Evidence map›Paper›PMID 41670187›Full record

ArticleAlzheimer's & dementia : the journal of the Alzheimer's Association2026

AI-enhanced Centiloid quantification of amyloid PET images.

Pierrick Bourgeat, Jurgen Fripp, Leo Lebrat, Ying Xia, Azadeh Feizpour, Timothy Cox, Georgios Zisis, Ashley Gillman, Manu S Goyal, Duygu Tosun and 35 more

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in Alzheimer's & dementia : the journal of the Alzheimer's Association, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 2 papers.

0numbers the graph read from it
0cells of the map it votes in
2citing papers in PubMed
–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

2 citing papers in PubMed.

  1. AI-enhanced Centiloid quantification of amyloid PET images.Alzheimer's & dementia : the journal of the Alzheimer's Association · 2026
    Article
  2. Article
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

45 authors.

Pierrick BourgeatAustralian eHealth Research Centre, CSIRO Health and Biosecurity, Brisbane, QLD, Australia.ORCID https://orcid.org/0000-0002-2605-4766
Jurgen FrippAustralian eHealth Research Centre, CSIRO Health and Biosecurity, Brisbane, QLD, Australia.
Leo LebratSchool of Electrical Engineering & Robotics, Faculty of Engineering, Queensland University of Technology, Brisbane, QLD, Australia.
Ying XiaAustralian eHealth Research Centre, CSIRO Health and Biosecurity, Brisbane, QLD, Australia.
Azadeh FeizpourDepartment of Molecular Imaging & Therapy, Austin Health, Melbourne, VIC, Australia.
Timothy CoxAustralian eHealth Research Centre, CSIRO Health and Biosecurity, Brisbane, QLD, Australia.
Georgios ZisisThe Florey Institute of Neuroscience and Mental Health, University of Melbourne, Parkville, Melbourne, VIC, Australia.
Ashley GillmanAustralian eHealth Research Centre, CSIRO Health and Biosecurity, Brisbane, QLD, Australia.
Manu S GoyalMallinckrodt Institute of Radiology, Washington University School of Medicine, St Louis, Missouri, USA.
Duygu TosunDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, California, USA.
Tammie Ls BenzingerMallinckrodt Institute of Radiology, Washington University School of Medicine, St Louis, Missouri, USA.
Pamela LaMontagneMallinckrodt Institute of Radiology, Washington University School of Medicine, St Louis, Missouri, USA.
Michael BreakspearSchool of Psychological Sciences, University of Newcastle, Newcastle, NSW, Australia.
Michelle K LuptonBrain and Mental Health, QIMR Berghofer Medical Research Institute, Brisbane, QLD, Australia.
Cathy ShortCentral Adelaide Local Health Network Memory Service and Memory Clinical Trials, Adelaide, SA, Australia.
Robert AdamCentre for Health Services Research, The University of Queensland, Brisbane, QLD, Australia.
Joanne S RobertsonThe Florey Institute of Neuroscience and Mental Health, University of Melbourne, Parkville, Melbourne, VIC, Australia.
Reisa SperlingHarvard Medical School, Brigham and Women's Hospital, Massachusetts General Hospital, Boston, Massachusetts, USA.
Sid E O'BryantInstitute for Translational Research, University of North Texas Health Science Center, Fort Worth, Texas, USA.
Sterling C JohnsonAlzheimer's Disease Research Center, University of Wisconsin-Madison, Madison, Wisconsin, USA.
Clifford R Jack JrDepartment of Radiology, Mayo Clinic, Rochester, Minnesota, USA.
Christopher G SchwarzDepartment of Radiology, Mayo Clinic, Rochester, Minnesota, USA.
Frederik BarkhofBrain Imaging, Amsterdam Neuroscience, Amsterdam, the Netherlands.
Gill FarrarGE HealthCare, Chalfont St Giles, UK.
Ariane BollackGE HealthCare, Chalfont St Giles, UK.
Lyduine E CollijBrain Imaging, Amsterdam Neuroscience, Amsterdam, the Netherlands.
Susan LandauDepartment of Neuroscience, University of California, Berkeley, California, USA.
Robert KoeppeDivision of Nuclear Medicine, Department of Radiology, University of Michigan, Ann Arbor, Michigan, USA.
Alzheimer's Disease Neuroimaging Initiative
OASIS3
A4/LEARN Study Team
AMYPAD consortium
Health and Aging Brain Study (HABS‐HD) Study Team
Mayo Clinic Study of Aging
WRAP
ADNI‐DOD
PISA
ADNeT
AIBL research group
John C MorrisDepartment of Neurology, Washington University School of Medicine, St. Louis, Missouri, USA.
Michael W WeinerDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, California, USA.
Victor L VillemagneDepartment of Psychiatry, The University of Pittsburgh, Pittsburgh, Pennsylvania, USA.
Colin L MastersThe Florey Institute of Neuroscience and Mental Health, University of Melbourne, Parkville, Melbourne, VIC, Australia.
Christopher C RoweDepartment of Molecular Imaging & Therapy, Austin Health, Melbourne, VIC, Australia.
Vincent DoreAustralian eHealth Research Centre, CSIRO Health and Biosecurity, Brisbane, QLD, Australia.

