{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T19:25:07Z","timestamp":1793042707345,"version":"4.5.0"},"reference-count":41,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Wong Vung-Hoa Foundation of Radiological Medicine"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Spontaneous intracranial hypotension (SIH), caused by spinal cerebrospinal fluid (CSF) leakage, commonly presents with orthostatic headache and CSF hypovolemia. While CSF dynamics in the cerebral aqueduct are well studied, alterations in spinal CSF flow remain less defined. We aimed to quantitatively assess spinal CSF flow at C2 using phase-contrast (PC) MRI enhanced by artificial intelligence (AI) and to evaluate its utility for diagnosing SIH and predicting responses to epidural blood patch (EBP). Methods: We enrolled 31 patients with MRI-confirmed SIH and 26 age- and sex-matched healthy volunteers (HVs). All participants underwent ECG-gated cine PC-MRI at the C2 level and whole-spine MR myelography. AI-based segmentation using YOLOv4 and a pulsatility-based algorithm was used to extract quantitative CSF flow metrics. Between-group comparisons were analyzed using Mann\u2013Whitney U tests, and receiver operating characteristic (ROC) analysis was used to evaluate diagnostic and predictive performance. Results: Compared to HVs, SIH patients showed significantly reduced CSF flow parameters across all metrics, including upward\/downward mean flow, peak flow, total flow per cycle, and absolute stroke volume (all p &lt; 0.001). ROC analysis revealed excellent diagnostic accuracy for multiple parameters, particularly downward peak flow (AUC = 0.844) and summation of peak flow (AUC = 0.841). Importantly, baseline CSF flow metrics significantly distinguished patients who required one versus multiple epidural blood patches (EBPs) (all p &lt; 0.001). ROC analysis demonstrated that several parameters achieved near-perfect to perfect accuracy in predicting EBP success, with AUCs up to 1.0 and 100% sensitivity\/specificity. Conclusions: AI-enhanced PC-MRI enables the robust, quantitative evaluation of spinal CSF dynamics in SIH. These flow metrics not only differentiate SIH patients from healthy individuals but also predict response to EBP treatment with high accuracy. Quantitative CSF flow analysis may support both diagnosis and personalized treatment planning in SIH.<\/jats:p>","DOI":"10.3390\/diagnostics15182339","type":"journal-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T16:27:33Z","timestamp":1757953653000},"page":"2339","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["AI-Augmented Quantitative MRI Predicts Spontaneous Intracranial Hypotension"],"prefix":"10.3390","volume":"15","author":[{"given":"Yi-Jhe","family":"Huang","sequence":"first","affiliation":[{"name":"Graduate Institute of Biomedical Sciences, China Medical University, Taichung 404328, Taiwan"},{"name":"Department of Radiology, Taichung Veterans General Hospital, Taichung 407219, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jyh-Wen","family":"Chai","sequence":"additional","affiliation":[{"name":"Department of Radiology, Taichung Veterans General Hospital, Taichung 407219, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4028-8697","authenticated-orcid":false,"given":"Wen-Hsien","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Radiology, Taichung Veterans General Hospital, Taichung 407219, Taiwan"},{"name":"Department of Post-Baccalaureate Medicine, College of Medicine, National Chung Hsing University, Taichung 402202, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3544-5045","authenticated-orcid":false,"given":"Hung-Chieh","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Radiology, Taichung Veterans General Hospital, Taichung 407219, Taiwan"},{"name":"Department of Post-Baccalaureate Medicine, College of Medicine, National Chung Hsing University, Taichung 402202, Taiwan"},{"name":"College of Medicine, National Yang-Ming Chiao Tung University, Taipei 112304, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7955-9234","authenticated-orcid":false,"given":"Da-Chuan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Biomedical Imaging and Radiological Science, China Medical University, Taichung 404328, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2286","DOI":"10.1001\/jama.295.19.2286","article-title":"Spontaneous spinal cerebrospinal fluid leaks and intracranial hypotension","volume":"295","author":"Schievink","year":"2006","journal-title":"Jama"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1034","DOI":"10.1111\/head.12149","article-title":"Spontaneous low pressure, low CSF volume headaches: Spontaneous CSF leaks","volume":"53","author":"Mokri","year":"2013","journal-title":"Headache"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1339","DOI":"10.3174\/ajnr.A8030","article-title":"Likelihood of Discovering a CSF Leak Based on Intracranial MRI Findings in Patients without a Spinal Longitudinal Extradural Collection: A New Probabilistic Scoring System","volume":"44","author":"Benson","year":"2023","journal-title":"AJNR Am. J. Neuroradiol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1177\/0333102413519513","article-title":"Usefulness of phase-contrast magnetic resonance imaging for diagnosis and treatment evaluation in patients with SIH","volume":"34","author":"Tung","year":"2014","journal-title":"Cephalalgia"},{"key":"ref_5","first-page":"67","article-title":"Application of Cine Phase Contrast MRI in Spontaneous Intracranial Hypotension Before and After Treatment","volume":"39","author":"Yang","year":"2014","journal-title":"J. Radiol. