{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:43:43Z","timestamp":1777866223776,"version":"3.51.4"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T00:00:00Z","timestamp":1775174400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:00:00Z","timestamp":1777507200000},"content-version":"vor","delay-in-days":27,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Brain Inf."],"published-print":{"date-parts":[[2026,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>MELD Graph is a state-of-the-art artificial intelligence (AI) model for automated detection of focal cortical dysplasia (FCD), but its performance remains limited, highlighting the need to investigate which aspects of the pipeline affect its accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A retrospective failure-mode analysis of the MELD Graph pipeline was performed in 242 subjects, with model predictions and FreeSurfer segmentations reviewed to classify errors as segmentation-associated or algorithm-related. FCD imaging features salient to humans were quantified, with statistical associations examined for both MELD Graph detection and focal FreeSurfer segmentation failure.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>MELD Graph demonstrated overall performance similar to previously published non-harmonized results, achieving a sensitivity of 69%, specificity of 44%, and positive predictive value (PPV) of 75%. Focal FreeSurfer segmentation failures were associated with 21% of false negative patients, 25% of false positive clusters in patients, and 16% of false positive clusters in controls. Following manual cortical segmentation correction and rerunning of MELD Graph, 67% of the segmentation-associated missed lesions were detected, and segmentation-associated false positive clusters were reduced or eliminated in 75% of controls with such clusters. Higher conspicuity on T1-weighted images was associated with MELD Graph detection, whereas greater conspicuity on T2-FLAIR images relative to T1 was associated with detection failure. Non\u2013bottom-of-sulcus lesion location, higher human conspicuity measures, and low T1 image quality were positively associated with focal FreeSurfer segmentation failures.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>FreeSurfer segmentation failures are a significant potential source of error in the MELD Graph pipeline. FCD imaging features salient to humans and image quality were also associated with variability in algorithm performance. Robust cortical segmentation and stronger integration of T2-FLAIR imaging features may be beneficial for automated FCD detection tools.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Clinical trial registration<\/jats:title>\n                    <jats:p>Not applicable. This study is a retrospective analysis of previously acquired open-source imaging datasets and does not constitute a clinical trial.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s40708-026-00299-w","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:36:49Z","timestamp":1775201809000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pipeline evaluation of a state-of-the-art AI algorithm for detection of focal cortical dysplasia: insights into potential failure sources"],"prefix":"10.1186","volume":"13","author":[{"given":"Mateus A.","family":"Esmeraldo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefanie","family":"Chambers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanniklas","family":"Kravutske","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eduardo P.","family":"Reis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregor","family":"Kasprian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ana Filipa","family":"Geraldo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergios","family":"Gatidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bruno P.","family":"Soares","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,3]]},"reference":[{"issue":"3","key":"299_CR1","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1212\/WNL.0000000000003509","volume":"88","author":"KM Fiest","year":"2017","unstructured":"Fiest KM, Sauro