Visual deep learning of unprocessed neuroimaging characterises dementia subtypes and generalises across non-stereotypic samples
Open accessAbstract
BACKGROUND: Dementia's diagnostic protocols are mostly based on standardised neuroimaging data collected in the Global North from homogeneous samples. In other non-stereotypical samples (participants with diverse admixture, genetics, demographics, MRI signals, or cultural origins), classifications of disease are difficult due to demographic and region-specific sample heterogeneities, lower quality scanners, and non-harmonised pipelines. METHODS: We implemented a fully automatic computer-vision classifier using deep learning neural networks. A DenseNet was applied on raw (unpreprocessed) data from 3000 participants (behavioural variant frontotemporal dementia-bvFTD, Alzheimer's disease-AD, and healthy controls; both male and female as self-reported by participants). We tested our results in demographically matched and unmatched samples to discard possible biases and performed multiple out-of-sample validations. FINDINGS: Robust classification results across all groups were achieved from standardised 3T neuroimaging data from the Global North, which also generalised to standardised 3T neuroimaging data from Latin America. Moreover, DenseNet also generalised to non-standardised, routine 1.5T clinical images from Latin America. These generalisations were robust in samples with heterogenous MRI recordings and were not confounded by demographics (i.e., were robust in both matched and unmatched samples, and when incorporating demographic variables in a multifeatured model). Model interpretability analysis using occlusion sensitivity evidenced core pathophysiological regions for each disease (mainly the hippocampus in AD, and the insula in bvFTD) demonstrating biological specificity and plausibility. INTERPRETATION: The generalisable approach outlined here could be used in the future to aid clinician decision-making in diverse samples. FUNDING: The specific funding of this article is provided in the acknowledgements section.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
A few studies have attempted to discern neuroimaging signatures unique to AD by contrasting them with other dementia types.
“A few studies have attempted to discern neuroimaging signatures unique to AD by contrasting them with other dementia types31–40.”
From AI-based differential diagnosis of dementia etiologies on multimodal data (2024) · cites this paper as [40]
Cites
Alzheimer's Disease Neuroimaging Initiative (ADNI)
Petersen, R. C., Aisen, P. S., Beckett, L. A., Donohue, M. C., Gamst, A. C., Harvey, D. J., Jack, C. R., Jagust, W. J., Shaw, L. M., Toga, A. W., et al. (2010) · Neurology · doi:10.1212/wnl.0b013e3181cb3e25 · Cited by 2,572 · see citing works
Frontotemporal dementia and its subtypes: a genome-wide association study
Ferrari, R., Hernandez, D. G., Nalls, M. A., Rohrer, J. D., Ramasamy, A., Kwok, J. B. J., Dobson-Stone, C., Brooks, W. S., Schofield, P. R., Halliday, G. M., et al. (2014) · The Lancet Neurology · doi:10.1016/s1474-4422(14)70065-1 · Cited by 383 · see citing works
The human connectome in Alzheimer disease — relationship to biomarkers and genetics
Yu, M., Sporns, O., & Saykin, A. J. (2021) · Nature Reviews Neurology · doi:10.1038/s41582-021-00529-1 · Cited by 265 · see citing works
Alzheimer rsquo s disease diagnostics by a 3D deeply supervised adaptable convolutional network
Ghazal, M. (2018) · Frontiers in Bioscience · doi:10.2741/4606 · Cited by 204 · see citing works
Amini, M., Pedram, M. M., Moradi, A., & Ouchani, M. (2021) · Computational and Mathematical Methods in Medicine · doi:10.1155/2021/5514839 · Cited by 84 · see citing works
Hu, J., Qing, Z., Liu, R., Zhang, X., Lv, P., Wang, M., Wang, Y., He, K., Gao, Y., & Zhang, B. (2021) · Frontiers in Neuroscience · doi:10.3389/fnins.2020.626154 · Cited by 70 · see citing works
Sedeño, L., Piguet, O., Abrevaya, S., Desmaras, H., García‐Cordero, I., Baez, S., Alethia de la Fuente, L., Reyes, P., Tu, S., Moguilner, S., et al. (2017) · Human Brain Mapping · doi:10.1002/hbm.23627 · Cited by 55 · see citing works
