Evidence map›Paper›PMID 37084926›Full record

ReviewNeuroImage2023

Image harmonization: A review of statistical and deep learning methods for removing batch effects and evaluation metrics for effective harmonization.

Fengling Hu, Andrew A Chen, Hannah Horng, Vishnu Bashyam, Christos Davatzikos, Aaron Alexander-Bloch, Mingyao Li, Haochang Shou, Theodore D Satterthwaite, Meichen Yu and 1 more

Abstract readReview
In one paragraph

Review in NeuroImage, 2023. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 92 papers, 1 of them a synthesis that pooled it.

0numbers the graph read from it
0cells of the map it votes in
92citing papers in PubMed, 1 pooled it
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

92 citing papers in PubMed, 1 synthesis or guideline pooled it.

  1. Pooled it
  2. Article
  3. Article
  4. Article
  5. Review
  6. Article
  7. Advances in artificial intelligence for neuroimaging.Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism · 2026
    Review
  8. Article
  9. Review
  10. Article
  11. Review
  12. Article
  13. Review
  14. Review
  15. Article
  16. Article
  17. Article
  18. Article
  19. Article
  20. Two axes of white matter development.Nature communications · 2026
    Article

32 more citing papers are in PubMed but not listed here.

4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

11 authors.

Fengling HuPenn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, 423 Guardian Dr, Philadelphia, PA 19104, United States. Electronic address: fengling.hu@pennmedicine.upenn.edu.
Andrew A ChenPenn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, 423 Guardian Dr, Philadelphia, PA 19104, United States.
Hannah HorngPenn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, 423 Guardian Dr, Philadelphia, PA 19104, United States.
Vishnu BashyamCenter for Biomedical Image Computing and Analytics (CBICA), Perelman School of Medicine, United States.
Christos DavatzikosCenter for Biomedical Image Computing and Analytics (CBICA), Perelman School of Medicine, United States.
Aaron Alexander-BlochDepartment of Psychiatry, Perelman School of Medicine, University of Pennsylvania, United States; Penn-CHOP Lifespan Brain Institute, United States; Department of Child and Adolescent Psychiatry and Behavioral Science, Children's Hospital of Philadelphia, United States.
Mingyao LiStatistical Center for Single-Cell and Spatial Genomics, Perelman School of Medicine, University of Pennsylvania, United States.
Haochang ShouPenn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, 423 Guardian Dr, Philadelphia, PA 19104, United States; Center for Biomedical Image Computing and Analytics (CBICA), Perelman School of Medicine, United States.
Theodore D SatterthwaiteDepartment of Psychiatry, Perelman School of Medicine, University of Pennsylvania, United States; Penn-CHOP Lifespan Brain Institute, United States; The Penn Lifespan Informatics and Neuroimaging Center, Department of Psychiatry, Perelman School of Medicine, University of Pennsylvania, United States.
Meichen YuIndiana Alzheimer's Disease Research Center, Indiana University School of Medicine, United States.
Russell T ShinoharaPenn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, 423 Guardian Dr, Philadelphia, PA 19104, United States; Center for Biomedical Image Computing and Analytics (CBICA), Perelman School of Medicine, United States.

