{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T10:47:24Z","timestamp":1782211644486,"version":"3.54.5"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Fluids Barriers CNS"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Disproportionately enlarged subarachnoid space hydrocephalus (DESH) is a characteristic neuroimaging feature of idiopathic normal pressure hydrocephalus (iNPH), a treatable but frequently underdiagnosed condition. While brain MRI enables detailed region-based segmentation, CT is faster and widely used in daily clinical practice. However, objective and automated evaluation of DESH-related features on plain CT remains challenging. This study aimed to develop and validate an artificial intelligence-based segmentation model for automatically extracting four cerebrospinal fluid (CSF) regions from plain CT.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Synthetic CT images were generated from annotated 3D T1-weighted MRI using a cycle-generative adversarial network (Cycle-GAN) to create training data. However, segmentation accuracy based on synthetic CT was insufficient. therefore, the final model was trained using manually annotated real CT images. A deep learning model was developed to segment four CSF regions (total ventricles, total subarachnoid space [SAS], high-convexity SAS, and Sylvian fissures with basal cisterns). Model performance was evaluated using an external validation dataset (30 DESH and 30 non-DESH). In addition, a second independent validation set consisting of 115 consecutive patients was used to assess clinical utility and determine optimal cutoff values using receiver operating characteristic analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Based on external validation Dice scores, Version 10 was adopted as the final model. In internal validation, the final model achieved Dice scores\u2009&gt;\u20090.9 for total ventricles and &gt;\u20090.8 for total intracranial CSF space, with lower scores for high-convexity SAS and Sylvian fissures with basal cisterns. External validation yielded Dice scores of 0.92, 0.85, 0.60, and 0.94 for the four regions, respectively. In the second validation set, the DESH index demonstrated excellent diagnostic performance, with an area under the curve of 1.00 and an optimal cutoff value of 10 (sensitivity 100%, specificity 100%). Venthi and Sylhi indices also showed high diagnostic performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The proposed artificial intelligence model enables fully automated segmentation and quantitative assessment of DESH-related CSF regions on plain CT with high reliability. This approach may improve diagnostic accuracy, facilitate earlier detection, and support objective evaluation of postoperative changes in iNPH. Its applicability to routine CT makes it particularly valuable in settings where MRI is unavailable or contraindicated.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12987-026-00814-5","type":"journal-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T07:25:16Z","timestamp":1782199516000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CT-based automatic segmentation of key CSF regions for detecting disproportionately enlarged subarachnoid space hydrocephalus"],"prefix":"10.1186","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7158-5569","authenticated-orcid":false,"given":"Shigeki","family":"Yamada","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hirotaka","family":"Ito","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keisuke","family":"Hagiwara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasuo","family":"Kawata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chifumi","family":"Iseki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Motoki","family":"Tanikawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomohiro","family":"Otani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satoshi","family":"Ii","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshiyuki","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shigeo","family":"Wada","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marie","family":"Oshima","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mitsuhito","family":"Mase","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,23]]},"reference":[{"key":"814_CR1","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1056\/NEJM196507152730301","volume":"273","author":"RD