AUTHOR=Zhang Shu , Wang Ruoyang , Wang Junxin , He Zhibin , Wu Jinru , Kang Yanqing , Zhang Yin , Gao Huan , Hu Xintao , Zhang Tuo 

TITLE=Differentiate preterm and term infant brains and characterize the corresponding biomarkers via DICCCOL-based multi-modality graph neural networks

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 16 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2022.951508

DOI=10.3389/fnins.2022.951508

ISSN=1662-453X

ABSTRACT=Preterm birth is a world-wide problem which affects infants throughout their lives significantly. Therefore, differentiating brain disorders, and further identifying and characterizing the corresponding biomarkers are key issues to investigate the effects from the preterm birth, which facilitates the interventions for neuroprotection and improves outcomes of prematurity. Until now, many efforts have been made, however, most of the studies are merely focused on either functional or structural perspective. In addition, lacking an effective framework not only jointly studying the brain function and structure at a group-level, but also retaining the individual differences among the subjects. In this work, a novel dense individualized and common connectivity-based cortical landmarks (DICCCOL)-based multi-modality Graph Neural Networks (DM-GNN) framework is proposed to differentiate preterm and term infant brains and characterize the corresponding biomarkers. This framework adopts the DICCCOL system as the initialized graph nodes of GNN for each subject, utilizing both functional and structural profiles and effectively retaining the individual differences. To be specific, brain functional magnetic resonance imaging (fMRI) provides the features for the graph nodes, and brain fiber connectivity is utilized as the structural representation of the graph edges. Self-attention graph pooling (SAGPOOL)-based GNN is then applied to jointly study the brain function and structure and identify the biomarkers. Our results successfully demonstrate that the proposed framework can effectively differentiate the preterm and term infant brains. Furthermore, the self-attention-based mechanism can accurately calculate the attention score and recognize the most significant biomarkers. In this work, not only 87.6% classification accuracy is observed for the developing Human Connectome Project (dHCP) dataset, but also distinguishing features are explored and extracted. Our work provides a novel and uniform framework to differentiate brain disorders and characterize the corresponding biomarkers.