alzhub.org
Get help now — free helplines

You can call any of these for free. You do not need a diagnosis, an appointment, or a crisis to call — questions and plain exhaustion are reasons enough.

  • Alzheimer's Association 24/7 Helpline 800-272-3900 24 hours a day, 365 days a year Free, confidential support and information for people with dementia, caregivers, families and the public. Master's-level clinicians. Also Spanish.
  • 988 Suicide & Crisis Lifeline 988 24/7 Call or text 988, or chat at 988lifeline.org. For anyone in emotional distress or a mental-health crisis, including caregivers.
  • Alzheimer's Foundation of America (AFA) Helpline 866-232-8484 9:00 am - 9:00 pm ET, seven days a week Licensed social workers providing support, info and referrals. Also text message and web chat. Text: 646-586-5283

In a medical emergency, call 911. More numbers, and what each line does, on the help page.

Research

27,380 Alzheimer's and dementia studies in plain English, each scored out of 100.

Find studies

Showing 1–25 of 42 studies in Brain scans and imaging (page 1 of 2) · 27,380 in the whole library · How the 0–100 score works

Showing 42 studies tagged convolutional — clear

Browse by subject, author or institution

Each number is how many studies that link shows, with your other filters kept.

Other subjects

Authors

Names as each record prints them; the same person can appear under two spellings.

What “Brain scans and imaging” covers

Brain scans and imaging — MRI, PET and other scans: what they show, how early, and how reliably.

A note on reading research. One study is rarely the final word.

We try to note the size of a study, whether it was in humans or animals, and how early-stage the finding is. If a summary here doesn't make that clear, treat it with extra caution and check the original source.

Assessment of the predictive potential of cognitive scores from retinal images and retinal fundus metadata via deep learning using the CLSA database

✓ Peer-reviewed alzhub usefulness score 61 out of 100. Scientific reports 2022-04-06

Accumulation of beta-amyloid in the brain and cognitive decline are considered hallmarks of Alzheimer's disease. 2 key findings →

Design: longitudinal study Evidence: moderate

Full summary, score breakdown and related studies → Original source

Visual interpretation of [18F]Florbetaben PET supported by deep learning-based estimation of amyloid burden

✓ Peer-reviewed alzhub usefulness score 57 out of 100. European journal of nuclear medicine and molecular imaging 2020-09-29

Inter-reader agreements for the visual reading based on a 3-point scale (BAPL score) calculated by Fleiss kappa coefficients were 0.46 and 0.76 for the visual reading without and with the deep learning system, respectively. 3 key findings →

Participants: 121 Evidence: high

Full summary, score breakdown and related studies → Original source

Deep learning detection of informative features in tau PET for Alzheimer’s disease classification

✓ Peer-reviewed alzhub usefulness score 57 out of 100. BMC Bioinformatics 2020-12-01

A deep learning framework combining 3D CNN and LRP algorithms can be used with tau PET images to identify informative features for AD classification and may have application for early detection during prodromal stages of AD. 4 key findings →

Participants: 132 Evidence: moderate

Full summary, score breakdown and related studies → Original source

Deep residual inception encoder-decoder network for amyloid PET harmonization

✓ Peer-reviewed alzhub usefulness score 55 out of 100. Alzheimer's & dementia : the journal of the Alzheimer's Association 2022-02-09

Significantly stronger between-tracer correlations (P < .001) were observed after harmonization for both global amyloid burden indices and voxel-wise measurements in the training cohort and the external testing cohort. 3 key findings →

Participants: 92 Evidence: moderate

Full summary, score breakdown and related studies → Original source

Convolutional neural network to identify symptomatic Alzheimer's disease using multimodal retinal imaging

✓ Peer-reviewed alzhub usefulness score 55 out of 100. The British journal of ophthalmology 2020-11-26

284 eyes of 159 subjects (222 eyes from 123 cognitively healthy subjects and 62 eyes from 36 subjects with AD) were used to develop the model. 5 key findings →