Adams","year":"1965","unstructured":"Adams RD, Fisher CM, Hakim S, Ojemann RG, Sweet WH. Symptomatic Occult Hydrocephalus with Normal Cerebrospinal-Fluid Pressure.A Treatable Syndrome. N Engl J Med. 1965;273:117\u201326.","journal-title":"N Engl J Med"},{"issue":"3 Suppl","key":"814_CR2","first-page":"S1","volume":"57","author":"A Marmarou","year":"2005","unstructured":"Marmarou A, Bergsneider M, Relkin N, Klinge P, Black PM. Development of guidelines for idiopathic normal-pressure hydrocephalus: introduction. Neurosurgery. 2005;57(3 Suppl):S1\u20133. discussion ii-v.","journal-title":"Neurosurgery"},{"key":"814_CR3","doi-asserted-by":"crossref","unstructured":"Nakajima M, Yamada S, Miyajima M, Ishii K, Kuriyama N, Kazui H, et al. Guidelines for management of idiopathic normal pressure hydrocephalus (Third edition): Endorsed by the Japanese society of normal pressure hydrocephalus. Neurol Med Chir (Tokyo). 2021.","DOI":"10.2176\/nmc.st.2020-0292"},{"key":"814_CR4","doi-asserted-by":"publisher","first-page":"116510","DOI":"10.1016\/j.jns.2019.116510","volume":"408","author":"C Akiba","year":"2020","unstructured":"Akiba C, Gyanwali B, Villaraza S, Nakajima M, Miyajima M, Cheng CY, et al. The prevalence and clinical associations of disproportionately enlarged subarachnoid space hydrocephalus (DESH), an imaging feature of idiopathic normal pressure hydrocephalus in community and memory clinic based Singaporean cohorts. J Neurol Sci. 2020;408:116510.","journal-title":"J Neurol Sci"},{"issue":"5","key":"814_CR5","doi-asserted-by":"publisher","first-page":"e0217705","DOI":"10.1371\/journal.pone.0217705","volume":"14","author":"J Andersson","year":"2019","unstructured":"Andersson J, Rosell M, Kockum K, Lilja-Lund O, Soderstrom L, Laurell K. Prevalence of idiopathic normal pressure hydrocephalus: A prospective, population-based study. PLoS ONE. 2019;14(5):e0217705.","journal-title":"PLoS ONE"},{"issue":"2","key":"814_CR6","doi-asserted-by":"publisher","first-page":"e208037","DOI":"10.1212\/WNL.0000000000208037","volume":"102","author":"C Constantinescu","year":"2024","unstructured":"Constantinescu C, Wikkelso C, Westman E, Ziegelitz D, Jaraj D, Ryden L, et al. Prevalence of Possible Idiopathic Normal Pressure Hydrocephalus in Sweden: A Population-Based MRI Study in 791 70-Year-Old Participants. Neurology. 2024;102(2):e208037.","journal-title":"Neurology"},{"issue":"5","key":"814_CR7","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1111\/ane.13710","volume":"146","author":"C Iseki","year":"2022","unstructured":"Iseki C, Takahashi Y, Adachi M, Igari R, Sato H, Koyama S, et al. Prevalence and development of idiopathic normal pressure hydrocephalus: A 16-year longitudinal study in Japan. Acta Neurol Scand. 2022;146(5):680\u20139.","journal-title":"Acta Neurol Scand"},{"issue":"1\u20132","key":"814_CR8","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.jns.2014.01.033","volume":"339","author":"C Iseki","year":"2014","unstructured":"Iseki C, Takahashi Y, Wada M, Kawanami T, Adachi M, Kato T. Incidence of idiopathic normal pressure hydrocephalus (iNPH): a 10-year follow-up study of a rural community in Japan. J Neurol Sci. 2014;339(1\u20132):108\u201312.","journal-title":"J Neurol Sci"},{"issue":"3","key":"814_CR9","doi-asserted-by":"publisher","first-page":"e00635","DOI":"10.1002\/brb3.635","volume":"7","author":"N Kuriyama","year":"2017","unstructured":"Kuriyama N, Miyajima M, Nakajima M, Kurosawa M, Fukushima W, Watanabe Y, et al. Nationwide hospital-based survey of idiopathic normal pressure hydrocephalus in Japan: Epidemiological and clinical characteristics. Brain Behav. 2017;7(3):e00635.","journal-title":"Brain Behav"},{"key":"814_CR10","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.wneu.2023.12.094","volume":"183","author":"M Tullberg","year":"2024","unstructured":"Tullberg M, Toma AK, Yamada S, Laurell K, Miyajima M, Watkins LD, et al. Classification of Chronic Hydrocephalus in Adults: A Systematic Review and Analysis. World Neurosurg. 