{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T13:01:47Z","timestamp":1784811707747,"version":"3.55.0"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neuroinform."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Automatically localizing the Anterior Commissure (AC) and Posterior Commissure (PC) is foundational for CT-based algorithmic disease screening, yet robust computational methods for this on CT remain lacking. We developed a registration-guided 3D-UNet framework for CT-based AC-PC localization, demonstrating its utility in computing ventriculomegaly features for Normal Pressure Hydrocephalus (NPH) detection.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Framework development and evaluation were on an internal cohort of scans from patients with NPH, Alzheimer\u2019s disease, post-traumatic volume loss, and headache (Veterans Affairs [VA]-Cohort,\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f427). External validation was on separate datasets (VA-ExtCohort, University of California, Santa Barbara [UCSB]-ExtCohort). AC-PC reference standard definition, model development, and evaluation were on 1 mm\n                      <jats:sup>3<\/jats:sup>\n                      \u2013resampled scans.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      On 1-mm\n                      <jats:sup>3<\/jats:sup>\n                      resampled scans, test-set AC-PC mean radial errors (MREs) were 1.64\/1.49 mm on the VA-Cohort, 2.42\/1.79 mm on the VA-ExtCohort (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f40), and 2.31\/1.93 mm on the UCSB-ExtCohort (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f43). Notably, the upper limits of the 95% confidence intervals (CIs) for localization errors across all cohorts were well below 3.2 mm; we empirically determined this to be a clinically relevant threshold beyond which the discriminative power of AC-PC-referenced ventriculomegaly features degrades. Ventriculomegaly features assessed using our framework\u2019s predictions successfully distinguished NPH from Alzheimer\u2019s disease, post-traumatic volume loss, and headache on a chart-verified VA-Cohort subset (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f238) with a test-set Area Under the Receiver Operating Characteristic Curve (AUC) of 0.95, closely matching the performance of features assessed using manual AC-PC localization.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed registration-guided 3D-UNet framework accurately and automatically localizes the AC-PC on CT despite varied structural degeneration, enabling standardized radiological feature computation. This approach can augment neurodegenerative disease screening on CT, the primary modality for elderly patients evaluated for falls and altered mentation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fninf.2026.1853412","type":"journal-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T05:34:38Z","timestamp":1784612078000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic coarse-to-fine AC-PC localization on CT using registration-guided 3D-UNets"],"prefix":"10.3389","volume":"20","author":[{"given":"Sharada","family":"Kadaba Sridhar","sequence":"first","affiliation":[{"name":"Department of Bioinformatics and Computational Biology, University of Minnesota","place":["Minneapolis, MN, United States"]},{"name":"Neurotrauma Research Lab, Center for Veterans Research and Education","place":["Minneapolis, MN, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alyssa","family":"Eastman","sequence":"additional","affiliation":[{"name":"Neurotrauma Research Lab, Center for Veterans Research and Education","place":["Minneapolis, MN, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Wilson","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, University of Minnesota","place":["Minneapolis, MN, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shubhendu","family":"Mishra","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, University of Minnesota","place":["Minneapolis, MN, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charles","family":"Broadbent","sequence":"additional","affiliation":[{"name":"Neurotrauma Research Lab, Center for Veterans Research and Education","place":["Minneapolis, MN, United States"]},{"name":"Department of Computer Science and Engineering, University of Minnesota","place":["Minneapolis, MN, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chip","family":"Truwit","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of Minnesota","place":["Minneapolis, MN, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Kuang","sequence":"additional","affiliation":[{"name":"Department of Bioinformatics and Computational Biology, University of Minnesota","place":["Minneapolis, MN, United States"]},{"name":"Department of Computer Science and Engineering, University of Minnesota","place":["Minneapolis, MN, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Uzma","family":"Samadani","sequence":"additional","affiliation":[{"name":"Department of Bioinformatics and Computational Biology, University of Minnesota","place":["Minneapolis, MN, United States"]},{"name":"Neurotrauma Research Lab, Center for Veterans Research and Education","place":["Minneapolis, MN, United States"]},{"name":"Division of Neurosurgery, Department of Surgery, Minneapolis Veterans Affairs Health Care System","place":["Minneapolis, MN, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1016\/j.neuroimage.2009.02.030","article-title":"Model-based automatic detection of the anterior and posterior commissures on MRI scans","volume":"46","author":"Ardekani","year":"2009","journal-title":"NeuroImage"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1186\/s12987-025-00677-2","article-title":"qDESH: a method to quantify disproportionately enlarged subarachnoid space hydrocephalus","volume":"22","author":"Behndig","year":"2025","journal-title":"Fluids Barriers of the CNS"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.3174\/ajnr.A7153","article-title":"Head CT: toward making full use of the information the X-rays give","volume":"42","author":"Cauley","year":"2021","journal-title":"AJNR Am. J. Neuroradiol."