Participants: 159 Evidence: low

Full summary, score breakdown and related studies → Original source

Deep-learning retinal vessel calibre measurements and risk of cognitive decline and dementia

✓ Peer-reviewed alzhub usefulness score 54 out of 100. Brain communications 2022-08-17

Previous studies have explored the associations of retinal vessel calibre, measured from retinal photographs or fundus images using semi-automated computer programs, with cognitive impairment and dementia, supporting the concept that retinal blood vessels reflect microvascular changes in the brain. 3 key findings →

Participants: 212 Evidence: low

Full summary, score breakdown and related studies → Original source

Color Fundus Photography and Deep Learning Applications in Alzheimer Disease

✓ Peer-reviewed alzhub usefulness score 46 out of 100. Mayo Clinic proceedings. Digital health 2024-08-26

The self-supervised ADRET model had superior accuracy when compared with ADVAS, in both UK Biobank (98.27% vs 77.20%; P<.001) and our institutional testing data sets (98.90% vs 94.17%; P=.04). 5 key findings →

Evidence: low

Full summary, score breakdown and related studies → Original source

Automatic classification of patients with Alzheimer's disease from structural MRI: a comparison of ten methods using the ADNI database

✓ Peer-reviewed alzhub usefulness score 45 out of 100. NeuroImage 2010-06-11

Recently, several high dimensional classification methods have been proposed to automatically discriminate between patients with Alzheimer's disease (AD) or mild cognitive impairment (MCI) and elderly controls (CN) based on T1-weighted MRI. 4 key findings →

Participants: 509 Evidence: low

Full summary, score breakdown and related studies → Original source

Classification and Visualization of Alzheimer’s Disease using Volumetric Convolutional Neural Network and Transfer Learning

✓ Peer-reviewed alzhub usefulness score 45 out of 100. Scientific Reports 2019-12-03

Recently, deep-learning-based approaches have been proposed for the classification of neuroimaging data related to Alzheimer's disease (AD), and significant progress has been made. 3 key findings →

Evidence: low

Full summary, score breakdown and related studies → Original source

Deep Learning Analysis of Retinal Structures and Risk Factors of Alzheimer's Disease

✓ Peer-reviewed alzhub usefulness score 43 out of 100. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference 2024-07

The importance of early Alzheimer's Disease screening is becoming more apparent, given the fact that there is no way to revert the patient's status after the onset. 1 key finding →

Evidence: low

Full summary, score breakdown and related studies → Original source

Automatic lesion detection and segmentation in 18F-flutemetamol positron emission tomography images using deep learning

✓ Peer-reviewed alzhub usefulness score 41 out of 100. Biomedical engineering online 2022-12-20

The following intersection over union values were obtained for the various slices in the verification dataset: frontal lobe axial/sagittal: 0.733/0.804; posterior cingulate cortex and precuneus coronal/sagittal: 0.661/0.726; lateral temporal lobe axial/coronal: 0.864/0.892; parietal lobe axial/coronal: 0.542/0.759; and striatum axial/sagittal: 0.679/0.752. 4 key findings →

Evidence: low

Full summary, score breakdown and related studies → Original source

Automatic Segmentation of Retinal Layers in Multiple Neurodegenerative Disorder Scenarios

✓ Peer-reviewed alzhub usefulness score 41 out of 100. IEEE journal of biomedical and health informatics 2023-11-07

Retinal Optical Coherence Tomography (OCT) allows the non-invasive direct observation of the central nervous system, enabling the measurement and extraction of biomarkers from neural tissue that can be helpful in the assessment of ocular, systemic and Neurological Disorders (ND). 2 key findings →

Evidence: low

Full summary, score breakdown and related studies → Original source

Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis

✓ Peer-reviewed alzhub usefulness score 40 out of 100. NeuroImage 2014-07-18

For the last decade, it has been shown that neuroimaging can be a potential tool for the diagnosis of Alzheimer's Disease (AD) and its prodromal stage, Mild Cognitive Impairment (MCI), and also fusion of different modalities can further provide the complementary information to enhance diagnostic accuracy. 3 key findings →