KM, Wiebe S, Patten SB, Kwon CS, Dykeman J et al (2017) Prevalence and incidence of epilepsy: A systematic review and meta-analysis of international studies. Neurology 88(3):296\u2013303. https:\/\/doi.org\/10.1212\/WNL.0000000000003509","journal-title":"Neurology"},{"issue":"4","key":"299_CR2","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1001\/jamaneurol.2024.5406","volume":"82","author":"M Ripart","year":"2025","unstructured":"Ripart M, Spitzer H, Williams LZJ, Walger L, Chen A, Napolitano A et al (2025) Detection of Epileptogenic Focal Cortical Dysplasia Using Graph Neural Networks: A MELD Study. JAMA Neurol 82(4):397. https:\/\/doi.org\/10.1001\/jamaneurol.2024.5406","journal-title":"JAMA Neurol"},{"issue":"5","key":"299_CR3","doi-asserted-by":"publisher","first-page":"1093","DOI":"10.1111\/epi.17522","volume":"64","author":"L Walger","year":"2023","unstructured":"Walger L, Adler S, Wagstyl K, Henschel L, David B, Borger V et al (2023) Artificial intelligence for the detection of focal cortical dysplasia: Challenges in translating algorithms into clinical practice. Epilepsia 64(5):1093\u20131112. https:\/\/doi.org\/10.1111\/epi.17522","journal-title":"Epilepsia"},{"key":"299_CR4","doi-asserted-by":"publisher","unstructured":"Commission on Neurosurgery of the International League Against Epilepsy (ILAE) 1997\u20132001:, Wieser HG, Blume WT, Fish D, Goldensohn E, Hufnagel A, et al. Proposal for a New Classification of Outcome with Respect to Epileptic Seizures Following Epilepsy Surgery. Epilepsia. 2001 Feb 8;42(2):282\u20136. https:\/\/doi.org\/10.1046\/j.1528-1157.2001.35100.x","DOI":"10.1046\/j.1528-1157.2001.35100.x"},{"issue":"10","key":"299_CR5","doi-asserted-by":"publisher","first-page":"2491","DOI":"10.1111\/epi.17350","volume":"63","author":"L Jehi","year":"2022","unstructured":"Jehi L, Jette N, Kwon C, Josephson CB, Burneo JG, Cendes F et al (2022) Timing of referral to evaluate for epilepsy surgery: Expert Consensus Recommendations from the Surgical Therapies Commission of the International League Against Epilepsy. Epilepsia 63(10):2491\u20132506. https:\/\/doi.org\/10.1111\/epi.17350","journal-title":"Epilepsia"},{"key":"299_CR6","doi-asserted-by":"publisher","unstructured":"Walger L, Schmitz MH, Bauer T, K\u00fcgler D, Schuch F, Arendt C et al A public benchmark for human performance in the detection of focal cortical dysplasia. Epilepsia Open 2025 June;10(3):778\u2013786. https:\/\/doi.org\/10.1002\/epi4.70028","DOI":"10.1002\/epi4.70028"},{"key":"299_CR7","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/j.seizure.2024.06.007","volume":"120","author":"YK Takahashi","year":"2024","unstructured":"Takahashi YK, Baba S, Kawashima T, Tachimori H, Iijima K, Kimura Y et al (2024) Treatment odyssey to epilepsy surgery in children with focal cortical dysplasia: Risk factors for delayed surgical intervention. Seizure Eur J Epilepsy 120:5\u201311. https:\/\/doi.org\/10.1016\/j.seizure.2024.06.007","journal-title":"Seizure Eur J Epilepsy"},{"issue":"8","key":"299_CR8","doi-asserted-by":"publisher","first-page":"2791","DOI":"10.1093\/brain\/awae121","volume":"147","author":"MH Eriksson","year":"2024","unstructured":"Eriksson MH, Prentice F, Piper RJ, Wagstyl K, Adler S, Chari A et al (2024) Long-term neuropsychological trajectories in children with epilepsy: does surgery halt decline? Brain 147(8):2791\u20132802. https:\/\/doi.org\/10.1093\/brain\/awae121","journal-title":"Brain"},{"key":"299_CR9","doi-asserted-by":"publisher","unstructured":"Dashtkoohi M, Ghadimi DJ, Moodi F, Behrang N, Khormali E, Salari HM et al (2025 June) Focal cortical dysplasia detection by artificial intelligence using MRI: A systematic review and meta-analysis. Epilepsy Behav 167:110403. https:\/\/doi.org\/10.1016\/j.yebeh.2025.110403","DOI":"10.1016\/j.yebeh.2025.110403"},{"key":"299_CR10","unstructured":"Ripart M, Spitzer H, Adler S, Wagstyl K MELD Graph: MELD classifier documentation. https:\/\/meld-graph.readthedocs.io\/en\/latest\/index.html. Accessed 18 Nov 2025"},{"key":"299_CR11","doi-asserted-by":"publisher","unstructured":"Schuch F, Walger L, Schmitz M, David B, Bauer T, Harms A et al An open presurgery