{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T06:01:11Z","timestamp":1772517671996,"version":"3.50.1"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T00:00:00Z","timestamp":1772496000000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Trigeminal neuralgia (TN) is a severe neuropathic pain disorder traditionally attributed to neurovascular compression. However, emerging evidence suggests that non-vascular anatomical variations of the prepontine cistern may significantly contribute to disease susceptibility.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To quantify non-vascular morphometric features of the trigeminal nerve and adjacent cistern and evaluate their discriminative value using a leakage-free, machine-learning-based MRI pipeline.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We retrospectively analyzed 131 participants (71 with idiopathic TN (iTN) and 60 controls) who were imaged with temporal MRI. Two neuroradiologists independently assessed the neurovascular conflict status, achieving inter-rater agreement of 97% (\n                      <jats:italic>\u03ba<\/jats:italic>\n                      \u202f=\u202f0.91). Measured parameters included trigeminal nerve thickness (root and porus trigeminus level), Meckel cave area (axial and coronal plane) and height (sagittal plane), cisternal length (Mean), cisternopontine angle, sagittal angle, and trigeminoclival angle. Model selection employed nested, paired splits across 20 outer repetitions with Optuna-based tuning; average precision (PR-AUC) was the optimization target. Six classifier families (Random Forest, SVM, MLP, XGBoost, KNN, Bagging) were evaluated; SHAP and LIME were applied\n                      <jats:italic>post-hoc<\/jats:italic>\n                      for interpretability.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      TN showed thinner nerve diameters (particularly at the porus), larger Meckel cave areas (axial and coronal) and height, smaller sagittal angles, and shorter cisternal length; several of these differences remained significant after multiple-comparison control (e.g., porus diameters and Meckel cave areas, Holm-adjusted\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.01; sagittal angle, Holm\n                      <jats:italic>p<\/jats:italic>\n                      \u202f=\u202f0.0092). On held-out test sets, discrimination was consistently high: for SVM, PR-AUC was 86.16\u202f\u00b1\u202f4.39% and ROC-AUC was 87.40\u202f\u00b1\u202f4.52%; the other models clustered closely around ROC-AUC (\u22480.85\u20130.87). Friedman testing demonstrated a global difference on\n                      <jats:italic>F<\/jats:italic>\n                      <jats:sub>1<\/jats:sub>\n                      across models;\n                      <jats:italic>post-hoc<\/jats:italic>\n                      Wilcoxon\u2013Holm confirmed that only Random Forest exceeded KNN, while RF, SVM, and XGBoost did not differ pairwise on\n                      <jats:italic>F<\/jats:italic>\n                      <jats:sub>1<\/jats:sub>\n                      or ROC AUC. SHAP\/LIME prioritized porus-level diameters and Meckel cave measures as leading contributors, aligning with groupwise morphometric shifts.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Non-vascular morphometric variation in the prepontine cistern, particularly at the porus level nerve caliber, Meckel cave size, and sagittal angle, contributes to TN pathophysiology. An AI-assisted, leakage-free morphometry pipeline yields reproducible and interpretable discrimination, supporting the integration of vascular and non-vascular anatomy into diagnostic and treatment planning workflows.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1745815","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T05:23:47Z","timestamp":1772515427000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A comprehensive evaluation of non-vascular prepontine cistern anatomy influencing trigeminal nerve vulnerability using machine learning-based morphometric analysis"],"prefix":"10.3389","volume":"13","author":[{"given":"Ak\u00e7ay \u00d6v\u00fcn\u00e7","family":"Karada\u015f","sequence":"first","affiliation":[{"name":"Private Clinic","place":["Ankara, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gokalp","family":"Tulum","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Istanbul Topkapi University","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"\u00d6mer","family":"Karada\u015f","sequence":"additional","affiliation":[{"name":"Department of Neurology, Gulhane Training and Research Hospital, Health Science University","place":["Ankara, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammet \u0130kbal","family":"I\u015f\u0131k","sequence":"additional","affiliation":[{"name":"Department of Radiology, Gulhane Training and Research Hospital, Health Science University","place":["Ankara, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ferhat","family":"C\u00fcce","sequence":"additional","affiliation":[{"name":"Department of Radiology, Gulhane Training and Research Hospital, Health Science University","place":["Ankara, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Onur","family":"Osman","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Istanbul Topkapi University","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zehra","family":"\u015eim\u015fek","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Istanbul Topkapi University","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Necibe Sare","family":"Mert","sequence":"additional","affiliation":[{"name":"Department of Information Systems Engineering, Istanbul Topkapi University","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Niray","family":"Ba\u015f","sequence":"additional","affiliation":[{"name":"Department of Neurology, Gulhane Training and Research Hospital, Health Science University","place":["Ankara, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Berza","family":"\u00d6zcan","sequence":"additional","affiliation":[{"name":"Department of Neurology, Gulhane Training and Research Hospital, Health Science University","place":["Ankara, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tuba Baldan","family":"A\u011fao\u011flu","sequence":"additional","affiliation":[{"name":"Department of Neurology, Gulhane Training and Research Hospital, Health Science University","place":["Ankara, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,3]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1097\/j.pain.0000000000001435","article-title":"The IASP classification of chronic pain for ICD-11: chronic secondary headache or orofacial pain","volume":"160","author":"Benoliel","year":"2019","journal-title":"Pain"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s10143-004-0372-3","article-title":"Is preoperative high-resolution magnetic resonance imaging accurate in predicting neurovascular compression in patients with trigeminal