{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T11:11:11Z","timestamp":1765278671713,"version":"3.46.0"},"posted":{"date-parts":[[2025,12,2]]},"group-title":"Radiology and Imaging","reference-count":22,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"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":[[2025,12,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Ventriculomegaly is a key neuroimaging feature in conditions such as normal pressure hydrocephalus (NPH) and other disorders of cerebrospinal fluid (CSF) dynamics. The Evans Index (EI), defined as the ratio of the maximal frontal horn width to the maximal inner skull diameter, remains a simple and widely used marker for ventricular enlargement. However, manual EI measurement is subject to observer variability and dependent on proper alignment to the anterior commissure-posterior commissure (AC-PC) plane, limiting reproducibility in large-scale and multi-center studies.<\/jats:p>\n                <jats:p>We present a fully automated deep learning-based pipeline for EI calculation directly from raw T1-weighted MPRAGE MRI scans. The pipeline integrates (i) landmark detection using the BrainSignsNet model, (ii) rigid AC-PC alignment, and (iii) robust segmentation of the lateral ventricles (LV) and intracranial volume (ICV) via nnU-Net models, including a custom ventricular network trained on 1,300 annotated scans enriched for hydrocephalus. The Evans Index is then derived from automated measurement of frontal horn width and inner skull diameter at the aligned axial slice.<\/jats:p>\n                <jats:p>Internal validation using data from the Baltimore Longitudinal Study of Aging, BIOCARD, and Johns Hopkins cohorts demonstrated high segmentation accuracy (Dice coefficient = 0.98). External validation on the PENS trial, including pre- and post-shunt NPH scans, showed excellent agreement with expert manual EI measurements (mean bias = 0.0068, mean absolute error = 0.0103, r = 0.96, p &lt; 0.001). Bias analyses revealed no significant association between measurement error and age, sex, or ventricular volume<\/jats:p>\n                <jats:p>This fully automated, orientation-standardized method achieves accurate and reproducible Evans Index measurement across diverse MRI datasets. By eliminating manual intervention, the pipeline enhances scalability for large neuroimaging cohorts and provides a reliable tool for clinical assessment, screening and monitoring of ventriculomegaly, especially in NPH.<\/jats:p>","DOI":"10.64898\/2025.11.30.25341302","type":"posted-content","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T11:06:03Z","timestamp":1765278363000},"source":"Crossref","is-referenced-by-count":0,"title":["Fully Automated Deep Learning-Based Pipeline for Evans Index Measurement from Raw 3D MRI"],"prefix":"10.64898","author":[{"given":"Siavash","family":"Shirzadeh Barough","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5042-7422","authenticated-orcid":false,"given":"Murat","family":"Bilgel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ameya","family":"Moghekar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Catalina","family":"Ventura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark G.","family":"Luciano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9464-1551","authenticated-orcid":false,"given":"Abhay","family":"Moghekar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2025120902592397000_2025.11.30.25341302v1.1","doi-asserted-by":"publisher","DOI":"10.1002\/ana.25046"},{"key":"2025120902592397000_2025.11.30.25341302v1.2","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1590\/1980-57642018dn13-020001","article-title":"Normal-pressure hydrocephalus: A critical review","volume":"13","year":"2019","journal-title":"Dementia & neuropsychologia"},{"key":"2025120902592397000_2025.11.30.25341302v1.3","first-page":"12","article-title":"Characterizing biomarker features of cognitively normal individuals with ventriculomegaly","volume":"10","year":"2018","journal-title":"Alzheimer\u2019s & Dementia: Diagnosis, Assessment & Disease Monitoring"},{"key":"2025120902592397000_2025.11.30.25341302v1.4","doi-asserted-by":"publisher","DOI":"10.1159\/000370033"},{"key":"2025120902592397000_2025.11.30.25341302v1.