MRI dataset of people with epilepsy and focal cortical dysplasia type II. Sci Data 2023 July 20;10(1):475. https:\/\/doi.org\/10.1038\/s41597-023-02386-7","DOI":"10.1038\/s41597-023-02386-7"},{"issue":"2","key":"299_CR12","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1111\/epi.18192","volume":"66","author":"PN Taylor","year":"2025","unstructured":"Taylor PN, Wang Y, Simpson C, Janiukstyte V, Horsley J, Leiberg K et al (2025) The Imaging Database for Epilepsy And Surgery (IDEAS). Epilepsia 66(2):471\u2013481. https:\/\/doi.org\/10.1111\/epi.18192","journal-title":"Epilepsia"},{"issue":"2","key":"299_CR13","doi-asserted-by":"publisher","first-page":"774","DOI":"10.1016\/j.neuroimage.2012.01.021","volume":"62","author":"B Fischl","year":"2012","unstructured":"Fischl B, FreeSurfer (2012) NeuroImage 62(2):774\u2013781. https:\/\/doi.org\/10.1016\/j.neuroimage.2012.01.021","journal-title":"NeuroImage"},{"key":"299_CR14","unstructured":"MELD Project MELD classifier using geometric deep learning. https:\/\/github.com\/MELDProject\/meld_graph. Accessed 28 Aug 2025"},{"issue":"11","key":"299_CR15","doi-asserted-by":"publisher","first-page":"3859","DOI":"10.1093\/brain\/awac224","volume":"145","author":"H Spitzer","year":"2022","unstructured":"Spitzer H, Ripart M, Whitaker K, D\u2019Arco F, Mankad K, Chen AA et al (2022) Interpretable surface-based detection of focal cortical dysplasias: a Multi-centre Epilepsy Lesion Detection study. Brain 145(11):3859\u20133871. https:\/\/doi.org\/10.1093\/brain\/awac224","journal-title":"Brain"},{"key":"299_CR16","doi-asserted-by":"publisher","first-page":"120306","DOI":"10.1016\/j.neuroimage.2023.120306","volume":"279","author":"V Vahermaa","year":"2023","unstructured":"Vahermaa V, Aydogan DB, Raij T, Armio RL, Laurikainen H, Saram\u00e4ki J et al (2023) FreeSurfer 7 quality control: Key problem areas and importance of manual corrections. NeuroImage 279:120306. https:\/\/doi.org\/10.1016\/j.neuroimage.2023.120306","journal-title":"NeuroImage"},{"issue":"4","key":"299_CR17","doi-asserted-by":"publisher","first-page":"1264","DOI":"10.1093\/brain\/awad379","volume":"147","author":"E Macdonald-Laurs","year":"2024","unstructured":"Macdonald-Laurs E, Warren AEL, Francis P, Mandelstam SA, Lee WS, Coleman M et al (2024) The clinical, imaging, pathological and genetic landscape of bottom-of-sulcus dysplasia. Brain 147(4):1264\u20131277. https:\/\/doi.org\/10.1093\/brain\/awad379","journal-title":"Brain"},{"issue":"8","key":"299_CR18","doi-asserted-by":"publisher","first-page":"1899","DOI":"10.1111\/epi.17301","volume":"63","author":"I Najm","year":"2022","unstructured":"Najm I, Lal D, Alonso Vanegas M, Cendes F, Lopes-Cendes I, Palmini A et al (2022) The ILAE consensus classification of focal cortical dysplasia: an update proposed by an ad hoc task force of the ILAE diagnostic methods commission. Epilepsia 63(8):1899\u20131919. https:\/\/doi.org\/10.1111\/epi.17301","journal-title":"Epilepsia"},{"issue":"6","key":"299_CR19","doi-asserted-by":"publisher","first-page":"3070","DOI":"10.1007\/s00330-024-11195-4","volume":"35","author":"A Santonocito","year":"2024","unstructured":"Santonocito A, Zarcaro C, Zeitouni L, Ferrara F, Kapetas P, Helbich TH et al (2024) A head-to-head comparison of breast lesion\u2019s conspicuity at contrast-enhanced mammography and contrast-enhanced MRI. Eur Radiol 35(6):3070\u20133079. https:\/\/doi.org\/10.1007\/s00330-024-11195-4","journal-title":"Eur Radiol"},{"key":"299_CR20","doi-asserted-by":"publisher","first-page":"IMAG","DOI":"10.1162\/IMAG.a.4","volume":"3","author":"G Bhalerao","year":"2025","unstructured":"Bhalerao G, Gillis G, Dembele M, Suri S, Ebmeier K, Klein J et al (2025) Automated quality control of T1-weighted brain MRI scans for clinical research datasets: methods comparison and design of a quality prediction classifier. Imaging Neurosci IMAG.a.4","journal-title":"Imaging Neurosci"},{"issue":"4","key":"299_CR21","doi-asserted-by":"publisher","first-page":"1165","DOI":"10.1111\/epi.18240","volume":"66","author":"LN Kersting","year":"2025","unstructured":"Kersting LN, Walger L, Bauer T, Gnatkovsky V, Schuch F, David B et al (2025) Detection