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1255","DOI":"10.1002\/jmri.25976","article-title":"Noninvasive assessment of intracranial elastance and pressure in spontaneous intracranial hypotension by MRI","volume":"48","author":"Tsai","year":"2018","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e651","DOI":"10.1212\/WNL.0000000000201527","article-title":"CSF Flow and Spinal Cord Motion in Patients With Spontaneous Intracranial Hypotension: A Phase Contrast MRI Study","volume":"100","author":"Wolf","year":"2023","journal-title":"Neurology"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"4336","DOI":"10.1007\/s00415-024-12365-6","article-title":"Non-invasive biomarkers for spontaneous intracranial hypotension (SIH) through phase-contrast MRI","volume":"271","author":"Wolf","year":"2024","journal-title":"J. Neurol."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Beltr\u00e1n, S., Reisert, M., Krafft, A.J., Frase, S., Mast, H., Urbach, H., Luetzen, N., Hohenhaus, M., and Wolf, K. (2024). Spinal cord motion and CSF flow in the cervical spine of 70 healthy participants. NMR Biomed., 37.","DOI":"10.1002\/nbm.5013"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2463","DOI":"10.1007\/s00701-020-04447-x","article-title":"Semantic segmentation of cerebrospinal fluid and brain volume with a convolutional neural network in pediatric hydrocephalus-transfer learning from existing algorithms","volume":"162","author":"Grimm","year":"2020","journal-title":"Acta Neurochir."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"e26673","DOI":"10.1016\/j.heliyon.2024.e26673","article-title":"Automatic segmentation of hemispheric CSF on MRI using deep learning: Quantifying cerebral edema following large hemispheric infarction","volume":"10","author":"Cui","year":"2024","journal-title":"Heliyon"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Puzio, T., Matera, K., Wi\u015bniewski, K., Grobelna, M., Wanibuchi, S., Jask\u00f3lski, D.J., and Bobeff, E.J. (2024). Automated volumetric evaluation of intracranial compartments and cerebrospinal fluid distribution on emergency trauma head CT scans to quantify mass effect. Front. Neurosci., 18.","DOI":"10.3389\/fnins.2024.1341734"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1007\/s11517-016-1483-z","article-title":"3D cerebral MR image segmentation using multiple-classifier system","volume":"55","author":"Amiri","year":"2017","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1109\/42.387715","article-title":"Segmentation of brain parenchyma and cerebrospinal fluid in multispectral magnetic resonance images","volume":"14","author":"Lundervold","year":"1995","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1350","DOI":"10.1016\/j.acra.2010.06.005","article-title":"Automatic segmentation of cerebrospinal fluid, white and gray matter in unenhanced computed tomography images","volume":"17","author":"Gupta","year":"2010","journal-title":"Acad. Radiol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"102559","DOI":"10.1016\/j.artmed.2023.102559","article-title":"Automatic semantic segmentation of the lumbar spine: Clinical applicability in a multi-parametric and multi-center study on magnetic resonance images","volume":"140","author":"Domenech","year":"2023","journal-title":"Artif. Intell. Med."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Liang, S., Liu, H., Chen, C., Qin, C., Yang, F., Feng, Y., and Lin, Z. (2021). Research on multi-path dense networks for MRI spinal segmentation. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0248303"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.1016\/j.neuroimage.2013.07.060","article-title":"Automatic magnetic resonance spinal cord segmentation with topology constraints for variable fields of view","volume":"83","author":"Chen","year":"2013","journal-title":"Neuroimage"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1007\/s12021-024-09661-x","article-title":"Enhanced Spatial Fuzzy C-Means Algorithm for Brain Tissue Segmentation in T1 Images","volume":"22","author":"Jafrasteh","year":"2024","journal-title":"Neuroinformatics"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Fu, J., Chai, J.W., Chen, P.L., Ding, Y.W., and Chen, H.C. (2022). Quantitative Measurement of Spinal Cerebrospinal Fluid by Cascade Artificial Intelligence Models in Patients with Spontaneous Intracranial Hypotension. Biomedicines, 10.","DOI":"10.3390\/biomedicines10082049"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.jocn.2021.05.010","article-title":"Using deep learning convolutional neural networks to automatically perform cerebral aqueduct CSF flow analysis","volume":"90","author":"Tsou","year":"2021","journal-title":"J. Clin. Neurosci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1007\/s10334-006-0030-6","article-title":"Semiautomatic analysis of phase contrast magnetic resonance imaging of cerebrospinal fluid flow through the aqueduct of Sylvius","volume":"19","author":"Moratal","year":"2006","journal-title":"Magma"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Le, R.F.D., Karmonik, C., Regnier-Golanov, A.S., Golanov, E.V., and Britz, G.W. (2025). Quantitative evaluation of normal cerebrospinal fluid flow in Sylvian aqueduct and perivascular spaces of middle cerebral artery and circle of Willis using 2D phase-contrast MRI imaging. Front. Neurosci., 19.","DOI":"10.3389\/fnins.2025.1622351"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1615","DOI":"10.1177\/02841851221125916","article-title":"Influence of the area of the aqueduct and region of interest on quantification of stroke volume in healthy volunteers using phase-contrast cine magnetic resonance imaging","volume":"64","author":"Zhang","year":"2023","journal-title":"Acta. Radiol."