Author

Mahbaneh Eshaghzadeh Torbati

University of PittsburghORCID 0000-0002-3425-3036Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Signature Assays, Organisms & Methods

Click to filter · or open tag

Research Focus:batch correction / integration· 3 Research Focus:benchmarking· 3 Assay:imaging· 3 Approach:statistical model· 2 Approach:Bayesian inference· 1 Approach:deep learning· 1 Research Focus:dimensionality reduction· 1 Approach:experimental assay· 1

Frequent Co-Authors

Dana TudorascuiD· 3 shared Charles M. LaymoniD· 2 shared Davneet Singh MinhasiD· 2 shared Annabelle ColemaniD· 1 shared Chang-Le Chen· 1 shared Chang‐Le CheniD· 1 shared Charles S DeCarliiD· 1 shared Ciprian M. CrainiceanuiD· 1 shared

Activity by Year

2023-2026 · peak 2/yr

Co-Author Collaboration Network

10 top collaborators · 33 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

3 shared papersNeuroscience

Dana TudorascuORCID

Mutual co-authors in cluster

Author profile →

3 papers

Recent·Most cited

Superpixel-ComBat multi-site harmonization of unpaired T1W MRI data in Huntingtons disease

Annabelle Coleman, Chang-Le Chen, Joelle Hanson-Baiden, Davneet Singh Minhas, Mahbaneh Eshaghzadeh Torbati, Charles M. Laymon, Sarah J. Tabrizi, Edward J. Wild, Dana Tudorascu, Rachael I. Scahill, Lauren M. Byrne

This paper adapts Superpixel-ComBat to harmonize unpaired multi-site T1W MRI data in HD, improving image quality and enabling unified VBM analyses across scanners.

bioRxiv · May 29, 2026 · PreprintNeuroscience

MISPEL: A supervised deep learning harmonizationmethod for multi-scanner neuroimaging data

Mahbaneh Eshaghzadeh Torbati, Davneet Singh Minhas, Charles M. Laymon, Pauline Maillard, James David Wilson, Chang‐Le Chen, Ciprian M. Crainiceanu, Charles S DeCarli, Seong Jae Hwang, Dana Tudorascu

MISPEL is a supervised deep learning method for harmonizing multi-scanner neuroimaging data, outperforming existing methods in reducing scanner-related variability.

Medical Image Analysis · Aug 9, 2023Peer-reviewedNeuroscience

ComBat Harmonization: Empirical Bayes versus Fully Bayes Approaches

Maxwell J. Reynolds, Tigmanshu Chaudhary, Mahbaneh Eshaghzadeh Torbati, Dana Tudorascu, Kayhan N. Batmanghelich, the Alzheimer’s Disease Neuroimaging Initiative

This paper compares empirical Bayes and fully Bayesian approaches for harmonizing neuroimaging data, finding empirical Bayes more efficient but underestimating uncertainty, while fully Bayesian better preserves biological information.

NeuroImage Clinical · Jan 1, 2023Peer-reviewedNeuroscience