{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T19:49:02Z","timestamp":1768506542088,"version":"3.49.0"},"posted":{"date-parts":[[2023,6,23]]},"group-title":"Neuroscience","reference-count":49,"publisher":"openRxiv","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2023,10,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  Detection and measurement of amyloid-beta (A\u03b2) aggregation in the brain is a key factor for early identification and diagnosis of Alzheimer\u2019s disease (AD). We aimed to develop a deep learning model to predict A\u03b2 cerebrospinal fluid (CSF) concentration directly from amyloid PET images, independent of tracers, brain reference regions or preselected regions of interest. We used 1870 A\u03b2 PET images and CSF measurements to train and validate a convolutional neural network (\u201cArcheD\u201d). We evaluated the ArcheD performance in relation to episodic memory and the standardized uptake value ratio (SUVR) of cortical A\u03b2. We also compared the brain region\u2019s relevance for the model\u2019s CSF prediction within clinical-based and biological-based classifications. ArcheD-predicted A\u03b2 CSF values correlated strongly with measured A\u03b2 CSF values (\n                  <jats:italic>r<\/jats:italic>\n                  =0.81;\n                  <jats:italic>p<\/jats:italic>\n                  &lt;0.001) and showed correlations with SUVR and episodic memory measures in all participants except in those with AD. For both clinical and biological classifications, cerebral white matter significantly contributed to CSF prediction (\n                  <jats:italic>q<\/jats:italic>\n                  &lt;0.01), specifically in non-symptomatic and early stages of AD. However, in late-stage disease, brain stem, subcortical areas, cortical lobes, limbic lobe, and basal forebrain made more significant contributions (q&lt;0.01). Considering cortical gray matter separately, the parietal lobe was the strongest predictor of CSF amyloid levels in those with prodromal or early AD, while the temporal lobe played a more crucial role for those with AD. In summary, ArcheD reliably predicted A\u03b2 CSF concentration from A\u03b2 PET scans, offering potential clinical utility for A\u03b2 level determination and early AD detection.\n                <\/jats:p>","DOI":"10.1101\/2023.06.20.545686","type":"posted-content","created":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T10:34:49Z","timestamp":1687602889000},"source":"Crossref","is-referenced-by-count":0,"title":["ArcheD, a residual neural network for prediction of cerebrospinal fluid amyloid-beta from amyloid PET images"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2906-6279","authenticated-orcid":false,"given":"Arina A.","family":"Tagmazian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3234-912X","authenticated-orcid":false,"given":"Claudia","family":"Schwarz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6745-8441","authenticated-orcid":false,"given":"Catharina","family":"Lange","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9818-6370","authenticated-orcid":false,"given":"Esa","family":"Pitk\u00e4nen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6534-3667","authenticated-orcid":false,"given":"Eero","family":"Vuoksimaa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"name":"the Alzheimer\u2019s Disease Neuroimaging Initiative","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2023103004100562000_2023.06.20.545686v3.1","doi-asserted-by":"publisher","DOI":"10.1001\/archneur.65.11.1509"},{"key":"2023103004100562000_2023.06.20.545686v3.2","doi-asserted-by":"publisher","DOI":"10.54294\/uvnhin"},{"key":"2023103004100562000_2023.06.20.545686v3.3","doi-asserted-by":"publisher","DOI":"10.1007\/s12021-014-9258-x"},{"key":"2023103004100562000_2023.06.20.545686v3.4","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.7795644"},{"key":"2023103004100562000_2023.06.20.545686v3.5","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-019-04538-7"},{"key":"2023103004100562000_2023.06.20.545686v3.6","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018180958"},{"issue":"1","key":"2023103004100562000_2023.06.20.545686v3.7","first-page":"1","article-title":"Improving 3D Convolutional Neural Network Comprehensibility via Interactive Visualization of Relevance Maps: Evaluation in Alzheimer\u2019s Disease","volume":"13","year":"2021","journal-title":"Alzheimer\u2019s Research & Therapy"},{"key":"2023103004100562000_2023.06.20.545686v3.8","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1146\/annurev-clinpsy-072720-014213","article-title":"Cognitive Aging and the Promise of Physical Activity","volume":"18","year":"2022","journal-title":"Annual Review of Clinical