<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

Automated segmentation of postsurgical resection cavities on magnetic resonance imaging in focal epilepsy: A Multicentre Epilepsy Lesion Detection study

dc.contributor.authorSeo, Jieun
dc.contributor.authorRipart, Mathilde
dc.contributor.authorKaas, Helene
dc.contributor.authorKronlage, Cornelius
dc.contributor.authorSinclair, Ben
dc.contributor.authorVivash, Lucy
dc.contributor.authorCourtney, Merran R.
dc.contributor.authorO'Brien, Terence J.
dc.contributor.authorGopinath, Siby
dc.contributor.authorParasuram, Harilal
dc.contributor.authorKandemirli, Sedat
dc.contributor.authorAlarab, Natally
dc.contributor.authorLai, Lillian
dc.contributor.authorLikeman, Marcus
dc.contributor.authorZhang, Kai
dc.contributor.authorMo, Jiajie
dc.contributor.authorCiobotaru, Georgian
dc.contributor.authorGalea, James
dc.contributor.authorSequeiros-Peggs, Philip
dc.contributor.authorHamandi, Khalid
dc.contributor.authorXie, Hua
dc.contributor.authorIllapani, Venkata Sita Priyanka
dc.contributor.authorGaillard, William D.
dc.contributor.authorCohen, Nathan T.
dc.contributor.authorWeil, Alexander G.
dc.contributor.authorHenrichon-Goulet, Florence
dc.contributor.authorLahlou, Kenza S.
dc.contributor.authorHadjinicolaou, Aristides
dc.contributor.authorIbáñez, Agustín
dc.contributor.authorRojas-Costa, Gonzalo M.
dc.contributor.authorUrbach, Horst
dc.contributor.authorBücheler, Lara
dc.contributor.authorHeers, Marcel
dc.contributor.authorValls Carbó, Adrián
dc.contributor.authorToledano, Rafael
dc.contributor.authorNobile, Giulia
dc.contributor.authorParodi, Costanza
dc.contributor.authorTortora, Domenico
dc.contributor.authorConsales, Alessandro
dc.contributor.authorRiva, Antonella
dc.contributor.authorSeverino, Mariasavina
dc.contributor.authorTisdall, Martin
dc.contributor.authorD'Arco, Felice
dc.contributor.authorMankad, Kshitij
dc.contributor.authorChari, Aswin
dc.contributor.authorEriksson, Maria H.
dc.contributor.authorPiper, Rory J.
dc.contributor.authorCross, J. Helen
dc.contributor.authorBaldeweg, Torsten
dc.contributor.authorGonzález-Ortiz, Sofia
dc.contributor.authorPariente, Jose
dc.contributor.authorBargalló, Nuria
dc.contributor.authorLiu, Yawu
dc.contributor.authorKälviäinen, Reetta
dc.contributor.authorBarba, Carmen
dc.contributor.authorLenge, Matteo
dc.contributor.authorGuerrini, Renzo
dc.contributor.authorIwasaki, Masaki
dc.contributor.authorSone, Daichi
dc.contributor.authorMaki, Hiroyuki
dc.contributor.authorImokawa, Tomoki
dc.contributor.authorSato, Noriko
dc.contributor.authorJung, Julien
dc.contributor.authorSepulveda, Francisco
dc.contributor.authorMansilla, Daniel
dc.contributor.authorGoycoolea, Andres
dc.contributor.authorLopez, Ingeborg
dc.contributor.authorNapolitano, Antonio
dc.contributor.authorDe Benedictis, Alessandro
dc.contributor.authorDe Palma, Luca
dc.contributor.authorRossi-Espagnet, Maria Camilla
dc.contributor.authorKondylidis, Nikolaos
dc.contributor.authorGkiatis, Kostakis
dc.contributor.authorGarganis, Kyriakos
dc.contributor.authorPepper, Joshua
dc.contributor.authorSeri, Stefano
dc.contributor.authorDuncan, John S.
dc.contributor.authorYasuda, Clarissa L.
dc.contributor.authorScárdua-Silva, Lucas
dc.contributor.authorAlvim, Marina K. M.
dc.contributor.authorCendes, Fernando
dc.contributor.authorGennari, Antonio G.
dc.contributor.authorO'Gorman Tuura, Ruth
dc.contributor.authorRamantani, Georgia
dc.contributor.authorJosyula, Mariam
dc.contributor.authorStein, Joel
dc.contributor.authorSinha, Nishant