neuralgia?","volume":"28","author":"Benes","year":"2005","journal-title":"Neurosurg Rev"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1555","DOI":"10.1016\/j.jocn.2009.02.028","article-title":"Enhanced three-dimensional fast spoiled gradient recalled MRI combined with magnetic resonance angiography for preoperative assessment of patients with trigeminal neuralgia","volume":"16","author":"Ni","year":"2009","journal-title":"J Clin Neurosci"},{"key":"ref4","first-page":"8640","article-title":"Radiomics analysis of unaffected side changes in classic trigeminal neuralgia","volume":"14","author":"Pan","year":"2022","journal-title":"Am J Transl Res"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"2505","DOI":"10.1007\/s00701-019-04099-6","article-title":"Correlations between the trigeminal nerve microstructural changes and the trigeminal-pontine angle features","volume":"161","author":"Pang","year":"2019","journal-title":"Acta Neurochir"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1048","DOI":"10.3171\/2014.1.JNS131410","article-title":"Trigeminal neuralgia occurs and recurs in the absence of neurovascular compression","volume":"120","author":"Lee","year":"2014","journal-title":"J Neurosurg"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1016\/j.ejrad.2007.10.010","article-title":"A single-blinded pilot study assessing neurovascular contact using high-resolution MR imaging in patients with trigeminal neuralgia","volume":"69","author":"Chun-Cheng","year":"2009","journal-title":"Eur J Radiol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1002\/ar.23818","article-title":"Neurovascular relations of the trigeminal nerve in asymptomatic individuals studied with high-resolution three-dimensional magnetic resonance imaging","volume":"302","author":"Ruiz-Juretschke","year":"2019","journal-title":"Anat Rec"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"E800","DOI":"10.1093\/neuros\/nyz309","article-title":"In reply: the spectrum of trigeminal neuralgia without neurovascular compression","volume":"85","author":"Magown","year":"2019","journal-title":"Neurosurgery"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1610","DOI":"10.3174\/ajnr.A7205","article-title":"Absence of Meckel cave: a rare cause of trigeminal neuralgia","volume":"42","author":"Jain","year":"2021","journal-title":"AJNR Am J Neuroradiol"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1007\/s10143-023-02221-y","article-title":"Association between morphological characteristics of Meckel\u2019s cave and outcomes after percutaneous balloon compression for primary trigeminal neuralgia","volume":"46","author":"Li","year":"2023","journal-title":"Neurosurg Rev"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1016\/j.wneu.2017.05.057","article-title":"Nerve atrophy and a small trigeminal pontine angle in primary trigeminal neuralgia: a morphometric magnetic resonance imaging study","volume":"104","author":"Cheng","year":"2017","journal-title":"World Neurosurg"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1007\/s00701-012-1327-z","article-title":"Patients with idiopathic trigeminal neuralgia have a sharper-than-normal trigeminal-pontine angle and trigeminal nerve atrophy","volume":"154","author":"Ha","year":"2012","journal-title":"Acta Neurochir"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"631","DOI":"10.3171\/2018.9.JNS181768","article-title":"Sex-dependent posterior fossa anatomical differences in trigeminal neuralgia patients with and without neurovascular compression: a volumetric MRI age- and sex-matched case-control study","volume":"132","author":"Hardaway","year":"2019","journal-title":"J Neurosurg"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.55730\/1300-0144.5503","article-title":"Morphometric examination of trigeminal nerve and its adjacent structures in patients with trigeminal neuralgia: a case-control study","volume":"52","author":"Kundak\u00e7\u0131","year":"2022","journal-title":"Turk J Med Sci"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1460","DOI":"10.3174\/ajnr.A7634","article-title":"Sagittal angle of the trigeminal nerve at the porus trigeminus: a novel measurement to distinguish different causes of classic trigeminal neuralgia","volume":"43","author":"Branstetter","year":"2022","journal-title":"AJNR Am J Neuroradiol"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1707588","DOI":"10.3389\/fmed.2025.1707588","article-title":"Potential of AI-based diagnostic grading system for knee osteoarthritis","volume":"12","author":"Shahid","year":"2025","journal-title":"Front Med"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/10255842.2025.2530645","article-title":"Sequence-similarity-based approach to SARS-CoV-2 genome sequence and lung cancer-related genes via multivariate feature extraction method","volume":"11","author":"\u00c7evik","year":"2025","journal-title":"Comput Methods Biomech Biomed Eng"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"20220758","DOI":"10.1259\/bjr.20220758","article-title":"Radiomics method in the differential diagnosis of diabetic foot osteomyelitis and Charcot neuroarthropathy","volume":"96","author":"Cuce","year":"2023","journal-title":"Br J Radiol"},{"key":"ref20","first-page":"2623","article-title":"Optuna: a next-generation hyperparameter optimization framework","author":"Akiba","year":"2019"},{"key":"ref21","volume-title":"Statistical methods for research workers","author":"Fisher","year":"1925"},{"key":"ref22","first-page":"2546","article-title":"Algorithms for hyper-parameter optimization","author":"Bergstra","year":"2011"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.5555\/1953048.2078195","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref24","first-page":"233","article-title":"The relationship between precision-recall and ROC curves","author":"Davis","year":"2006"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5555\/1248547.1248548","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"Dem\u0161ar","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref26","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"ref27","first-page":"1135","article-title":"Why should I trust you?: Explaining the predictions of any classifier","author":"Ribeiro","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"31","DOI":"10.4103\/JASI.JASI_38_19","article-title":"Morphometric evaluation of trigeminal nerve and Meckel cave with 3.0 magnetic resonance imaging","volume":"69","author":"Sen","year":"2020","journal-title":"J Anat Soc India"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1745815\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T05:23:49Z","timestamp":1772515429000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1745815\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,3]]},"references-count":28,"alternative-id":["10.3389\/fmed.2026.1745815"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1745815","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,3]]},"article-number":"1745815"}}