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcms.2015.04.025"},{"key":"2025120902592397000_2025.11.30.25341302v1.6","doi-asserted-by":"crossref","first-page":"783092","DOI":"10.3389\/fnagi.2021.783092","article-title":"Application of Evans index in normal pressure hydrocephalus patients: a mini review","volume":"13","year":"2022","journal-title":"Frontiers in Aging Neuroscience"},{"key":"2025120902592397000_2025.11.30.25341302v1.7","doi-asserted-by":"publisher","DOI":"10.1227\/NEU.0b013e318208f5e0"},{"key":"2025120902592397000_2025.11.30.25341302v1.8","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-020-07555-5"},{"key":"2025120902592397000_2025.11.30.25341302v1.9","first-page":"1416","volume-title":"The Baltimore Longitudinal Study of Aging (BLSA): a 50-year-long journey and plans for the future","volume":"63","year":"2008"},{"key":"2025120902592397000_2025.11.30.25341302v1.10","doi-asserted-by":"publisher","DOI":"10.1227\/neu.0000000000002225"},{"key":"2025120902592397000_2025.11.30.25341302v1.11","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2010.2046908"},{"key":"2025120902592397000_2025.11.30.25341302v1.12","doi-asserted-by":"crossref","unstructured":"shirzadeh barough , s., et al. BrainSignsNET: A Deep Learning Model for 3D Anatomical Landmark Detection in the Human Brain Imaging. medRxiv, 2025.2007. 2031.25332457 (2025).","DOI":"10.1101\/2025.07.31.25332457"},{"key":"2025120902592397000_2025.11.30.25341302v1.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2015.11.073"},{"key":"2025120902592397000_2025.11.30.25341302v1.14","article-title":"Medical sam 2: Segment medical images as video via segment anything model 2","year":"2024","journal-title":"arXiv preprint"},{"key":"2025120902592397000_2025.11.30.25341302v1.15","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","year":"2021","journal-title":"Nature methods"},{"key":"2025120902592397000_2025.11.30.25341302v1.16","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.clineuro.2012.04.012","article-title":"CSF dynamics analysis in patients with post-traumatic ventriculomegaly","volume":"115","year":"2013","journal-title":"Clinical neurology and neurosurgery"},{"key":"2025120902592397000_2025.11.30.25341302v1.17","doi-asserted-by":"crossref","first-page":"107","DOI":"10.4103\/ajns.AJNS_354_19","article-title":"Reliability and interobserver variability of Evans\u2019 index and disproportionately enlarged subarachnoid space hydrocephalus as diagnostic criteria for idiopathic normal pressure hydrocephalus","volume":"15","year":"2020","journal-title":"Asian Journal of Neurosurgery"},{"key":"2025120902592397000_2025.11.30.25341302v1.18","doi-asserted-by":"crossref","first-page":"2624","DOI":"10.1038\/s41467-020-15948-9","article-title":"The UK Biobank imaging enhancement of 100,000 participants: rationale, data collection, management and future directions","volume":"11","year":"2020","journal-title":"Nature communications"},{"key":"2025120902592397000_2025.11.30.25341302v1.19","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1002\/jmri.21049","article-title":"The Alzheimer\u2019s disease neuroimaging initiative (ADNI): MRI methods","volume":"27","year":"2008","journal-title":"Journal of Magnetic Resonance Imaging: An Official Journal of the International Society for Magnetic Resonance in Medicine"},{"key":"2025120902592397000_2025.11.30.25341302v1.20","first-page":"540","volume-title":"in radiology: current technology and future directions. in Seminars in musculoskeletal radiology","volume":"22","year":"2018"},{"key":"2025120902592397000_2025.11.30.25341302v1.21","doi-asserted-by":"crossref","unstructured":"Wang, Y. , et al. Automated ventricle parcellation and evan\u2019s ratio computation in pre- and post-surgical ventriculomegaly. in 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI) 1\u20135 (IEEE, 2023).","DOI":"10.1109\/ISBI53787.2023.10230729"},{"key":"2025120902592397000_2025.11.30.25341302v1.22","first-page":"600","volume-title":"in Medical imaging 2017: Computer-aided diagnosis","volume":"10134","year":"2017"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2025.11.30.25341302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T11:06:08Z","timestamp":1765278368000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2025.11.30.25341302"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":22,"URL":"https:\/\/doi.org\/10.64898\/2025.11.30.25341302","relation":{},"subject":[],"published":{"date-parts":[[2025,12,2]]},"subtype":"preprint"}}