dc.contributor.authorDavis, Kate
dc.contributor.authorHogan, R. Edward
dc.contributor.authorMaccotta, Luigi
dc.contributor.authorAdler, Sophie
dc.contributor.authorWagstyl, Konrad
dc.date.accessioned2026-11-16T16:06:22Z
dc.date.issued2026-08-04
dc.description.abstractObjective: Quantitative assessment of extent of tissue resection following epilepsy surgery requires accurate delineation of the resection cavity on postoperative magnetic resonance imaging (MRI). Current methods for resection cavity masking are time-consuming and labor-intensive, and existing automated approaches exhibit variable segmentation accuracy, particularly on extratemporal resections. We developed MELD-PostOp, a deep learning tool trained and evaluated on a large, heterogeneous cohort to automatically segment resection cavities. Methods: The study included 1.5-and 3T postoperative three-dimensional T1-weighted MRI images from the Multicentre Epilepsy Lesion Detection (MELD) project (nsubjects = 969, 27 centers) and from the EPISURG dataset (n = 133). The cohort included children and adults, alongside a range of resection locations, pathologies, and MRI characteristics. Resection cavities were individually segmented in 285 subjects and used to train an nnU-Net prototype model. The prototype model was used to generate an additional 680 resection masks, which were subsequently quality-controlled, edited, and combined with the original 285 to train the final MELD-PostOp model (n = 965). A Stratified Test Cohort (n = 50) and Independent Test Cohort (n = 87) were withheld for model evaluation. Performance was evaluated using Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), number of predicted clusters, and inference runtime, and compared against established tools (Epic-CHOP, ResectVol, and RESSEG). Results: MELD-PostOp achieved a median DSC of .85 and HD95 of 3.61 on the combined test cohort, outperforming Epic-CHOP (DSC .69, HD95 9.67), ResectVol (DSC .66, HD95 15.05), and RESSEG (DSC .43, HD95 32.67), with significant improvements seen in both temporal and especially extratemporal resections. The model detected 98.5% (135/137) of resection cavities. MELD-PostOp runtime was 17 s per MRI, compared to 612 s (ResectVol), 3205 s (Epic-CHOP), and 4 s (RESSEG). MELD-PostOp performance remained high across clinical and imaging subgroups (median DSC > .8). Significance: MELD-PostOp is an open-source research tool that provides an accurate, efficient, and generalizable solution for postoperative resection cavity segmentation using only postoperative MRI scans.
dc.identifier.citationEpilepsia. Vol. 67, N° 11 (2026) pp. 5901-5918
dc.identifier.doihttps://doi.org/10.1002/epi.70450
dc.identifier.issn1528-1167
dc.identifier.urihttps://hdl.handle.net/20.500.12254/7827
dc.language.isoen
dc.publisherWiley Periodicals LLC
dc.rightsAtribución-NoComercial-CompartirIgual 3.0 Chile (CC BY-NC-SA 3.0 CL)
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/cl/
dc.subjectartificial intelligence
dc.subjectepilepsy surgery
dc.subjectfocal epilepsy
dc.subjectMRI
dc.subjectsegmentatio
dc.titleAutomated segmentation of postsurgical resection cavities on magnetic resonance imaging in focal epilepsy: A Multicentre Epilepsy Lesion Detection study
dc.title.alternativehttps://orcid.org/0000-0002-6228-2678
dc.typeArtículo

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
Epilepsia - 2026 - Seo - Automated segmentation of postsurgical resection cavities on magnetic resonance imaging in focal (1).pdf
Tamaño:
2,67 MB
Formato:
Adobe Portable Document Format