Evidence: low

Full summary, score breakdown and related studies → Original source

Adaptive template generation for amyloid PET using a deep learning approach

✓ Peer-reviewed alzhub usefulness score 39 out of 100. Human brain mapping 2018-05-11

Accurate spatial normalization (SN) of amyloid positron emission tomography (PET) images for Alzheimer's disease assessment without coregistered anatomical magnetic resonance imaging (MRI) of the same individual is technically challenging. 1 key finding →

Evidence: low

Full summary, score breakdown and related studies → Original source

↑ Change the filters

Where “Free full text” comes from

Free full text links and the Full text may need a subscription label come from Unpaywall, Europe PMC and OpenAlex records of free copies, checked 10 Oct 2026. A study with neither is unknown, not paywalled. Show only studies that are free to read

How the 0–100 score works — and why some entries are capped

This is alzhub's own score. It is not an official metric, not an impact factor, and no journal, publisher or ranking body endorses it. We built it so that a reader who is not a scientist can tell a landmark trial from a conference abstract without having to already know the difference. Every point comes from one of 20 components, all of them printed on the study itself, so you can disagree with our arithmetic rather than having to trust the total.

  • Journal tier up to 10 pts
  • Journal's citation record up to 4 pts
  • Study design up to 12 pts
  • Strength of evidence up to 5 pts
  • Peer-review validation up to 10 pts
  • How recent up to 5 pts
  • Sample size up to 4 pts
  • Effect reported up to 3 pts
  • Studied in people up to 3 pts
  • Randomised / blinded up to 2 pts
  • Times cited up to 7 pts
  • Citations per year up to 5 pts
  • Impact for its field and year up to 6 pts
  • Cited by studies here up to 6 pts
  • Still being cited up to 4 pts
  • Senior author's track record up to 4 pts
  • Institution's track record up to 3 pts
  • Multi-centre collaboration up to 3 pts
  • Indexed in PubMed up to 2 pts
  • Free to read up to 2 pts

Journals are placed in ordered tiers, never given a numeric impact factor — we could not verify current impact factors from a source we control, and an invented one would be worse than none. Tier 1 is the top-tier general journals (NEJM, The Lancet, JAMA, Nature, Science, Nature Medicine); tier 2 is the leading specialty journals; tier 3 is every other peer-reviewed journal. A separate part scores how much the journal's own papers are cited, which tells the tier-3 journals apart.

Two rules we don't bend. First, we never fill in a missing value: if a record does not state a sample size or a design, that component scores zero, and if we simply have no data for a part, such as a citation count, that part is left out and the study is scored on the parts we could check. The study card says which. Second, anything that is not a peer-reviewed article is capped at 16/100 and carries a warning chip — so a conference abstract or a company press release can never outrank a peer-reviewed paper, no matter how good it looks.

We rank a rigorous null result — a good trial showing that something does not work — above an early positive finding. Someone deciding whether to buy a supplement is served by that, and the rigour is already counted by the design and journal components.

The score is computed from the published data alone and is reproducible: the same file always yields the same numbers.

See the whole rubric drawn out → — four charts covering all 27,380 studies: how the scores are spread and where the cap bites, which of the 20 components the library is strong and weak on, which subjects rest on stronger evidence, and what kinds of study each subject is actually built from.

What this library is — and isn't

This is a large sample of the Alzheimer's literature, not an exhaustive index of it. It holds 27,380 records, built mostly from automated pulls of Europe PMC (60.6% of the library) and OpenAlex (18.6%), plus smaller pulls from PubMed, Crossref and medRxiv. If a study, a drug, or a finding isn't here, that is not evidence it doesn't exist in the literature — it may simply not have been pulled in yet.

1,032 records (3.8% of the library) are not peer-reviewed — 962 of those are preprints posted before any journal review, and the rest are conference abstracts, regulatory notices and reports. Every study card on this page states its status plainly, and the score above is capped for anything that isn't a peer-reviewed article.

See the full, machine-readable breakdown of this library's coverage →

Newest studies, as a dated timeline →    Atom feed