{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T10:44:55Z","timestamp":1788173095667,"version":"build-2803163510"},"posted":{"date-parts":[[2023,2,16]]},"group-title":"Neuroscience","reference-count":26,"publisher":"openRxiv","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2023,2,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Abnormal \u03b2-amyloid (A\u03b2) accumulation in the brain is an early indicator of Alzheimer\u2019s disease and practical tests could help identify patients who could respond to treatment, now that promising anti-amyloid drugs are available. Even so, A\u03b2 positivity (A\u03b2+) is assessed using PET or CSF assays, both highly invasive procedures. Here, we investigate how well A\u03b2+ can be predicted from T1 weighted brain MRI and gray matter, white matter and cerebrospinal fluid segmentations from T1-weighted brain MRI (T1w), a less invasive alternative. We used 3D convolutional neural networks to predict A\u03b2+ based on 3D brain MRI data, from 762 elderly subjects (mean age: 75.1 yrs. \u00b17.6SD; 394F\/368M; 459 healthy controls, 67 with MCI and 236 with dementia) scanned as part of the Alzheimer\u2019s Disease Neuroimaging Initiative. We also tested whether the accuracy increases when using transfer learning from the larger UK Biobank dataset. Overall, the 3D CNN predicted A\u03b2+ with 76% balanced accuracy from T1w scans. The closest performance to this was using white matter maps alone when the model was pre-trained on an age prediction in the UK Biobank. The performance of individual tissue maps was less than the T1w, but transfer learning helped increase the accuracy. Although tests on more diverse data are warranted, deep learned models from standard MRI show initial promise for A\u03b2+ estimation, before considering more invasive procedures.<\/jats:p>\n                <jats:sec>\n                  <jats:title>Clinical Relevance<\/jats:title>\n                  <jats:p>Early detection of A\u03b2 positivity from less invasive MRI images, could offer a screening test prior to more invasive testing procedures.<\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2023.02.15.528705","type":"posted-content","created":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T15:00:11Z","timestamp":1676559611000},"source":"Crossref","is-referenced-by-count":9,"title":["Predicting Brain Amyloid Positivity from T1 weighted brain MRI and MRI-derived Gray Matter, White Matter and CSF maps using Transfer Learning on 3D CNNs*"],"prefix":"10.64898","author":[{"given":"Tamoghna","family":"Chattopadhyay","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saket S.","family":"Ozarkar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ketaki","family":"Buwa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sophia I.","family":"Thomopoulos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul M.","family":"Thompson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"the Alzheimer\u2019s Disease Neuroimaging Initiative","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2023022000100876000_2023.02.15.528705v1.1","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1186\/s40537-022-00650-y","article-title":"A Practical Alzheimer Disease Classifier via Brain Imaging-Based Deep Learning on 85,721 Samples","volume":"9","year":"2022","journal-title":"J Big Data"},{"issue":"1","key":"2023022000100876000_2023.02.15.528705v1.2","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1186\/s13195-019-0526-8","article-title":"Prediction of amyloid pathology in cognitively unimpaired individuals using voxel-wise analysis of longitudinal structural brain MRI","volume":"11","year":"2019","journal-title":"Alzheimers Res Ther"},{"key":"2023022000100876000_2023.02.15.528705v1.3","doi-asserted-by":"publisher","DOI":"10.1002\/ana.23650"},{"key":"2023022000100876000_2023.02.15.528705v1.4","doi-asserted-by":"crossref","unstructured":"G. Folego , M. Weiler , R. F. Casseb , et.al., \u201cAlzheimer\u2019s Disease Detection through Whole-Brain 3D-CNN MRI,\u201d Frontiers in Bioengineering and Biotechnology, 8, 2020.","DOI":"10.3389\/fbioe.2020.534592"},{"key":"2023022000100876000_2023.02.15.528705v1.5","doi-asserted-by":"crossref","unstructured":"N. J. Dhinagar , S. I. Thomopoulos , P. Rajagopalan , D. Stripelis , J. L. Ambite , G. ver Steeg , P. M. Thompson , \u201cEvaluation of Transfer Learning Methods for Detecting Alzheimer\u2019s Disease with Brain MRI,\u201d SIPAIM, 2022.","DOI":"10.1101\/2022.08.23.505030"},{"key":"2023022000100876000_2023.02.15.528705v1.6","doi-asserted-by":"crossref","unstructured":"A. Ezzati , D. J. Harvey , C. Habeck , et al., \u201cPredicting Amyloid-\u03b2 Levels in Amnestic Mild Cognitive Impairment Using Machine Learning Techniques.\u201d J Alz. Dis. 1211\u20131219, 2020.","DOI":"10.3233\/JAD-191038"},{"key":"2023022000100876000_2023.02.15.528705v1.7","doi-asserted-by":"crossref","unstructured":"G. Gelosa , D.J. Brooks , \u201cThe prognostic value of amyloid imaging.