Funding

The Health & Aging Brain Study - Health Disparities (HABS-HD)U19AG078109 · NIA · UNIVERSITY OF NORTH TEXAS HLTH SCI CTR · PI LEIGH A JOHNSON · 2022 to 2026
$181.1M
Alzheimer's Disease Neuroimaging Initiative - SupplementU01AG024904 · NIA · NORTHERN CALIFORNIA INSTITUTE RES &EDUC · PI WEINER, MICHAEL W · 2004 to 2015
$121.0M
Smartphone-Based "Burst" Cognitive AssessmentsP01AG003991 · NIA · WASHINGTON UNIVERSITY · PI JOHN MORRIS · 1985 to 2026
$69.5M
SUPPLEMENT TO ALZHEIMERS DISEASE PATIENT REGISTRYU01AG006786 · NIA · MAYO CLINIC ROCHESTER · PI GRAFF-RADFORD, JONATHAN, JACK, CLIFFORD R. · 1986 to 2023
$49.6M
The natural history of AB accumulation in preclinical ADP01AG026276 · NIA · WASHINGTON UNIVERSITY · PI MORRIS, JOHN · 2005 to 2025
$49.5M
Health and Aging Brain among Latino Elders (HABLE-AT(N)) StudyR01AG058533 · NIA · UNIVERSITY OF NORTH TEXAS HLTH SCI CTR · PI JOHNSON, LEIGH A, O'BRYANT, SID E · 2020 to 2025
$45.4M
Washington University Institute of Clinical and Translational SciencesUL1TR000448 · NCATS · WASHINGTON UNIVERSITY · PI EVANOFF, BRADLEY A · 2012 to 2016
$41.4M
Wisconsin Registry for Alzheimer's Prevention: Sex Differences in DNA MethylationR01AG027161 · NIA · UNIVERSITY OF WISCONSIN-MADISON · PI Nathaniel Ark Chin, Sterling C Johnson · 2007 to 2026
$35.6M
Research Education ComponentP30AG062677 · NIA · MAYO CLINIC ROCHESTER · PI KEJAL KANTARCI · 2019 to 2026
$33.5M
Research Education ComponentP30AG066444 · NIA · WASHINGTON UNIVERSITY · PI Susan Lynn Stark · 2020 to 2026
$28.7M
UC Davis Alzheimer's Disease Core CenterP30AG010129 · NIA · UNIVERSITY OF CALIFORNIA DAVIS · PI JOHNSON, DAVID K · 1991 to 2020
$28.3M
The Longitudinal Course of Neural Function and Amyloid in People At Risk for ADR01AG021155 · NIA · UNIVERSITY OF WISCONSIN-MADISON · PI Sterling C Johnson · 2004 to 2026
$27.0M
National Health and Medical Research Council GA16788NCATS NIH HHS UL1 TR000448NIA NIH HHS K01 AG030514NIA NIH HHS P01 AG003991NIA NIH HHS P01 AG026276NIA NIH HHS P30 AG010129NIA NIH HHS P30 AG062677NIA NIH HHS P30 AG066444NIA NIH HHS R01 AG021155NIA NIH HHS R01 AG027161NIA NIH HHS R01 AG034676NIA NIH HHS R01 AG041851NIA NIH HHS R01 AG043434NIA NIH HHS R01 AG054073NIA NIH HHS R01 AG056366NIA NIH HHS R01 AG058533NIA NIH HHS R01 AG058676NIA NIH HHS R01 AG062167NIA NIH HHS R01 AG062285NIA NIH HHS R01 AG068206NIA NIH HHS R37 AG011378NIA NIH HHS U01 AG006786NIA NIH HHS U01 AG024904NIA NIH HHS U19 AG078109NIBIB NIH HHS P41 EB015922NIBIB NIH HHS R01 EB009352NIH HHS R01-AG058676-01A1NINDS NIH HHS R01 NS097495
6 · The paper itself

Abstract

introductionThe Centiloid scale is the standard for amyloid (Aβ) PET quantification in research and clinical settings. However, variability between tracers and scanners remains a challenge.

methodsThis study introduces DeepSUVR, a deep learning method to correct Centiloid quantification, by penalizing implausible longitudinal trajectories during training. The model was trained using data from 2,129 participants (7,149 Aβ positron emission tomography [PET] scans) in the Australian Imaging, Biomarkers and Lifestyle Study of ageing (AIBL)/Alzheimer's Disease Neuroimaging Initiative (ADNI) and validated using 15,807 Aβ PET scans from 10,543 participants across 10 external datasets.

resultsDeepSUVR increased correlation between tracers, and reduced variability in the Aß-negatives. It showed significantly stronger association with cognition, visual reads, neuropathology, and increased longitudinal consistency between studies. DeepSUVR also increased the effect size for detecting small treatment related slowing of amyloid accumulation in the A4 study. DISCUSSION: DeepSUVR substantially advances Aβ PET quantification, outperforming all standard approaches, which is particularly important for clinical decision making and to detect subtle or early changes in Aβ. HIGHLIGHTS: Novel artificial intelligence (AI)-method that penalizes biologically implausible longitudinal trajectories, enabling the model to learn standardized uptake value ratios (SUVR) correction factors without requiring longitudinal data at inference time. Improves Centiloid consistency across tracers and studies, significantly enhancing cross-sectional and longitudinal amyloid positron emission tomography (PET) quantification. DeepSUVR-derived Centiloids show stronger associations with cognition, visual reads, and neuropathology. Longitudinal variability is reduced three- to five-fold, enabling more reliable tracking of amyloid accumulation and better detection of treatment effects. Novel reference and target masks derived from DeepSUVR replicate most of the model's performance, offering a practical alternative for integration into existing pipelines.

Indexed as

Alzheimer DiseaseAmyloid beta-PeptidesBrainDeep LearningPositron-Emission TomographyAgedAged, 80 and overFemaleHumansMaleNeuroimagingAmyloid beta-PeptidesAlzheimer's diseaseamyloid positron emission tomographyCentiloiddeep Learninglongitudinal analysis

Identifiers

PMID41670187
PMCPMC12892302

What Socratic 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 Socratic graph.