{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T01:48:46Z","timestamp":1768700926531,"version":"3.49.0"},"posted":{"date-parts":[[2025,9,30]]},"group-title":"Radiology and Imaging","reference-count":27,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,9,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Alzheimer\u2019s disease (AD) causes progressive structural brain changes that precede clinical symptoms by years. Detecting these changes using structural MRI remains challenging, especially in early stages and when relying on visual interpretation alone. Automated semantic segmentation methods offer anatomical precision and objective measurements, but their outputs are rarely used to support human visual assessment.<\/jats:p>\n                <jats:p>In this study, we explored whether such segmentation outputs can be used to guide a non-expert investigator in developing and applying interpretable diagnostic criteria. We used images from the Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI) and implemented a structured, segmentation-informed workflow in which a novice with no prior training in radiology or neuroanatomy developed classification rules based on visual appearance and volumetric readouts through three guided pilot phases. In a fourth phase, the investigator applied these criteria to an independent subset of ADNI images while blinded to the respective ADNI participants\u2019 diagnostic labels.<\/jats:p>\n                <jats:p>\n                  Using an anatomical segmentation model (MAPER) with training data from a pre-release version of the Hammers Adult Brain Atlas Database (120 brain regions), the investigator focused on the piriform cortex (PC). The choice of PC was context-driven, reflecting an ongoing quantitative study of PC volume. A binary classification (AD-like versus CN-like) rule based on PC volume (&lt; or &gt; 430\n                  <jats:italic>mm<\/jats:italic>\n                  <jats:sup>3<\/jats:sup>\n                  ), supported by assessments of PC shape and global atrophy, yielded an accuracy of 0.71 across 200 cases spanning four diagnostic groups. Accuracy increased to 0.77 when the analysis was restricted to CN and AD cases (with intermediate pathology (MCI) excluded).\n                <\/jats:p>\n                <jats:p>These results show that segmentation-guided visual workflows can enable non-experts to apply anatomically grounded classification criteria with moderate accuracy. Our framework can be expanded to other regions and promises to be useful for generating interpretable models, for supporting explainable AI, and for accelerating the acquisition of diagnostic skills.<\/jats:p>","DOI":"10.1101\/2025.09.29.25336750","type":"posted-content","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T20:40:21Z","timestamp":1759264821000},"source":"Crossref","is-referenced-by-count":0,"title":["Segmentation-Guided Development of Visual Classification Criteria for Alzheimer\u2019s Disease"],"prefix":"10.64898","author":[{"given":"Mirjam","family":"Peters","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6952-430X","authenticated-orcid":false,"given":"David","family":"Steinbart","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9530-4848","authenticated-orcid":false,"given":"Alexander","family":"Hammers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3582-3683","authenticated-orcid":false,"given":"Rolf A.","family":"Heckemann","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":"2025100301501282000_2025.09.29.25336750v1.1","doi-asserted-by":"publisher","DOI":"10.3390\/ijms22042110"},{"key":"2025100301501282000_2025.09.29.25336750v1.2","doi-asserted-by":"publisher","DOI":"10.1038\/s41380-023-02215-8"},{"key":"2025100301501282000_2025.09.29.25336750v1.3","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-021-08340-8"},{"key":"2025100301501282000_2025.09.29.25336750v1.4","doi-asserted-by":"publisher","DOI":"10.1136\/jnnp.55.10.967"},{"key":"2025100301501282000_2025.09.29.25336750v1.5","doi-asserted-by":"crossref","unstructured":"Lombardi G , Crescioli G , Cavedo E , Lucenteforte E , Casazza G , Bellatorre AG , et al. Structural magnetic resonance imaging for the early diagnosis of dementia due to Alzheimer\u2019s disease in people with mild cognitive impairment. Cochrane Database Syst Rev. 2020 [cited 2025 Apr 4];(3). Available from: https:\/\/www.cochranelibrary.com\/cdsr\/doi\/10.1002\/14651858.CD009628.pub2\/full","DOI":"10.1002\/14651858.CD009628.pub2"},{"key":"2025100301501282000_2025.09.29.25336750v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2006.05.061"},{"key":"2025100301501282000_2025.09.29.25336750v1.7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2011.03.014"},{"key":"2025100301501282000_2025.09.29.25336750v1.8","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1186\/1471-2342-8-9","article-title":"Automatic volumetry on MR brain images can support diagnostic decision making","volume":"8","year":"2008","journal-title":"BMC Med Imaging"},{"issue":"11","key":"2025100301501282000_2025.09.29.25336750v1.9","doi-asserted-by":"crossref","first-page":"3243","DOI":"10.3390\/s20113243","article-title":"MRI Segmentation and Classification of Human Brain Using Deep Learning for Diagnosis of Alzheimer\u2019s Disease: A Survey","volume":"20","year":"2020","journal-title":"Sensors (Basel)"},{"key":"2025100301501282000_2025.09.29.25336750v1.10","doi-asserted-by":"crossref","first-page":"1073909","DOI":"10.3389\/fnagi.2022.1073909","article-title":"A novel cascade machine learning pipeline for Alzheimer\u2019s disease identification and prediction","volume":"14","year":"2023","journal-title":"Front Aging Neurosci"},{"issue":"1","key":"2025100301501282000_2025.09.29.25336750v1.11","doi-asserted-by":"crossref","first-page":"27756","DOI":"10.1038\/s41598-024-76313-0","article-title":"Explainable early detection of Alzheimer\u2019s disease using ROIs and an ensemble of 138 3D vision transformers","volume":"14","year":"2024","journal-title":"Sci Rep"},{"key":"2025100301501282000_2025.09.29.25336750v1.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2010.01.072"},{"issue":"6","key":"2025100301501282000_2025.09.29.25336750v1.13","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1001\/jamaneurol.2019.0204","article-title":"Association of Piriform Cortex Resection With Surgical Outcomes in Patients With Temporal Lobe Epilepsy","volume":"76","year":"2019","journal-title":"JAMA Neurol"},{"issue":"4","key":"2025100301501282000_2025.09.29.25336750v1.14","doi-asserted-by":"crossref","first-page":"e70040","DOI":"10.1002\/dad2.70040","article-title":"Elevated tau in the piriform cortex in Alzheimer\u2019s but not Parkinson\u2019s disease using PET\u2010MR","volume":"16","year":"2024","journal-title":"Alzheimers Dement (Amst)"},{"key":"2025100301501282000_2025.09.29.25336750v1.15","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.10123"},{"key":"2025100301501282000_2025.09.29.25336750v1.16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2007.11.034"},{"key":"2025100301501282000_2025.09.29.25336750v1.17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.01.073"},{"key":"2025100301501282000_2025.09.29.25336750v1.18","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0180866"},{"key":"2025100301501282000_2025.09.29.25336750v1.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2007.06.004"},{"key":"2025100301501282000_2025.09.29.25336750v1.20","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.20254"},{"key":"2025100301501282000_2025.09.29.25336750v1.21","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.26274"},{"key":"2025100301501282000_2025.09.29.25336750v1.22","doi-asserted-by":"publisher","DOI":"10.2174\/1567205011666140131123653"},{"key":"2025100301501282000_2025.09.29.25336750v1.23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0129211"},{"key":"2025100301501282000_2025.09.29.25336750v1.24","unstructured":"Powers DMW . Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. 2020 [cited 2025 May 16]. Available from: http:\/\/arxiv.org\/abs\/2010.16061"},{"key":"2025100301501282000_2025.09.29.25336750v1.25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00868807"},{"key":"2025100301501282000_2025.09.29.25336750v1.26","doi-asserted-by":"publisher","DOI":"10.1016\/S1053-8119(03)00219-2"},{"issue":"1","key":"2025100301501282000_2025.09.29.25336750v1.27","doi-asserted-by":"crossref","first-page":"2837","DOI":"10.1038\/s41598-020-57951-6","article-title":"On brain atlas choice and automatic segmentation methods: A comparison of MAPER & FreeSurfer using three atlas databases","volume":"10","year":"2020","journal-title":"Sci Rep"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.09.29.25336750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:47:16Z","timestamp":1768510036000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.09.29.25336750"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1101\/2025.09.29.25336750","relation":{},"subject":[],"published":{"date-parts":[[2025,9,30]]},"subtype":"preprint"}}