Evidence map›Paper›PMID 36127723›Full record

ArticleActa neuropathologica communications2022

Interpretable deep learning of myelin histopathology in age-related cognitive impairment.

Andrew T McKenzie, Gabriel A Marx, Daniel Koenigsberg, Mary Sawyer, Megan A Iida, Jamie M Walker, Timothy E Richardson, Gabriele Campanella, Johannes Attems, Ann C McKee and 6 more

Open access · goldAbstract read
In one paragraph

Article in Acta neuropathologica communications, 2022. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 22 papers.

0numbers the graph read from it
0cells of the map it votes in
22citing papers in PubMed
2.7field-weighted citation impact, top 10% of its field
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

22 citing papers in PubMed, 35 citations in OpenAlex.

  1. Article
  2. Digital neuropathology of neurodegenerative disorders: Foundations, research advances, and future directions.Alzheimer's & dementia : the journal of the Alzheimer's Association · 2025
    Review
  3. Primary age-related tauopathy.Acta neuropathologica · 2025
    Review
  4. Article
  5. Celebrating neuropathology's contributions to Alzheimer's Disease Research Centers.Alzheimer's & dementia : the journal of the Alzheimer's Association · 2025
    Article
  6. Comparison of multiple quantitative strategies for neuropathologic image analyses.Journal of neuropathology and experimental neurology · 2025
    Article
  7. Article
  8. Article
  9. Article
  10. SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology.Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 2024
    Article
  11. Article
  12. Article
  13. Article
  14. Article
  15. Article
  16. Article
  17. Article
  18. Article
  19. Article
  20. 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

16 authors at 6 institutions in 2 countries.

Andrew T McKenzie *Departments of Pathology, Neuroscience, and Artificial Intelligence & Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Gabriel A Marx *Departments of Pathology, Neuroscience, and Artificial Intelligence & Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Daniel KoenigsbergDepartments of Pathology, Neuroscience, and Artificial Intelligence & Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Mary SawyerDepartments of Pathology, Neuroscience, and Artificial Intelligence & Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Megan A IidaDepartments of Pathology, Neuroscience, and Artificial Intelligence & Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Jamie M WalkerDepartment of Pathology, University of Texas Health Science Center, San Antonio, TX, USA.
Timothy E RichardsonDepartment of Pathology, University of Texas Health Science Center, San Antonio, TX, USA.
Gabriele CampanellaDepartments of Pathology, Neuroscience, and Artificial Intelligence & Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Johannes AttemsTranslation and Clinical Research Institute, Newcastle University, Newcastle upon Tyne, NE4 5PL, UK.
Ann C McKeeDepartment of Pathology, VA Medical Center &, Boston University School of Medicine, Boston, MA, USA.
Thor D SteinDepartment of Pathology, VA Medical Center &, Boston University School of Medicine, Boston, MA, USA.
Thomas J FuchsDepartments of Pathology, Neuroscience, and Artificial Intelligence & Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Charles L WhiteDepartment of Pathology, University of Texas Southwestern Medical Center, Dallas, TX, USA.
PART working group
Kurt FarrellDepartments of Pathology, Neuroscience, and Artificial Intelligence & Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA. Kurt.farrell@mssm.edu.
John F CraryDepartments of Pathology, Neuroscience, and Artificial Intelligence & Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA. john.crary@mountsinai.org.ORCID 0000-0002-0556-293X
Allen Institute for Brain Science · USIcahn School of Medicine at Mount Sinai · USNewcastle University · GBBoston University · USThe University of Texas Health Science Center at San Antonio · USThe University of Texas Southwestern Medical Center · US

