interpretable brain mapping in neuroscience, though it is incremental as it builds on existing parcellation methods by incorporating hierarchy and uncertainty.
The paper tackles the problem of brain parcellation by introducing a method that accounts for hierarchical label structures and models uncertainty at each branch, outperforming flat uncertainty methods and enabling self-consistent parcellations with decomposed uncertainty estimates.
Many atlases used for brain parcellation are hierarchically organised, progressively dividing the brain into smaller sub-regions. However, state-of-the-art parcellation methods tend to ignore this structure and treat labels as if they are `flat'. We introduce a hierarchically-aware brain parcellation method that works by predicting the decisions at each branch in the label tree. We further show how this method can be used to model uncertainty separately for every branch in this label tree. Our method exceeds the performance of flat uncertainty methods, whilst also providing decomposed uncertainty estimates that enable us to obtain self-consistent parcellations and uncertainty maps at any level of the label hierarchy. We demonstrate a simple way these decision-specific uncertainty maps may be used to provided uncertainty-thresholded tissue maps at any level of the label tree.