},{"key":"ref4","year":"2026"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"653","DOI":"10.3348\/kjr.2013.14.4.653","article-title":"Anterior commissure--posterior commissure revisited","volume":"14","author":"Choi","year":"2013","journal-title":"Korean J. Radiol."},{"key":"ref6","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1007\/978-3-319-46723-8_49","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2016","author":"\u00c7i\u00e7ek","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"670287","DOI":"10.3389\/fnins.2021.670287","article-title":"DeepNavNet: automated landmark localization for neuronavigation","volume":"15","author":"Edwards","year":"2021","journal-title":"Front. Neurosci."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1016\/j.mri.2012.05.001","article-title":"3D slicer as an image computing platform for the quantitative imaging network","volume":"30","author":"Fedorov","year":"2012","journal-title":"Magn. Reson. Imaging"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1016\/j.neuroimage.2017.04.012","article-title":"Robust automated constellation-based landmark detection in human brain imaging","volume":"170","author":"Ghayoor","year":"2018","journal-title":"NeuroImage"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1016\/j.procs.2023.01.082","article-title":"Deep learning-based automated localisation of anterior commissure and posterior commissure landmarks in 3D space from three-plane 2D MRI localiser slices of the brain","volume":"218","author":"Gohel","year":"2023","journal-title":"Procedia Comput. Sci."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/j.jdbs.2023.05.004","article-title":"Impact of preoperative computed tomography image slice thickness on the planning of deep brain stimulation surgery: a phantom study","volume":"2","author":"Gubler","year":"2023","journal-title":"Deep Brain Stimulation"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"9907","DOI":"10.1007\/s00521-023-08225-5","article-title":"Detection of idiopathic normal pressure hydrocephalus on head CT using a deep convolutional neural network","volume":"35","author":"Haber","year":"2023","journal-title":"Neural Comput. & Applic."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"119474","DOI":"10.1016\/j.neuroimage.2022.119474","article-title":"SynthStrip: skull-stripping for any brain image","volume":"260","author":"Hoopes","year":"2022","journal-title":"NeuroImage"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1347200","DOI":"10.3389\/fneur.2024.1347200","article-title":"Structural neuroimaging markers of normal pressure hydrocephalus versus Alzheimer\u2019s dementia and Parkinson\u2019s disease, and hydrocephalus versus atrophy in chronic TBI-a narrative review","volume":"15","author":"Kadaba Sridhar","year":"","journal-title":"Front. Neurol."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"822","DOI":"10.3171\/2023.12.JNS231780","article-title":"A ventriculomegaly feature computational pipeline to improve the screening of normal pressure hydrocephalus on CT","volume":"141","author":"Kadaba Sridhar","year":"","journal-title":"J. Neurosurg."},{"key":"ref16","volume-title":"Khan\u2019s the Physics of Radiation Therapy","author":"Khan","year":"2014"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"15-U32","DOI":"10.3238\/arztebl.2012.0015","article-title":"The differential diagnosis and treatment of normal-pressure hydrocephalus","volume":"109","author":"Kiefer","year":"2012","journal-title":"Dtsch. Arztebl. Int."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1704","DOI":"10.3174\/ajnr.A1676","article-title":"A new reference line for the brain CT: the tuberculum sellae-occipital protuberance line is parallel to the anterior\/posterior commissure line","volume":"30","author":"Kim","year":"2009","journal-title":"Am. J. Neuroradiol."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1109\/TMI.2009.2035616","article-title":"Elastix: a toolbox for intensity-based medical image registration","volume":"29","author":"Klein","year":"2010","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e0232275","DOI":"10.1371\/journal.pone.0232275","article-title":"Diagnostic accuracy of the iNPH Radscale in idiopathic normal pressure hydrocephalus","volume":"15","author":"Kockum","year":"2020","journal-title":"PLoS One"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1659","DOI":"10.1007\/s00234-021-02658-2","article-title":"Callosal angle in idiopathic normal pressure hydrocephalus: small angular mal-rotations of the coronal plane affect measurement reliability","volume":"63","author":"Lee","year":"2021","journal-title":"Neuroradiology"},{"key":"ref22","first-page":"2999","author":"Lin","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.1109\/JBHI.2015.2428672","article-title":"Automatic localization of the anterior commissure, posterior commissure, and midsagittal plane in MRI scans using regression forests","volume":"19","author":"Liu","year":"2015","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"54","DOI":"10.3390\/diagnostics11010054","article-title":"An extension of the bland-Altman plot for analyzing the agreement of more than two raters","volume":"11","author":"M\u00f6ller","year":"2021","journal-title":"Diagnostics"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"63","DOI":"10.2176\/nmc.st.2020-0292","article-title":"Guidelines for management of idiopathic normal pressure hydrocephalus (third edition): endorsed by the Japanese Society of Normal Pressure Hydrocephalus","volume":"61","author":"Nakajima","year":"2021","journal-title":"Neurol. Med. Chir. (Tokyo)"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"906","DOI":"10.1377\/hlthaff.2020.00338","article-title":"Rural hospital imaging: the authors reply","volume":"39","author":"O\u2019Hanlon","year":"2020","journal-title":"Health Aff. (Millwood)."