2024;183:113\u201322.","journal-title":"World Neurosurg"},{"key":"814_CR11","doi-asserted-by":"publisher","first-page":"583","DOI":"10.3389\/fneur.2017.00583","volume":"8","author":"S Yamada","year":"2017","unstructured":"Yamada S, Ishikawa M, Yamamoto K. Fluid distribution pattern in adult-onset congenital, idiopathic and secondary normal-pressure hydrocephalus: implications for clinical care. Front Neurol. 2017;8:583.","journal-title":"Front Neurol"},{"issue":"7","key":"814_CR12","first-page":"1277","volume":"19","author":"H Kitagaki","year":"1998","unstructured":"Kitagaki H, Mori E, Ishii K, Yamaji S, Hirono N, Imamura T. CSF spaces in idiopathic normal pressure hydrocephalus: morphology and volumetry. AJNR Am J Neuroradiol. 1998;19(7):1277\u201384.","journal-title":"AJNR Am J Neuroradiol"},{"key":"814_CR13","doi-asserted-by":"publisher","first-page":"39070","DOI":"10.1038\/srep39070","volume":"6","author":"S Yamada","year":"2016","unstructured":"Yamada S, Ishikawa M, Iwamuro Y, Yamamoto K. Choroidal fissure acts as an overflow device in cerebrospinal fluid drainage: morphological comparison between idiopathic and secondary normal-pressure hydrocephalus. Sci Rep. 2016;6:39070.","journal-title":"Sci Rep"},{"issue":"7","key":"814_CR14","doi-asserted-by":"publisher","first-page":"1249","DOI":"10.3174\/ajnr.A4695","volume":"37","author":"S Yamada","year":"2016","unstructured":"Yamada S, Ishikawa M, Yamamoto K. Comparison of CSF distribution between idiopathic normal pressure hydrocephalus and Alzheimer disease. AJNR Am J Neuroradiol. 2016;37(7):1249\u201355.","journal-title":"AJNR Am J Neuroradiol"},{"key":"814_CR15","doi-asserted-by":"publisher","first-page":"e427","DOI":"10.1016\/j.wneu.2023.05.077","volume":"176","author":"S Yamada","year":"2023","unstructured":"Yamada S, Ito H, Matsumasa H, Tanikawa M, Ii S, Otani T, et al. Tightened Sulci in the High Convexities as a Noteworthy Feature of Idiopathic Normal Pressure Hydrocephalus. World Neurosurg. 2023;176:e427\u201337.","journal-title":"World Neurosurg"},{"key":"814_CR16","doi-asserted-by":"crossref","unstructured":"Hashimoto M, Ishikawa M, Mori E, Kuwana N. Diagnosis of idiopathic normal pressure hydrocephalus is supported by MRI-based scheme: a prospective cohort study. Cerebrospinal Fluid Res. 2010;7(1).","DOI":"10.1186\/1743-8454-7-18"},{"issue":"2","key":"814_CR17","doi-asserted-by":"publisher","first-page":"119","DOI":"10.2176\/nmc.50.119","volume":"50","author":"M Ishikawa","year":"2010","unstructured":"Ishikawa M, Oowaki H, Matsumoto A, Suzuki T, Furuse M, Nishida N. Clinical significance of cerebrospinal fluid tap test and magnetic resonance imaging\/computed tomography findings of tight high convexity in patients with possible idiopathic normal pressure hydrocephalus. Neurol Med Chir (Tokyo). 2010;50(2):119\u201323. disucussion 23.","journal-title":"Neurol Med Chir (Tokyo)"},{"issue":"10","key":"814_CR18","doi-asserted-by":"publisher","first-page":"1831","DOI":"10.3174\/ajnr.A4838","volume":"37","author":"W Narita","year":"2016","unstructured":"Narita W, Nishio Y, Baba T, Iizuka O, Ishihara T, Matsuda M, et al. High-convexity tightness predicts the shunt response in idiopathic normal pressure hydrocephalus. Am J Neuroradiol. 2016;37(10):1831\u20137.","journal-title":"Am J Neuroradiol"},{"issue":"2","key":"814_CR19","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/s00234-007-0318-x","volume":"50","author":"M Sasaki","year":"2008","unstructured":"Sasaki M, Honda S, Yuasa T, Iwamura A, Shibata E, Ohba H. Narrow CSF space at high convexity and high midline areas in idiopathic normal pressure hydrocephalus detected by axial and coronal MRI. Neuroradiology. 2008;50(2):117\u201322.","journal-title":"Neuroradiology"},{"issue":"6","key":"814_CR20","doi-asserted-by":"publisher","first-page":"1436","DOI":"10.3171\/2016.9.JNS161080","volume":"127","author":"N Shinoda","year":"2017","unstructured":"Shinoda N, Hirai O, Hori S, Mikami K, Bando T, Shimo D, et al. Utility of MRI-based disproportionately enlarged subarachnoid space hydrocephalus scoring for predicting prognosis after surgery for idiopathic normal pressure hydrocephalus: clinical research. J Neurosurg. 