Effective and Interpretable fMRI Analysis via Functional Brain Network Generation
This work addresses the challenge of improving fMRI analysis for neuroscience research and clinical predictions, though it appears incremental as it builds on existing GNN methods.
The authors tackled the problem of noisy and task-unaware functional brain networks from fMRI data by developing an end-to-end trainable pipeline that extracts features, generates networks, and makes predictions using GNNs, guided by downstream tasks, showing superior effectiveness and unique interpretability in experiments on PNC fMRI data.
Recent studies in neuroscience show great potential of functional brain networks constructed from fMRI data for popularity modeling and clinical predictions. However, existing functional brain networks are noisy and unaware of downstream prediction tasks, while also incompatible with recent powerful machine learning models of GNNs. In this work, we develop an end-to-end trainable pipeline to extract prominent fMRI features, generate brain networks, and make predictions with GNNs, all under the guidance of downstream prediction tasks. Preliminary experiments on the PNC fMRI data show the superior effectiveness and unique interpretability of our framework.