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"2039","DOI":"10.1109\/TMI.2014.2330355","article-title":"Comparative evaluation of registration algorithms in different brain databases with varying difficulty: results and insights","volume":"33","author":"Ou","year":"2014","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"4187","DOI":"10.1002\/hbm.25474","article-title":"Improved normalization of lesioned brains via cohort-specific templates","volume":"42","author":"Pappas","year":"2021","journal-title":"Hum. Brain Mapp."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"827","DOI":"10.3348\/kjr.2016.17.6.827","article-title":"Structural MR imaging in the diagnosis of Alzheimer\u2019s disease and other neurodegenerative dementia: current imaging approach and future perspectives","volume":"17","author":"Park","year":"2016","journal-title":"Korean J. Radiol."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.meddos.2007.09.002","article-title":"Impact of different CT slice thickness on clinical target volume for 3D conformal radiation therapy","volume":"34","author":"Prabhakar","year":"2009","journal-title":"Med. Dosim."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.3390\/biomedicines11051265","article-title":"Imaging markers for Normal pressure hydrocephalus: an overview","volume":"11","author":"Pyrgelis","year":"2023","journal-title":"Biomedicine"},{"key":"ref32","volume-title":"Python Language Reference, Version 3.12","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1405363","DOI":"10.3389\/fnins.2024.1405363","article-title":"Evaluating normalized registration and preprocessing methodologies for the analysis of brain MRI in pediatric patients with shunt-treated hydrocephalus","volume":"18","author":"Ragguett","year":"2024","journal-title":"Front. Neurosci."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s41597-020-0379-9","article-title":"High-resolution T2-FLAIR and non-contrast CT brain atlas of the elderly","volume":"7","author":"Rajashekar","year":"2020","journal-title":"Sci. Data"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1055\/a-1167-8368","article-title":"Automatic alignment of cranial CT examinations to the anterior commissure\/posterior commissure (ACPC) reference plane for reliable interpretation and quality assurance","volume":"193","author":"Rubbert","year":"2021","journal-title":"RoFo"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1201","DOI":"10.3174\/ajnr.A7095","article-title":"Variability of Normal pressure hydrocephalus imaging biomarkers with respect to section plane angulation: how wrong a radiologist can be?","volume":"42","author":"Ryska","year":"2021","journal-title":"AJNR Am. J. Neuroradiol."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"e4.2","DOI":"10.1136\/jnnp-2019-ABN.12","article-title":"WP1-10 prevalence of normal pressure hydrocephalus in falls clinic patients","volume":"90","author":"Sennik","year":"2019","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"2840","DOI":"10.3390\/diagnostics13172840","article-title":"The diagnostic accuracy of artificial intelligence in radiological markers of Normal-pressure hydrocephalus (NPH) on non-contrast CT scans of the brain","volume":"13","author":"Songsaeng","year":"2023","journal-title":"Diagnostics"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1007\/s00415-004-0276-8","article-title":"Falls in frequent neurological diseases--prevalence, risk factors and aetiology","volume":"251","author":"Stolze","year":"2004","journal-title":"J. Neurol."},{"key":"ref40","first-page":"101342C","volume-title":"SPIE Medical Imaging","author":"Takahashi","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1093\/ppar\/prz031","article-title":"A population-based perspective on health care for U.S. veterans","volume":"30","author":"Wilmoth","year":"2020","journal-title":"Public Policy Aging Rep."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1148\/radiology.184.1.1609066","article-title":"Gantry angulation in brain CT: dosage implications, effect on posterior fossa artifacts, and current international practice","volume":"184","author":"Yeoman","year":"1992","journal-title":"Radiology"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1186\/s12938-021-00971-8","article-title":"Brain CT registration using hybrid supervised convolutional neural network","volume":"20","author":"Yuan","year":"2021","journal-title":"Biomed. Eng. Online"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"9783128","DOI":"10.34133\/2022\/9783128","article-title":"Automated segmentation and connectivity analysis for Normal pressure hydrocephalus","volume":"2022","author":"Zhang","year":"2022","journal-title":"BME Front."},{"key":"ref45","first-page":"97840Y","author":"Zhao","year":"2016"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1007\/978-3-030-32226-7_60","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"Zhong","year":"2019"}],"container-title":["Frontiers in Neuroinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2026.1853412\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T12:14:47Z","timestamp":1784808887000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2026.1853412\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"references-count":46,"alternative-id":["10.3389\/fninf.2026.1853412"],"URL":"https:\/\/doi.org\/10.3389\/fninf.2026.1853412","relation":{},"ISSN":["1662-5196"],"issn-type":[{"value":"1662-5196","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,21]]},"article-number":"1853412"}}