Postoperative timing effects on AI-based resection-cavity segmentation in glioma: multi-site evaluation and relevance assessment
Recent evidence underscores the need for early post-surgical cavity delineation to improve brain tumor treatment. Manual segmentation—the gold standard—is slow and labor-intensive but necessary to link early post-surgical lesions to brain connectivity and functional outcome. Using one of the largest post-operative glioma MRI datasets available to date ( N = 1056), (i) we evaluated the effect of postoperative scan timing on AI-based resection-cavity segmentation; (ii) we investigated whether automated segmentations replicate findings showing that surgery-induced network disconnection severity predicts worse language fluency scores. While the segmentation of chronic cavities yielded accurate results, early postoperative segmentations initially posed challenges due to domain shift. Semi-supervised learning and model fine-tuning overcame this issue, providing preliminary evidence supporting the adoption of AI-driven disconnectomics. We provide a robust AI-driven tool for early postsurgical assessment and functional recovery prediction in neuro-oncological care, showing that the time between surgery and cavity delineation is critical for AI reliability.
Authors
- Alberto Morello (ORCID: https://orcid.org/0009-0004-7114-7787)
- Christian Rubbert (ORCID: https://orcid.org/0000-0002-9461-1173)
- Marion Rapp (ORCID: https://orcid.org/0000-0003-2343-244X)
- Lucía Amoruso (ORCID: https://orcid.org/0000-0003-4696-2187)
- Manuel Carreiras (ORCID: https://orcid.org/0000-0001-6726-7613)
- Luca Zigiotto (ORCID: https://orcid.org/0000-0002-2453-2007)
- Mitsutoshi Nakada (ORCID: https://orcid.org/0000-0001-9419-6101)
- Ludovico Coletta (ORCID: https://orcid.org/0000-0001-8052-5154)
- Paolo Avesani (ORCID: https://orcid.org/0000-0001-8943-8911)
- Diego Garbossa (ORCID: https://orcid.org/0000-0002-2692-7133)
- Iñigo Pomposo (ORCID: https://orcid.org/0000-0002-3095-2649)
- Fabio Cofano (ORCID: https://orcid.org/0000-0002-5100-7478)
- Hugues Duffau (ORCID: https://orcid.org/0000-0002-6558-2342)
- Silvio Sarubbo (ORCID: https://orcid.org/0000-0003-1113-3717)
- Michael S. Sabel (ORCID: https://orcid.org/0000-0001-9215-2914)
- Riho Nakajima (ORCID: https://orcid.org/0000-0002-8274-8922)
- Elena Garro
- Alberto Spolverato
- Naomi Houedjissin
- Laura de Frutos-Sagastuy (ORCID: https://orcid.org/0000-0003-0027-3116)
Institutions
- Kanazawa University (JP)
- Ikerbasque (ES)
- Centre National de la Recherche Scientifique (FR)
- Inserm (FR)
- University of the Basque Country (ES)
- University of Trento (IT)
- Université de Montpellier (FR)
- Fondazione Bruno Kessler (IT)
- Ospedale Santa Chiara (IT)
- Düsseldorf University Hospital (DE)
- BioCruces Health research Institute (ES)
- Centre Hospitalier Universitaire de Montpellier (FR)
- Basque Center on Cognition, Brain and Language (ES)
- Hôpital Gui de Chauliac (FR)
- Hospital de Cruces (ES)
- Institut de Génomique Fonctionnelle (FR)
- Heinrich Heine University Düsseldorf (DE)
- University of Turin (IT)
Publication Details
- Journal
- npj Precision Oncology
- Published
- 2026-11-19
- DOI
- https://doi.org/10.1038/s41698-026-01786-3
- Primary Topic
- Brain Tumor Detection and Classification
- Type
- article
- Field-Weighted Citation Impact
- 0.00