Research

Randomizing Human Brain Function Representation for Brain Disease Diagnosis

• Accepted by IEEE Transactions on Medical Imaging, 2024;
• Codes and pretrained weights are available at https://github.com/mjliu2020/RandomFR.

Resting-state fMRI (rs-fMRI) is an effective tool for quantifying functional connectivity (FC), which plays a crucial role in exploring various brain diseases. Due to the high dimensionality of fMRI data, FC is typically computed based on the region of interest (ROI), whose parcellation relies on a pre-defined atlas. However, utilizing the brain atlas poses several challenges including 1) subjective selection bias in choosing from various brain atlases, 2) parcellation of each subject’s brain with the same atlas yet disregarding individual specificity; 3) lack of interaction between brain region parcellation and downstream ROI-based FC analysis. To address these limitations, we propose a novel randomizing strategy for generating brain function representation to facilitate neural disease diagnosis. Specifically, we randomly sample brain patches, thus avoiding ROI parcellations of the brain atlas. Then, we introduce a new brain function representation framework for the sampled patches. Each patch has its function description by referring to anchor patches, as well as the position description. Furthermore, we design an adaptive-selection-assisted Transformer network to optimize and integrate the function representations of all sampled patches within each brain for neural disease diagnosis. To validate our framework, we conduct extensive evaluations on three datasets, and the experimental results establish the effectiveness and generality of our proposed method, offering a promising avenue for advancing neural disease diagnosis beyond the confines of traditional atlas-based methods. Our code is available at https://github.com/mjliu2020/RandomFR.

Hierarchical Encoding and Fusion of Brain Functions for Depression Subtype Classification

• Accepted by IEEE Transactions on Affective Computing, 2024.

Depression is a serious mental disorder with complex etiology, exhibiting strong heterogeneity in clinical manifestations such as various subtypes. Research on depression subtypes may deepen the understanding of the disease, contributing to the diagnosis and prognosis. While brain functional network and graph neural networks (GNNs) provide such a means, the task is still challenged by limited feature encoding from the informative fMRI data, ineffective information fusion of brain functional network, and small size of the recruited subjects. Therefore, we propose a hierarchical encoding and fusion framework of brain functions. First, we pre-train a model to extract the features from individual brain regions, which signify nodes in the brain functional network. Then, distinct graphs are constructed to link the nodes within each subject, resulting in multi-view graphs of the brain functional network. We further develop a graph fusion strategy to integrate the multi-view information, by referring to the local encoding of the nodes and their interactions across multiple graph instances. Finally, we attain the classification of depression subtypes based on the fused graph representation. The experimental results demonstrate that our method can superiorly distinguish major depression subtypes and outperform the state-of-the-art methods.

Affinity Learning Based Brain Function Representation for Disease Diagnosis

• Accepted by Medical Image Computing and Computer Assisted Intervention (MICCAI), 2024.

Resting-state functional magnetic resonance imaging (rsfMRI) serves as a potent means to quantify brain functional connectivity (FC), which holds potential in diagnosing diseases. However, conventional FC measures may fall short in encapsulating the intricate functional dynamics of the brain; for instance, FC computed via Pearson correlation merely captures linear statistical dependencies among signals from different brain regions. In this study, we propose an affinity learning framework for modeling FC, leveraging a pre-training model to discern informative function representation among brain regions. Specifically, we employ randomly sampled patches and encode them to generate region embeddings, which are subsequently utilized by the proposed affinity learning module to deduce function representation between any pair of regions via an affinity encoder and a signal reconstruction decoder. Moreover, we integrate supervision from large language model (LLM) to incorporate prior brain function knowledge. We evaluate the efficacy of our framework across two datasets. The results from downstream brain disease diagnosis tasks underscore the effectiveness and generalizability of the acquired function representation. In summary, our approach furnishes a novel perspective on brain function representation in connectomics.