2017;127(6):1436\u201342.","journal-title":"J Neurosurg"},{"key":"814_CR21","doi-asserted-by":"publisher","first-page":"1362637","DOI":"10.3389\/fnagi.2024.1362637","volume":"16","author":"S Yamada","year":"2024","unstructured":"Yamada S, Ito H, Matsumasa H, Ii S, Otani T, Tanikawa M, et al. Automatic assessment of disproportionately enlarged subarachnoid-space hydrocephalus from 3D MRI using two deep learning models. Front Aging Neurosci. 2024;16:1362637.","journal-title":"Front Aging Neurosci"},{"key":"814_CR22","doi-asserted-by":"crossref","unstructured":"Yamada S, Ito H, Matsumasa H, Ii S, Otani T, Tanikawa M, et al. Deep learning assessment of disproportionately enlarged subarachnoid-space hydrocephalus in Hakim\u2019s disease or idiopathic normal pressure hydrocephalus. Radiol Adv. 2024;1(3).","DOI":"10.1093\/radadv\/umae027"},{"key":"814_CR23","doi-asserted-by":"crossref","unstructured":"Zhu J-Y, Park T, Isola P, Efros. A. Unpaired image-to-image translation using cycle-consistent adversarial networks. IEEE Xplore, International Conference on Computer Vision. 2017.","DOI":"10.1109\/ICCV.2017.244"},{"issue":"6","key":"814_CR24","doi-asserted-by":"publisher","first-page":"862","DOI":"10.25122\/jml-2022-0188","volume":"16","author":"NK Abdulkareem","year":"2023","unstructured":"Abdulkareem NK, Hajee SI, Hassan FF, Ibrahim IK, Al-Khalidi REH, Abdulqader NA. Investigating the slice thickness effect on noise and diagnostic content of single-source multi-slice computerized axial tomography. J Med Life. 2023;16(6):862\u20137.","journal-title":"J Med Life"},{"key":"814_CR25","doi-asserted-by":"crossref","unstructured":"Takahashi S, Takahashi M, Kinoshita M, Miyake M, Kawaguchi R, Shinojima N, et al. Fine-tuning approach for segmentation of gliomas in brain magnetic resonance images with a machine learning method to normalize image differences among facilities. Cancers (Basel). 2021;13(6).","DOI":"10.3390\/cancers13061415"}],"container-title":["Fluids and Barriers of the CNS"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12987-026-00814-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12987-026-00814-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12987-026-00814-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T09:58:24Z","timestamp":1782208704000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12987-026-00814-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,23]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["814"],"URL":"https:\/\/doi.org\/10.1186\/s12987-026-00814-5","relation":{},"ISSN":["2045-8118"],"issn-type":[{"value":"2045-8118","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,23]]},"assertion":[{"value":"17 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study design and protocol of this prospective and observational study were approved by the ethics committees for human research at our institutes (IRB Number: 60-22-0083, R2019-227). Patients\u2019 CT data were obtained in an opt-out method, after their personal information was anonymized in a linkable manner. The study was performed in accordance with the approved guidelines of the Declaration of Helsinki.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"SY began working as a neurosurgeon in 1997 and commenced his research at Kyoto University Graduate School of Medicine in 2001. Over the course of four years, SY acquired a knowledge in medical statistics and genetics. In 2017, SY initiated collaborations with Fujifilm Corporation on 3D\/4D image analysis research.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Authors' information"}},{"value":"S.Y. was responsible for data control and analysis. He has received research funding from FUJIFILM Corporation and speaker honoraria from Fujifilm Medical Systems since 2019.H.I., K.H., and Y.K. are employees of FUJIFILM Corporation and were instrumental in developing the deep learning model. Specifically, K.H. served as the core developer of the Cycle-GAN, and HI and Y.K. as the core developers of the 3D U-Net model. However, they were not involved in the data extraction or statistical analysis for this study.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"83"}}