The paper develops a reliable network template and methods to estimate individualized functional networks from resting-state fMRI data across 100k+ individuals, showing how data length and spatial resolution affect network estimation.

bioRxiv · Sep 3, 2022 · PreprintNeuroscience

Machine Learning Predicts Treatment Response in Bipolar & Major Depressive Disorders

Mustafa S. Salman, Eric Verner, H. Jeremy Bockholt, Zening Fu, Maria B. Misiura, Bradley T. Baker, Elizabeth A. Osuch, Jing Sui （Beijing Normal University）， my correct affiliation is beijing normal university, not Qingdao University of Science and Technology, please correct the current affiliation. Thank you, Vince D. Calhoun

The paper uses a kernel SVM algorithm with neuromark ICA to predict treatment response in bipolar and major depressive disorders with up to 89% accuracy.

bioRxiv · May 13, 2022 · PreprintNeuroscience

Individualized Spatial Network Predictions Using Siamese Convolutional Neural Networks: A Resting-State fMRI Study of over 11,000 Unaffected Individuals

Reihaneh Hassanzadeh, Rogers F. Silva, Anees Abrol, Mustafa S. Salman, Anna Katharina Bonkhoff, Yuhui Du, Zening Fu, Thomas P. DeRamus, Eswar Damaraju, Bradley T. Baker, Vince D. Calhoun

This study uses a Siamese CNN framework to predict individual identity from resting-state fMRI data, achieving 88% accuracy in subject discrimination using spatial network pairs.

PLoS ONE · Jan 21, 2022Peer-reviewedNeuroscience

An Approach to Automatically Label & Order Brain Activity/Component Maps

Mustafa S. Salman, Tor Dessart Wager, Eswar Damaraju, Anees Abrol, Victor M. Vergara, Zening Fu, Vince D. Calhoun

The paper introduces a toolbox to automatically label and order brain activity maps with high accuracy using a pretrained model and integration of existing techniques.

Brain Connectivity · May 27, 2021Peer-reviewedNeuroscience

Hype versus hope: Deep learning encodes more predictive and robust brain imaging representations than standard machine learning

Anees Abrol, Zening Fu, Mustafa S. Salman, Rogers F. Silva, Yuhui Du, Sergey Plis, Vince D. Calhoun

This study compares deep learning and standard machine learning on brain imaging data, showing deep learning's superior predictive power and robustness in age and gender classification.

Nature Communications · Jan 13, 2021Peer-reviewedNeuroscience

Parallel Group ICA + ICA: Joint Estimation of Linked Functional Network Variability and Structural Covariation with Application to Schizophrenia

Shile Qi, Jing Sui （Beijing Normal University）， my correct affiliation is beijing normal university, not Qingdao University of Science and Technology, please correct the current affiliation. Thank you, Jiayu Chen, Jingyu Liu, Rongtao Jiang, Rogers F. Silva, Armin Iraji, Eswar Damaraju, Mustafa S. Salman, Dongdong Lin, Zening Fu, Dongmei Zhi, Jessica A. Turner, Juan Bustillo, Judith M. Ford, , Vince D. Calhoun

This paper introduces a method to fuse functional and structural MRI data by integrating temporal information, identifying linked variability and covariation in schizophrenia.

Human Brain Mapping · May 16, 2019Peer-reviewedBioinformatics

Group ICA for Identifying Biomarkers in Schizophrenia: ‘Adaptive’ Networks via Spatially Constrained ICA Show More Sensitivity to Group Differences than Spatio-temporal Regression

Mustafa S. Salman, Yuhui Du, Dongdong Lin, Zening Fu, Alex Fedorov, Eswar Damaraju, Jing Sui （Beijing Normal University）， my correct affiliation is beijing normal university, not Qingdao University of Science and Technology, please correct the current affiliation. Thank you, Jiayu Chen, Andrew R. Mayer, Stefan Posse, Daniel H. Mathalon, Judith M. Ford, Theodorus Van Erp, Vince D. Calhoun

This study compares GIG-ICA and STR for identifying brain functional networks in schizophrenia, finding GIG-ICA more sensitive to group differences and better at classification.

NeuroImage Clinical · Jan 1, 2019Peer-reviewedNeuroscience