Self-citationDi Benedetto, M., Carrara, F., Tafuri, B., Nigro, S., De Blasi, R., Falchi, F., Gennaro, C., Gigli, G., Logroscino, G., & Amato, G. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105937 · Cited by 14 · see citing works
Gonzalez-Gomez, R., Ibañez, A., & Moguilner, S. (2023) · Network Neuroscience · doi:10.1162/netn_a_00285 · Cited by 10 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
AI-based differential diagnosis of dementia etiologies on multimodal data
Xue, C., Kowshik, S. S., Lteif, D., Puducheri, S., Jasodanand, V. H., Zhou, O. T., Walia, A. S., Guney, O. B., Zhang, J. D., Poésy, S., et al. (2024) · Nature Medicine · doi:10.1038/s41591-024-03118-z · Cited by 182 · see citing works
A synergetic turn in cognitive neuroscience of brain diseases
Ibanez, A., Kringelbach, M. L., & Deco, G. (2024) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2023.12.006 · Cited by 65 · see citing works
Educational disparities in brain health and dementia across Latin America and the United States
Gonzalez‐Gomez, R., Legaz, A., Moguilner, S., Cruzat, J., Hernández, H., Baez, S., Cocchi, R., Coronel‐Olivero, C., Medel, V., Tagliazuchi, E., et al. (2024) · Alzheimer's & Dementia · doi:10.1002/alz.14085 · Cited by 55 · see citing works
Self-citationLegaz, A., Altschuler, F., Gonzalez-Gomez, R., Hernández, H., Baez, S., Migeot, J., Fittipaldi, S., Medel, V., Maito, M. A., Godoy, M. E., et al. (2024) · Nature Aging · doi:10.1038/s43587-024-00781-2 · Cited by 36 · see citing works
Self-citationBiomarkers of neurodegeneration across the Global South
McGlinchey, E., Duran-Aniotz, C., Akinyemi, R., Arshad, F., Zimmer, E. R., Cho, H., Adewale, B. A., & Ibanez, A. (2024) · The Lancet Healthy Longevity · doi:10.1016/s2666-7568(24)00132-6 · Cited by 32 · see citing works
Hazelton, J. L., Della Bella, G., Barttfeld, P., Dottori, M., Gonzalez-Gomez, R., Migeot, J., Moguilner, S., Legaz, A., Hernandez, H., Prado, P., et al. (2025) · eBioMedicine · doi:10.1016/j.ebiom.2025.105614 · Cited by 14 · see citing works
Self-citationDeep learning applications in vascular dementia using neuroimaging
Dong, C., & Hayashi, S. (2024) · Current Opinion in Psychiatry · doi:10.1097/yco.0000000000000920 · Cited by 13 · see citing works
- Authors
- Moguilner, S., Whelan, R., Adams, H., Valcour, V., Tagliazucchi, E., & Ibáñez, A.
- Affiliations
- University of California, San Francisco (US)
- Adolfo Ibáñez University (CL)
- Consejo Nacional de Investigaciones Científicas y Técnicas (AR)
- Corresponding author
- Ibáñez, Agustín
- Venue
- eBioMedicine
- Publisher
- Elsevier BV
- Published
- 2023-04
- Volume
- 90
- Pages
- 104540
- ISSN
- 2352-3964 (ISSN-L)
- PMC
- PMC10066533
- OpenAlex
- W4360966363
- Cited by
- 39
- References
- 9
- Citations by year
- 2026: 6 · 2025: 11 · 2024: 17 · 2023: 4
- FWCI
- 7.74
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- EBioMedicine (publishedVersion, cc-by)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- EUR Research Repository (Erasmus University Rotterdam) (publishedVersion, cc-by)
- EUR Research Repository (Erasmus University Rotterdam) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Consejo Nacional de Investigaciones Científicas y Técnicas
- National Institutes of Health (R01AG057234, SG-20-725707-ReDLat)
- Fondo para la Investigación Científica y Tecnológica (2017-1818, 2017-1820)
- National Institute on Aging
- Fondo de Fomento al Desarrollo Científico y Tecnológico (ANID / PIA / ANILLOS ACT210096, ID20I10152, ID22I10029)
- Alzheimer's Association
- Fondo de Financiamiento de Centros de Investigación en Áreas Prioritarias
- Alzheimer's Society (GBHI ALZ UK-21-721776)
- ANID
- Fondo Nacional de Desarrollo Científico y Tecnológico (1210195)
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Health Sciences › Medicine › Physiology › Alzheimer's disease research and treatments
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- dementia subtypes, behavioral variant frontotemporal dementia, Alzheimer's disease, DenseNet, sample heterogeneity, demographic bias, occlusion sensitivity, model interpretability, hippocampus, insula, Latin America, Global North
- MeSH terms
- Deep Learning, Alzheimer Disease, Brain, Female, Hippocampus, Humans, Magnetic Resonance Imaging, Male, Frontotemporal Dementia, Neuroimaging
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