Psychology"},{"issue":"8","key":"2023103004100562000_2023.06.20.545686v3.9","doi-asserted-by":"crossref","first-page":"986","DOI":"10.1016\/j.jalz.2015.03.002","article-title":"Florbetapir Positron Emission Tomography and Cerebrospinal Fluid Biomarkers","volume":"11","author":"Alzheimer\u2019s Disease Neuroimaging Initiative","year":"2015","journal-title":"Alzheimer\u2019s & Dementia"},{"issue":"8","key":"2023103004100562000_2023.06.20.545686v3.10","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1038\/s43587-022-00269-x","article-title":"Designing the next-Generation Clinical Care Pathway for Alzheimer\u2019s Disease","volume":"2","year":"2022","journal-title":"Nature Aging"},{"issue":"9","key":"2023103004100562000_2023.06.20.545686v3.11","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1038\/s41582-021-00520-w","article-title":"Developing the ATX(N) Classification for Use across the Alzheimer Disease Continuum","volume":"17","year":"2021","journal-title":"Nature Reviews. Neurology"},{"key":"2023103004100562000_2023.06.20.545686v3.12","doi-asserted-by":"publisher","DOI":"10.1038\/s41380-021-01249-0)"},{"key":"2023103004100562000_2023.06.20.545686v3.13","doi-asserted-by":"publisher","DOI":"10.1186\/s13550-020-00714-1"},{"key":"2023103004100562000_2023.06.20.545686v3.14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.03385"},{"key":"2023103004100562000_2023.06.20.545686v3.15","doi-asserted-by":"publisher","DOI":"10.1093\/braincomms\/fcaa024"},{"issue":"3","key":"2023103004100562000_2023.06.20.545686v3.16","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/j.jalz.2011.03.004","article-title":"Introduction to the Recommendations from the National Institute on Aging-Alzheimer\u2019s Association Workgroups on Diagnostic Guidelines for Alzheimer\u2019s Disease","volume":"7","year":"2011","journal-title":"Alzheimer\u2019s & Dementia: The Journal of the Alzheimer\u2019s Association"},{"issue":"4","key":"2023103004100562000_2023.06.20.545686v3.17","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/j.jalz.2018.02.018","article-title":"NIA-AA Research Framework: Toward a Biological Definition of Alzheimer\u2019s Disease","volume":"14","year":"2018","journal-title":"Alzheimer\u2019s & Dementia: The Journal of the Alzheimer\u2019s Association"},{"key":"2023103004100562000_2023.06.20.545686v3.18","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e3182840bbe"},{"issue":"1","key":"2023103004100562000_2023.06.20.545686v3.19","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/S1474-4422(09)70299-6","article-title":"Hypothetical Model of Dynamic Biomarkers of the Alzheimer\u2019s Pathological Cascade","volume":"9","year":"2010","journal-title":"The Lancet Neurology"},{"issue":"1","key":"2023103004100562000_2023.06.20.545686v3.20","first-page":"1","article-title":"Appropriate Use Criteria for Amyloid PET: A Report of the Amyloid Imaging Task Force, the Society of Nuclear Medicine and Molecular Imaging, and the Alzheimer\u2019s Association","volume":"9","year":"2013","journal-title":"Alzheimer\u2019s & Dementia: The Journal of the Alzheimer\u2019s Association"},{"issue":"Suppl 21","key":"2023103004100562000_2023.06.20.545686v3.21","first-page":"496","article-title":"Deep Learning Detection of Informative Features in Tau PET for Alzheimer\u2019s Disease Classification","volume":"21","author":"Alzheimer\u2019s Neuroimaging Initiative","year":"2020","journal-title":"BMC Bioinformatics"},{"key":"2023103004100562000_2023.06.20.545686v3.22","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":"Frontiers in Aging Neuroscience"},{"issue":"5","key":"2023103004100562000_2023.06.20.545686v3.23","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1007\/s13139-019-00610-0","article-title":"Amyloid PET Quantification Via End-to-End Training of a Deep Learning","volume":"53","author":"Alzheimer\u2019s Disease Neuroimaging Initiative","year":"2019","journal-title":"Nuclear Medicine and Molecular Imaging"},{"key":"2023103004100562000_2023.06.20.545686v3.24","doi-asserted-by":"publisher","DOI":"10.1053\/j.sult.2010.10.001"},{"key":"2023103004100562000_2023.06.20.545686v3.25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980"},{"key":"2023103004100562000_2023.06.20.545686v3.26","doi-asserted-by":"publisher","DOI":"10.1002\/ana.20009"},{"issue":"11","key":"2023103004100562000_2023.06.20.545686v3.27","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1093\/jnen\/62.11.1087","article-title":"Neuropathology of Cognitively Normal Elderly","volume":"62","year":"2003","journal-title":"Journal of Neuropathology & Experimental Neurology"},{"issue":"4","key":"2023103004100562000_2023.06.20.545686v3.28","doi-asserted-by":"crossref","first-page":"567","DOI":"10.2967\/jnumed.114.148981","article-title":"\u201cMeasurement of Longitudinal \u03b2-Amyloid Change with 18F-Florbetapir PET and Standardized Uptake Value Ratios.