Publication:
Deep learning-based postoperative glioblastoma segmentation and extent of resection evaluation: development, external validation, and model comparison

Simple item page
dc.contributor.authorCepeda, Santiago
dc.contributor.authorRomero, Roberto
dc.contributor.authorLuque, Lidia
dc.contributor.authorGarcía Pérez, Daniel
dc.contributor.authorBlasco, Guillermo
dc.contributor.authorTommaso Luppino, Luigi
dc.contributor.authorKuttner, Samuel
dc.contributor.authorEstéban-Sinovas, Olga
dc.contributor.authorArrese, Ignacio
dc.contributor.authorSolheim, Ole
dc.contributor.authorEikenes, Live
dc.contributor.authorKarlberg, Anna
dc.contributor.authorPérez-Núñez, Ángel
dc.contributor.authorZanier, Olivier
dc.contributor.authorSerra, Carlo
dc.contributor.authorStaartjes, Victor E.
dc.contributor.authorBianconi, Andrea
dc.contributor.authorRossi, Luca Francesco
dc.contributor.authorGarbossa, Diego
dc.contributor.authorEscudero, Trinidad
dc.contributor.authorHornero, Roberto
dc.contributor.authorSarabia, Rosario
dc.contributor.departmentFarmacología
dc.contributor.otherFarmacia
dc.date.accessioned2026-02-24T08:54:28Z
dc.date.available2026-02-24T08:54:28Z
dc.date.copyright© 2024 The Author(s)
dc.date.issued2024-11-16
dc.description.abstractBackground: The pursuit of automated methods to assess the extent of resection (EOR) in glioblastomas is challenging, requiring precise measurement of residual tumor volume. Many algorithms focus on preoperative scans, making them unsuitable for postoperative studies. Our objective was to develop a deep learning-based model for postoperative segmentation using magnetic resonance imaging (MRI). We also compared our model’s performance with other available algorithms. Methods: To develop the segmentation model, a training cohort from 3 research institutions and 3 public databases was used. Multiparametric MRI scans with ground truth labels for contrast-enhancing tumor (ET), edema, and surgical cavity, served as training data. The models were trained using MONAI and nnU-Net frameworks. Comparisons were made with currently available segmentation models using an external cohort from a research institution and a public database. Additionally, the model’s ability to classify EOR was evaluated using the RANO-Resect classification system. To further validate our best-trained model, an additional independent cohort was used. Results: The study included 586 scans: 395 for model training, 52 for model comparison, and 139 scans for independent validation. The nnU-Net framework produced the best model with median Dice scores of 0.81 for contrast ET, 0.77 for edema, and 0.81 for surgical cavities. Our best-trained model classified patients into maximal and submaximal resection categories with 96% accuracy in the model comparison dataset and 84% in the independent validation cohort. Conclusions: Our nnU-Net-based model outperformed other algorithms in both segmentation and EOR classification tasks, providing a freely accessible tool with promising clinical applicability.
dc.formatapplication/pdf
dc.format.extent12
dc.identifier.citationCepeda S, Romero R, Luque L, García-Pérez D, Blasco G, Luppino LT, Kuttner S, Esteban-Sinovas O, Arrese I, Solheim O, Eikenes L, Karlberg A, Pérez-Núñez Á, Zanier O, Serra C, Staartjes VE, Bianconi A, Rossi LF, Garbossa D, Escudero T, Hornero R, Sarabia R. Deep learning-based postoperative glioblastoma segmentation and extent of resection evaluation: Development, external validation, and model comparison. Neurooncol Adv. 2024 Nov 16;6(1):vdae199. doi: 10.1093/noajnl/vdae199
dc.identifier.doihttps://doi.org/10.1093/noajnl/vdae199
dc.identifier.eissn2632-2498
dc.identifier.urihttp://hdl.handle.net/10201/211561
dc.languageeng
dc.publisherOxford University Press
dc.relationThis work was partially funded by a grant awarded by the “Instituto Carlos III, Proyectos I-D-i, Acción Estratégica en Salud 2022,” under the project titled “Prediction of tumor recurrence in glioblastomas using magnetic resonance imaging, machine learning, and transcriptomic analysis: A supratotal resection guided by artificial intelligence,” reference PI22/01680.
dc.relation.publisherversionhttps://academic.oup.com/noa/article/6/1/vdae199/7902176
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.accessRightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectGlioblastomas
dc.subjectNeural network
dc.subjectPostoperative
dc.subjectSegmentation
dc.subjectDeep learning
dc.subject.odsNo relacionado con ningún objetivo de desarrollo sostenible
dc.titleDeep learning-based postoperative glioblastoma segmentation and extent of resection evaluation: development, external validation, and model comparison
dc.typeinfo:eu-repo/semantics/article
dc.type.versioninfo:eu-repo/semantics/publishedVersion
dspace.entity.typePublicationes
relation.isAuthorOfPublication2f2500a1-1b27-4420-820c-db8c16e79afd
relation.isAuthorOfPublication.latestForDiscovery2f2500a1-1b27-4420-820c-db8c16e79afd
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
31 Deep learning-based postoperative glioblastoma segmentation and extent of resection evaluation Development, external validation, and model comparison.pdf
Size:
711.23 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.37 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Artículos