Weikang Gong

This paper develops rare-variant polygenic risk scores (rvPRSs) using whole-genome sequencing data from the UK Biobank, showing they improve disease risk stratification and biological interpretability beyond common-variant PRSs.

The paper introduces Brain-DiT, a deep generative model for analyzing task-fMRI data, identifying cognitive regions and subgroups linked to psychiatric conditions like depression and alcohol abuse.

This paper introduces a semi-supervised, multimodal, and multi-task fusion method for discovering image-derived phenotypes from brain imaging data, showing improved prediction accuracy compared to conventional approaches.

The paper improves predictions of individual differences in task-evoked fMRI activity using a sparse ensemble learner and shows better performance than previous methods.

This paper introduces sPROFUMO, a hierarchical model for estimating functional brain networks in individuals and populations from large fMRI datasets, showing improved performance over traditional methods.

The paper describes a lightweight deep convolutional neural network for brain age prediction from MRI scans, achieving top results in the PAC 2019 challenge.

This paper introduces a multimodal independent component analysis method to discover imaging-derived phenotypes from large neuroimaging datasets, improving predictive power for phenotypic and behavioral variables.

The paper introduces a lightweight deep neural network, SFCN, for accurate brain age prediction using MRI data, achieving state-of-the-art performance on UK Biobank data.

This study introduces an overall reproducibility index for MRI-based association studies and evaluates its performance across multiple datasets, showing that sample size and experimental factors influence reproducibility.

This study examines age-related changes in dynamic functional network connectivity across the adult lifespan, finding reduced variability and specific topological features associated with cognitive aging.

This paper develops a statistical framework for connexel-wise analysis in brain-wide association studies, improving power and reducing false positives using spatial information from fMRI data.

This paper introduces sKPCR, a method for identifying voxel-phenotype associations in dense connectomes, showing better reproducibility and overlap with existing schizophrenia findings.

The paper introduces a toolbox to generate functional and genetic annotations for neuroimaging data, demonstrating its utility in interpreting brain regions and psychiatric disorders.