\u201d Journal of Nuclear Medicine: Official Publication","volume":"56","year":"2015","journal-title":"Society of Nuclear Medicine"},{"key":"2023103004100562000_2023.06.20.545686v3.29","doi-asserted-by":"publisher","DOI":"10.3390\/ijms22157911"},{"key":"2023103004100562000_2023.06.20.545686v3.30","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1016\/j.neuroimage.2016.09.028","article-title":"Impact of Spillover from White Matter by Partial Volume Effect on Quantification of Amyloid Deposition with [11C]PiB PET","volume":"143","year":"2016","journal-title":"NeuroImage"},{"issue":"11","key":"2023103004100562000_2023.06.20.545686v3.31","doi-asserted-by":"crossref","first-page":"1319","DOI":"10.1001\/jamaneurol.2019.2214","article-title":"Staging \u03b2-Amyloid Pathology With Amyloid Positron Emission Tomography","volume":"76","year":"2019","journal-title":"JAMA Neurology"},{"key":"2023103004100562000_2023.06.20.545686v3.32","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.34.7.939"},{"key":"2023103004100562000_2023.06.20.545686v3.33","doi-asserted-by":"publisher","DOI":"10.1007\/s00401-011-0826-y"},{"issue":"2","key":"2023103004100562000_2023.06.20.545686v3.34","doi-asserted-by":"crossref","first-page":"561","DOI":"10.3233\/JAD-170327","article-title":"The Cerebrospinal Fluid A\u03b21-42\/A\u03b21-40 Ratio Improves Concordance with Amyloid-PET for Diagnosing Alzheimer\u2019s Disease in a Clinical Setting","volume":"60","year":"2017","journal-title":"Journal of Alzheimer\u2019s Disease: JAD"},{"key":"2023103004100562000_2023.06.20.545686v3.35","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000001991"},{"key":"2023103004100562000_2023.06.20.545686v3.36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.06853"},{"key":"2023103004100562000_2023.06.20.545686v3.37","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e3181cb3e25"},{"key":"2023103004100562000_2023.06.20.545686v3.38","doi-asserted-by":"publisher","DOI":"10.1002\/trc2.12212"},{"key":"2023103004100562000_2023.06.20.545686v3.39","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A6573"},{"issue":"2","key":"2023103004100562000_2023.06.20.545686v3.40","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1007\/s40120-014-0022-9","article-title":"Florbetaben for PET Imaging of Beta-Amyloid Plaques in the Brain","volume":"3","year":"2014","journal-title":"Neurology and Therapy"},{"key":"2023103004100562000_2023.06.20.545686v3.41","doi-asserted-by":"crossref","unstructured":"Rieke, Johannes , Fabian Eitel , Martin Weygandt , John-Dylan Haynes , and Kerstin Ritter . 2018. \u201cVisualizing Convolutional Networks for MRI-Based Diagnosis of Alzheimer\u2019s Disease.\u201d Understanding and Interpreting Machine Learning in Medical Image Computing Applications, 24\u201331.","DOI":"10.1007\/978-3-030-02628-8_3"},{"key":"2023103004100562000_2023.06.20.545686v3.42","unstructured":"Shaw, Leslie M. , and John Q. Trojanowski . 2017. \u201cBiomarker Core Report: Year1 ADNI3, Roche Elecsys Immunoassay Analyses of ADNI1\/GO\/2 CSF Samples.\u201d"},{"key":"2023103004100562000_2023.06.20.545686v3.43","doi-asserted-by":"publisher","DOI":"10.1002\/ana.21610"},{"issue":"3","key":"2023103004100562000_2023.06.20.545686v3.44","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1007\/s13760-019-01112-8","article-title":"CSF Biomarkers and Amyloid PET: Concordance and Diagnostic Accuracy in a MCI Cohort","volume":"119","year":"2019","journal-title":"Acta Neurologica Belgica"},{"issue":"1","key":"2023103004100562000_2023.06.20.545686v3.45","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1038\/nrneurol.2012.241","article-title":"Preclinical Alzheimer Disease-the Challenges Ahead","volume":"9","year":"2013","journal-title":"Nature Reviews. Neurology"},{"key":"2023103004100562000_2023.06.20.545686v3.46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6806"},{"key":"2023103004100562000_2023.06.20.545686v3.47","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.58.12.1791"},{"key":"2023103004100562000_2023.06.20.545686v3.48","doi-asserted-by":"publisher","DOI":"10.1002\/trc2.12212"},{"key":"2023103004100562000_2023.06.20.545686v3.49","doi-asserted-by":"publisher","DOI":"10.1136\/jnnp-2012-302548"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2023.06.20.545686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T04:48:41Z","timestamp":1768452521000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2023.06.20.545686"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,23]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1101\/2023.06.20.545686","relation":{"is-preprint-of":[{"id-type":"doi","id":"10.1111\/ejn.16332","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2023,6,23]]},"subtype":"preprint"}}