Funding

MEDICAL SCIENTIST TRAINING PROGRAMT32GM007170 · NIGMS · UNIVERSITY OF PENNSYLVANIA · PI BRASS, LAWRENCE F · 1985 to 2022
$54.0M
Peripheral and Central Biomarkers of Alzheimer's Disease in Diverse CohortsU19AG074879 · NIA · MAYO CLINIC JACKSONVILLE · PI Minerva Maria Carrasquillo · 2023 to 2026
$42.0M
Research Education ComponentP30AG072976 · NIA · INDIANA UNIVERSITY INDIANAPOLIS · PI ANDREW J SAYKIN · 2021 to 2026
$24.1M
Ultrascale Machine Learning to Empower Discovery in Alzheimers Disease BiobanksU01AG068057 · NIA · UNIVERSITY OF SOUTHERN CALIFORNIA · PI Christos Davatzikos, Heng Huang · 2020 to 2026
$20.7M
KBASE2: Korean Brain Aging Study, Longitudinal Endophenotypes and Systems BiologyU01AG072177 · NIA · INDIANA UNIVERSITY INDIANAPOLIS · PI LEE, DONG YOUNG, NHO, KWANGSIK TIMOTHY · 2021 to 2025
$11.2M
Memory Circuitry in MCI and Early Alzheimer’s Disease Prodrome: Molecular DriversR01AG019771 · NIA · INDIANA UNIV-PURDUE UNIV AT INDIANAPOLIS · PI SAYKIN, ANDREW J · 2001 to 2021
$6.9M
Longitudinal Mapping of Network Development Underlying Executive Dysfunction in AdolescenceR01MH113550 · NIMH · UNIVERSITY OF PENNSYLVANIA · PI Danielle Smith Bassett, Theodore Satterthwaite · 2018 to 2026
$6.9M
Machine Learning and Large-scale Imaging analytics for dimensional representations of brain trajectories in aging and preclinical Alzheimer's Disease: The brain aging chart and the iSTAGING consortiumRF1AG054409 · NIA · UNIVERSITY OF PENNSYLVANIA · PI DAVATZIKOS, CHRISTOS · 2017 to 2023
$6.3M
Personalized Functional Network Modeling to Characterize and Predict Psychopathology in YouthR01EB022573 · NIBIB · UNIVERSITY OF PENNSYLVANIA · PI Yong Fan, Theodore Satterthwaite · 2016 to 2026
$6.0M
Inter-modal Coupling Image AnalyticsR01MH112847 · NIMH · UNIVERSITY OF PENNSYLVANIA · PI Theodore Satterthwaite, Russell Takeshi Shinohara · 2017 to 2026
$5.9M
Precision mapping of individualized executive networks in youthR37MH125829 · NIMH · UNIVERSITY OF MINNESOTA · PI Damien A Fair, Theodore Satterthwaite · 2021 to 2026
$4.7M
Harmonization of Multi-Site Neuroimaging Data from Complex Study DesignsR01MH123550 · NIMH · UNIVERSITY OF PENNSYLVANIA · PI SHINOHARA, RUSSELL TAKESHI · 2020 to 2025
$4.0M
NIA NIH HHS P30 AG072976NIA NIH HHS R01 AG019771NIA NIH HHS RF1 AG054409NIA NIH HHS U01 AG068057NIA NIH HHS U01 AG072177NIA NIH HHS U19 AG074879NIBIB NIH HHS R01 EB022573NIGMS NIH HHS T32 GM007170NIMH NIH HHS R01 MH112847NIMH NIH HHS R01 MH113550NIMH NIH HHS R01 MH120482NIMH NIH HHS R01 MH123550NIMH NIH HHS R37 MH125829NINDS NIH HHS R01 NS085211NINDS NIH HHS U24 NS130411
6 · The paper itself

Abstract

Magnetic resonance imaging and computed tomography from multiple batches (e.g. sites, scanners, datasets, etc.) are increasingly used alongside complex downstream analyses to obtain new insights into the human brain. However, significant confounding due to batch-related technical variation, called batch effects, is present in this data; direct application of downstream analyses to the data may lead to biased results. Image harmonization methods seek to remove these batch effects and enable increased generalizability and reproducibility of downstream results. In this review, we describe and categorize current approaches in statistical and deep learning harmonization methods. We also describe current evaluation metrics used to assess harmonization methods and provide a standardized framework to evaluate newly-proposed methods for effective harmonization and preservation of biological information. Finally, we provide recommendations to end-users to advocate for more effective use of current methods and to methodologists to direct future efforts and accelerate development of the field.

Indexed as

Deep LearningBrainHumansMagnetic Resonance ImagingReproducibility of Results

Identifiers

PMID37084926
PMCPMC10257347

What OpenQuestion holds

Textmetadata
LicenceCC BY
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.