\u201d Eur J Nucl Med Mol Imaging 1207\u201319, 2012.","DOI":"10.1007\/s00259-012-2108-x"},{"key":"2023022000100876000_2023.02.15.528705v1.8","first-page":"357","article-title":"Amyloid \u03b2 deposition, neurodegeneration, and cognitive decline in sporadic Alzheimer\u2019s disease: a prospective cohort study","volume":"4","year":"2013","journal-title":"Lancet Neurol"},{"key":"2023022000100876000_2023.02.15.528705v1.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neurobiolaging.2010.04.007"},{"key":"2023022000100876000_2023.02.15.528705v1.10","doi-asserted-by":"publisher","DOI":"10.1002\/ana.22248"},{"issue":"1","key":"2023022000100876000_2023.02.15.528705v1.11","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1159\/000341580","article-title":"Cognitive Decline and Amyloid Accumulation in Patients with Mild Cognitive Impairment","volume":"34","year":"2012","journal-title":"Dement Geriatr Cogn Disord"},{"key":"2023022000100876000_2023.02.15.528705v1.12","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e3181b23564"},{"key":"2023022000100876000_2023.02.15.528705v1.13","doi-asserted-by":"crossref","first-page":"220","DOI":"10.3389\/fnagi.2019.00220","article-title":"Deep Learning in Alzheimer\u2019s Disease: Diagnostic Classification and Prognostic Prediction using Neuroimaging Data","volume":"11","year":"2019","journal-title":"Front Aging Neurosci"},{"issue":"1","key":"2023022000100876000_2023.02.15.528705v1.14","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1186\/s13195-022-00985-x","article-title":"A Deep Learning MRI approach outperforms other biomarkers of prodromal Alzheimer\u2019s disease","volume":"14","year":"2022","journal-title":"Alzheimers Res Ther"},{"key":"2023022000100876000_2023.02.15.528705v1.15","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-014-2753-3"},{"key":"2023022000100876000_2023.02.15.528705v1.16","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.112.109009"},{"key":"2023022000100876000_2023.02.15.528705v1.17","doi-asserted-by":"crossref","first-page":"238","DOI":"10.3389\/fnagi.2020.00238","article-title":"Classification and Graphical Analysis of Alzheimer\u2019s Disease and its Prodromal Stage Using Multimodal Features From Structural, Diffusion, and Functional Neuroimaging Data and the APOE Genotype","volume":"12","year":"2020","journal-title":"Front Aging Neuroscience"},{"key":"2023022000100876000_2023.02.15.528705v1.18","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-022-00793-7"},{"key":"2023022000100876000_2023.02.15.528705v1.19","first-page":"1","article-title":"A comprehensive survey on transfer learning","volume":"11","year":"2020","journal-title":"Proc IEEE"},{"issue":"7","key":"2023022000100876000_2023.02.15.528705v1.20","doi-asserted-by":"crossref","first-page":"1590","DOI":"10.3390\/cancers13071590","article-title":"Novel Transfer Learning Approach for Medical Imaging with Limited Labeled Data","volume":"13","year":"2021","journal-title":"Cancers"},{"key":"2023022000100876000_2023.02.15.528705v1.21","doi-asserted-by":"crossref","first-page":"104115","DOI":"10.1016\/j.compbiomed.2020.104115","article-title":"A scoping review of transfer learning research on medical image analysis using ImageNet","volume":"128","year":"2021","journal-title":"Computers in Biology and Medicine"},{"key":"2023022000100876000_2023.02.15.528705v1.22","unstructured":"Alzheimer\u2019s Disease International, \u201cADI - Dementia statistics,\u201d Alzheimer\u2019s Disease International, 2020. https:\/\/www.alzint.org\/about\/dementia-facts-figures\/dementia-statistics\/"},{"key":"2023022000100876000_2023.02.15.528705v1.23","doi-asserted-by":"crossref","unstructured":"Islam, J. , Zhang, Y. GAN-based synthetic brain PET image generation. Brain Inf. 7, 3 (2020).","DOI":"10.1186\/s40708-020-00104-2"},{"key":"2023022000100876000_2023.02.15.528705v1.24","unstructured":"\u201cFreeSurfer,\u201d Harvard.edu, 2013. https:\/\/surfer.nmr.mgh.harvard.edu\/"},{"key":"2023022000100876000_2023.02.15.528705v1.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2012.01.021"},{"issue":"1","key":"2023022000100876000_2023.02.15.528705v1.26","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1056\/NEJMoa2212948","article-title":"Lecanemab in Early Alzheimer\u2019s Disease","volume":"388","year":"2023","journal-title":"The New England journal of medicine"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2023.02.15.528705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T04:16:58Z","timestamp":1768450618000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2023.02.15.528705"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,16]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1101\/2023.02.15.528705","relation":{},"subject":[],"published":{"date-parts":[[2023,2,16]]},"subtype":"preprint"}}