Funding

Smartphone-Based "Burst" Cognitive AssessmentsP01AG003991 · NIA · WASHINGTON UNIVERSITY · PI Tammie Lee Smith Benzinger · 1985 to 2026
$69.5M
THERAPEUTIC EFFECTS OF INTRA-NASAL INSULIN DETEMIRP50AG005136 · NIA · UNIVERSITY OF WASHINGTON · PI JAYADEY, SUMAN · 1985 to 2019
$57.2M
VIRUS-INDUCED BRAIN PATHOLOGYP50AG005131 · NIA · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI BREWER, JAMES B · 1985 to 2018
$55.4M
The natural history of AB accumulation in preclinical ADP01AG026276 · NIA · WASHINGTON UNIVERSITY · PI SCHINDLER, SUZANNE ELIZABETH · 2005 to 2025
$49.5M
SUPPLEMENT TO RUSH ALZHEIMERS DISEASE CENTER COREP30AG010161 · NIA · RUSH UNIVERSITY MEDICAL CENTER · PI BENNETT, DAVID ALAN · 1991 to 2020
$49.1M
Satellite Diagnostic and Treatment Clinic CoreP50AG008702 · NIA · COLUMBIA UNIV NEW YORK MORNINGSIDE · PI DE JAGER, PHILIP L · 1989 to 2019
$46.3M
THE ROLE OF ADVANCED CAA IN ALZHEIMER'S DEMENTIAP50AG005134 · NIA · MASSACHUSETTS GENERAL HOSPITAL · PI HYMAN, BRADLEY T. · 1985 to 2018
$42.1M
Furthering scientific understanding of mechanisms underlying resilience to the effects of AD pathology by incorporating state of the art quantification of gliosis, inflammation, & synaptic toxicityU01AG006781 · NIA · UNIVERSITY OF WASHINGTON · PI CRANE, PAUL K, LARSON, ERIC B · 1986 to 2020
$39.3M
VESICULAR LOCALIZATION AND FUNCTION OF PRESENILIN 1 FRAGMENTP50AG005138 · NIA · MOUNT SINAI SCHOOL OF MEDICINE OF NYU · PI SCHIMMING, CORBETT · 1985 to 2019
$37.9M
Transgenic Mouse Models of Tau PathologiesP01AG017586 · NIA · UNIVERSITY OF PENNSYLVANIA · PI LEE, VIRGINIA M · 2000 to 2021
$37.3M
UC Irvine Alzheimer's Disease Research Center Induced Pluripotent Stem Cell CoreP50AG016573 · NIA · UNIVERSITY OF CALIFORNIA-IRVINE · PI LAFERLA, FRANK M · 2000 to 2019
$37.0M
Diversity Supplement to R01AG021055; Clinical, Imaging, and Pathological Studies in the Oldest Old: The 90+ StudyR01AG021055 · NIA · UNIVERSITY OF CALIFORNIA-IRVINE · PI CORRADA, MARIA, KAWAS, CLAUDIA H. · 2002 to 2024
$36.9M
Medical Research Council G0400074NCI NIH HHS R01 CA079830NIA NIH HHS F32 AG056098NIA NIH HHS K01 AG070326NIA NIH HHS P01 AG000538NIA NIH HHS P01 AG003991NIA NIH HHS P01 AG017586NIA NIH HHS P01 AG026276NIA NIH HHS P01 AG066597NIA NIH HHS P30 AG008017NIA NIH HHS P30 AG010124NIA NIH HHS P30 AG010161NIA NIH HHS P30 AG013854NIA NIH HHS P30 AG019610NIA NIH HHS P30 AG028383NIA NIH HHS P30 AG062429NIA NIH HHS P30 AG066444NIA NIH HHS P30 AG066468NIA NIH HHS P30 AG066509NIA NIH HHS P30 AG066514NIA NIH HHS P30 AG066546NIA NIH HHS P30 AG072979NIA NIH HHS P30 AG072980NIA NIH HHS P50 AG005131NIA NIH HHS P50 AG005134NIA NIH HHS P50 AG005136NIA NIH HHS P50 AG005138NIA NIH HHS P50 AG008702NIA NIH HHS P50 AG016573NIA NIH HHS P50 AG025688NIA NIH HHS R01 AG021055NIA NIH HHS R01 AG054008NIA NIH HHS R01 AG062348NIA NIH HHS R01 AG066152NIA NIH HHS RF1 AG060961NIA NIH HHS U01 AG006781NIA NIH HHS U19 AG062418NIDA NIH HHS 75N95019C00049NINDS NIH HHS P30 NS055077NINDS NIH HHS R01 NS086736NINDS NIH HHS R01 NS095252NINDS NIH HHS RF1 NS095252NINDS NIH HHS U24 NS072026NINDS NIH HHS U54 NS115266
6 · The paper itself

Abstract

Age-related cognitive impairment is multifactorial, with numerous underlying and frequently co-morbid pathological correlates. Amyloid beta (Aβ) plays a major role in Alzheimer's type age-related cognitive impairment, in addition to other etiopathologies such as Aβ-independent hyperphosphorylated tau, cerebrovascular disease, and myelin damage, which also warrant further investigation. Classical methods, even in the setting of the gold standard of postmortem brain assessment, involve semi-quantitative ordinal staging systems that often correlate poorly with clinical outcomes, due to imperfect cognitive measurements and preconceived notions regarding the neuropathologic features that should be chosen for study. Improved approaches are needed to identify histopathological changes correlated with cognition in an unbiased way. We used a weakly supervised multiple instance learning algorithm on whole slide images of human brain autopsy tissue sections from a group of elderly donors to predict the presence or absence of cognitive impairment (n = 367 with cognitive impairment, n = 349 without). Attention analysis allowed us to pinpoint the underlying subregional architecture and cellular features that the models used for the prediction in both brain regions studied, the medial temporal lobe and frontal cortex. Despite noisy labels of cognition, our trained models were able to predict the presence of cognitive impairment with a modest accuracy that was significantly greater than chance. Attention-based interpretation studies of the features most associated with cognitive impairment in the top performing models suggest that they identified myelin pallor in the white matter. Our results demonstrate a scalable platform with interpretable deep learning to identify unexpected aspects of pathology in cognitive impairment that can be translated to the study of other neurobiological disorders.

Indexed as

Cognitive DysfunctionDeep LearningAgedAmyloid beta-PeptidesBrainHumansMyelin SheathAmyloid beta-PeptidesBrain agingCognitive impairmentDeep learningInterpretabilityLuxol fast blueMultiple instance learningMyelin pathology

Identifiers

PMID36127723
PMCPMC9490907
OpenAlexW4296785994

What OpenQuestion holds

Textmetadata
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.