},{"key":"ref_25","unstructured":"The MathWorks Inc (MATLAB, 2024). MATLAB, Version: 24.1.0 (R2024a)."},{"key":"ref_26","unstructured":"Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1016\/S0893-6080(00)00026-5","article-title":"Independent component analysis: Algorithms and applications","volume":"13","author":"Oja","year":"2000","journal-title":"Neural Netw."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"934","DOI":"10.1002\/mrm.10455","article-title":"PUBS: Pulsatility-based segmentation of lumens conducting non-steady flow","volume":"49","author":"Alperin","year":"2003","journal-title":"Magn. Reson. Med."},{"key":"ref_29","unstructured":"IBM Corp (IBM SPSS Statistics for Windows, 2012). IBM SPSS Statistics for Windows, Version 21.0."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1136\/jnnp-2023-331166","article-title":"Multidisciplinary consensus guideline for the diagnosis and management of spontaneous intracranial hypotension","volume":"94","author":"Cheema","year":"2023","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"ref_31","first-page":"e41457","article-title":"Recurrent Spontaneous Intracranial Hypotension (SIH) and the Durability of Repeat Epidural Blood Patch (EBP)","volume":"15","author":"Hazama","year":"2023","journal-title":"Cureus"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wang, Y.W., Teng, C.J., Chai, J.W., Wu, C.C., Chen, P.L., and Chen, H.C. (2022). Prediction of Target Epidural Blood Patch Treatment Efficacy in Spontaneous Intracranial Hypotension Using Follow-Up MRI. Diagnostics, 12.","DOI":"10.3390\/diagnostics12051158"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chen, H.C., Chai, J.W., Wu, C.C., Chen, P.L., and Teng, C.L. (2022). Magnetic resonance imaging predicted the therapeutic response of patients with spinal cerebrospinal fluid leakage undergoing targeted epidural blood patch. Br. J. Radiol., 95.","DOI":"10.1259\/bjr.20210841"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3331024221147488","DOI":"10.1177\/03331024221147488","article-title":"The SIH-EBP Score: A grading scale to predict the response to the first epidural blood patch in spontaneous intracranial hypotension","volume":"43","author":"Lin","year":"2023","journal-title":"Cephalalgia"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1097\/JCMA.0000000000001197","article-title":"SIH-EBP score for prediction of efficacy of epidural blood patching in patients with spontaneous intracranial hypotension","volume":"88","author":"Chen","year":"2025","journal-title":"J. Chin. Med. Assoc."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"838","DOI":"10.2214\/AJR.16.16995","article-title":"Phase-Contrast MRI CSF Flow Measurements for the Diagnosis of Normal-Pressure Hydrocephalus: Observer Agreement of Velocity Versus Volume Parameters","volume":"208","author":"Tawfik","year":"2017","journal-title":"AJR Am. J. Roentgenol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1148\/radiol.2332030884","article-title":"Supratentorial Cerebrospinal Fluid Production Rate in Healthy Adults: Quantification with Two-dimensional Cine Phase-Contrast MR Imaging with High Temporal and Spatial Resolution","volume":"233","author":"Huang","year":"2004","journal-title":"Radiology"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1186\/s12987-024-00578-w","article-title":"Phase-contrast MRI analysis of cerebral blood and CSF flow dynamic interactions","volume":"21","author":"Owashi","year":"2024","journal-title":"Fluids Barriers CNS"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"658","DOI":"10.1002\/mrm.27752","article-title":"Assessing test-retest reliability of phase contrast MRI for measuring cerebrospinal fluid and cerebral blood flow dynamics","volume":"82","author":"Sakhare","year":"2019","journal-title":"Magn. Reson. Med."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1007\/s11548-011-0642-9","article-title":"Automated segmentation of blood-flow regions in large thoracic arteries using 3D-cine PC-MRI measurements","volume":"7","author":"Nguyen","year":"2012","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Keles, A., Ozisik, P.A., Algin, O., Celebi, F.V., and Bendechache, M. (2024). Decoding pulsatile patterns of cerebrospinal fluid dynamics through enhancing interpretability in machine learning. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-67928-4"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/18\/2339\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T15:51:16Z","timestamp":1763394676000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/18\/2339"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,15]]},"references-count":41,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["diagnostics15182339"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15182339","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,15]]}}}