of focal cortical dysplasia: development and multicentric evaluation of artificial intelligence models. Epilepsia 66(4):1165\u20131176. https:\/\/doi.org\/10.1111\/epi.18240","journal-title":"Epilepsia"},{"issue":"1","key":"299_CR22","doi-asserted-by":"publisher","first-page":"2837","DOI":"10.1038\/s41598-020-57951-6","volume":"10","author":"SN Yaakub","year":"2020","unstructured":"Yaakub SN, Heckemann RA, Keller SS, McGinnity CJ, Weber B, Hammers A (2020) On brain atlas choice and automatic segmentation methods: a comparison of MAPER & FreeSurfer using three atlas databases. Sci Rep 10(1):2837. https:\/\/doi.org\/10.1038\/s41598-020-57951-6","journal-title":"Sci Rep"},{"issue":"3","key":"299_CR23","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/s00234-021-02865-x","volume":"64","author":"H Urbach","year":"2022","unstructured":"Urbach H, Kellner E, Kremers N, Bl\u00fcmcke I, Demerath T (2022) MRI of focal cortical dysplasia. Neuroradiology 64(3):443\u2013452. https:\/\/doi.org\/10.1007\/s00234-021-02865-x","journal-title":"Neuroradiology"},{"issue":"4","key":"299_CR24","doi-asserted-by":"publisher","first-page":"742","DOI":"10.3174\/ajnr.A8544","volume":"46","author":"Y Wei","year":"2025","unstructured":"Wei Y, Jagtap JM, Singh Y, Khosravi B, Cai J, Gunter JL et al (2025) Comprehensive segmentation of gray matter structures on T1-weighted brain MRI: a comparative study of convolutional neural network, convolutional neural network hybrid-transformer or -mamba architectures. Am J Neuroradiol 46(4):742\u2013749. https:\/\/doi.org\/10.3174\/ajnr.A8544","journal-title":"Am J Neuroradiol"}],"container-title":["Brain Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40708-026-00299-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40708-026-00299-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40708-026-00299-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T08:15:00Z","timestamp":1777536900000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s40708-026-00299-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,3]]},"references-count":24,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["299"],"URL":"https:\/\/doi.org\/10.1186\/s40708-026-00299-w","relation":{},"ISSN":["2198-4018","2198-4026"],"issn-type":[{"value":"2198-4018","type":"print"},{"value":"2198-4026","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,3]]},"assertion":[{"value":"18 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 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":"Not applicable. All imaging data were previously collected under ethical approvals by the original dataset providers and released in accordance with their respective consent procedures [\n                      \n                      ,\n                      \n                      ]. This study used only fully de-identified, publicly accessible data and did not involve prospective data collection or interaction with human participants [\n                      \n                      ,\n                      \n                      ]. According to institutional and national guidelines, Institutional Review Board (IRB) approval was not required.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"We confirm that we have read the\n                      Brain Informatics\n                      journal\u2019s position on ethical publication and affirm that this manuscript complies with those guidelines.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable. This study analyzed de-identified, publicly released data [\n                      \n                      ,\n                      \n                      ] and involved no direct patient contact.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"No copyrighted or previously published material requiring permission for reproduction was used in this manuscript. All figures and analyses are original and based on publicly available datasets [\n                      \n                      ,\n                      \n                      ].","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Permission to reproduce material from other sources"}}],"article-number":"13"}}