TY - JOUR

T1 - Glioblastoma MRI Dataset with Standardized Preprocessing, Expert-Validated Segmentation, and MGMT Profiling

AU - Тучинов, Баир Николаевич

AU - Шакур, Ахсан

AU - Бенедичук, Маргарита Вячеславовна

AU - Филимонова, Елена Андреевна

AU - Рзаев, Джамиль Афет Оглы

AU - Щукина, Мария Игоревна

AU - Лыу, Минь Шао Кхуэ

AU - Leone, Augusto

AU - Carbone, Francesco

AU - Zoli, Matteo

AU - Carretta, Alessandro

AU - Bianconi, Andrea

AU - Cofano, Fabio

AU - Morello, Alberto

AU - Armocida, Daniele

AU - Spetzger, Uwe

AU - Roumia, Safwan

AU - Di Napoli, Veronica

AU - Pio Fochi, Nicola

AU - Lau, Ruth

AU - Internо, Valeria

AU - Giordano, Guido

AU - Curcio, Antonello

AU - Rustici, Arianna

AU - Angileri, Flavio

AU - Mazzatenta, Diego

AU - Signorelli, Francesco

AU - Porta, Camillo

AU - Garbossa, Diego

AU - Colamaria, Antonio

N1 - Filimonova, E., Leone, A., Carbone, F. et al. Glioblastoma MRI Dataset with Standardized Preprocessing, Expert-Validated Segmentation, and MGMT Profiling. Sci Data 13, 1213 (2026). https://doi.org/10.1038/s41597-026-07953-2 This research was supported by a grant for research centers, provided by the Ministry of Economic Development of the Russian Federation in accordance with the subsidy agreement with the Novosibirsk State University dated 17 April 2025 No. 139-15-2025-006: IGK 000000C313925P3S0002

PY - 2026/8/7

Y1 - 2026/8/7

N2 - Glioblastoma research increasingly relies on large, well-curated imaging datasets that combine standardized MRI data, accurate tumor segmentations, and molecular profiling. We constructed a multi-center dataset of preoperative MRI scans from 337 patients with histologically confirmed primary glioblastoma collected across eight hospitals. All cases include T1-weighted (pre- and post-contrast), T2-weighted, and FLAIR sequences. Images underwent systematic quality assessment, BIDS organization, defacing, skull stripping, and linear registration to the MNI152 template. Tumor segmentation was performed using a SegResNet CNN model following the BraTS labeling convention, with all masks reviewed and manually refined by neuroradiologists. MGMT promoter methylation status was determined for all patients. This dataset provides a robust, clinically representative resource for radiomics, deep learning, and radiogenomic research in glioblastoma, supporting concrete downstream tasks including automated segmentation benchmarking (mean Dice = 0.94) and MGMT methylation prediction (baseline ACC = 0.60). Its multi-center origin, comprehensive preprocessing, expert-refined segmentations, and complete MGMT annotations address limitations of existing datasets and support the development and validation of reproducible imaging biomarkers.

AB - Glioblastoma research increasingly relies on large, well-curated imaging datasets that combine standardized MRI data, accurate tumor segmentations, and molecular profiling. We constructed a multi-center dataset of preoperative MRI scans from 337 patients with histologically confirmed primary glioblastoma collected across eight hospitals. All cases include T1-weighted (pre- and post-contrast), T2-weighted, and FLAIR sequences. Images underwent systematic quality assessment, BIDS organization, defacing, skull stripping, and linear registration to the MNI152 template. Tumor segmentation was performed using a SegResNet CNN model following the BraTS labeling convention, with all masks reviewed and manually refined by neuroradiologists. MGMT promoter methylation status was determined for all patients. This dataset provides a robust, clinically representative resource for radiomics, deep learning, and radiogenomic research in glioblastoma, supporting concrete downstream tasks including automated segmentation benchmarking (mean Dice = 0.94) and MGMT methylation prediction (baseline ACC = 0.60). Its multi-center origin, comprehensive preprocessing, expert-refined segmentations, and complete MGMT annotations address limitations of existing datasets and support the development and validation of reproducible imaging biomarkers.

UR - https://www.scopus.com/pages/publications/105047924963

U2 - https://doi.org/10.1038/s41597-026-07953-2

DO - https://doi.org/10.1038/s41597-026-07953-2

M3 - Article

C2 - 42629349

VL - 13

JO - Scientific Data

JF - Scientific Data

SN - 2052-4463

M1 - 1213

ER -