CFB-GBM v2.0: An Augmented Longitudinal Dataset for Multi-Modal Glioblastoma Segmentation, Radiomics, and RANO Progression Tracking

Leclerq, Alexandre G.; Moreau, Noémie N.; Audebert, Hugo; Nassar, Andros; Cochin, Thomas; Leleu, Thomas; Le Henaff, Loı̈c; Desmonts, Alexis; Poirier, Yoann; Dubru, Aurélie; Guillemette, Laura; Lecoeur, Pascal; Lemasson, Kévin; Jaudet, Cyril; Bougleux, Sébastien; Hérault, Romain; Brunaud, Carole; Valable, Samuel; Stefan, Dinu; Raboutet, Charlotte; Batalla, Alain; Lacroix, Joëlle; Rouzier, Roman; Corroyer-Dulmont, Aurélien

doi:https://doi.org/10.59275/j.melba.2026-dd48

CFB-GBM v2.0: An Augmented Longitudinal Dataset for Multi-Modal Glioblastoma Segmentation, Radiomics, and RANO Progression Tracking

Alexandre G. Leclerq^1,2,3, Noémie N. Moreau^1,2, Hugo Audebert⁴, Andros Nassar⁴, Thomas Cochin^2,4, Thomas Leleu^2,4, Loı̈c Le Henaff^2,5, Alexis Desmonts^1,2,6, Yoann Poirier⁵, Aurélie Dubru⁵, Laura Guillemette⁶, Pascal Lecoeur⁶, Kévin Lemasson⁶, Cyril Jaudet⁶, Sébastien Bougleux³, Romain Hérault³, Carole Brunaud², Samuel Valable², Dinu Stefan⁴, Charlotte Raboutet^2,5, Alain Batalla⁶, Joëlle Lacroix⁵, Roman Rouzier⁷, Aurélien Corroyer-Dulmont^1,2,6

1: Artificial Intelligence Department, Centre François Baclesse, 14000 Caen, France, 2: Université de Caen Normandie, CNRS, Normandie Univ, ISTCT UMR6030, CYCERON, F-14000 Caen, France, 3: Université Caen Normandie, ENSICAEN, CNRS, Normandie Univ, GREYC UMR 6072, F-14000 Caen, France, 4: Radiation Oncology Department, Centre François Baclesse, 14000 Caen, France, 5: Radiology Department, Centre François Baclesse, 14000 Caen, France, 6: Medical Physics Department, Centre François Baclesse, 14000 Caen, France, 7: Surgery Department, Centre François Baclesse, 14000 Caen, France

Publication date: 2026/09/21

https://doi.org/10.59275/j.melba.2026-dd48

PDF · Dataset

Abstract

Glioblastoma (GBM) is the most aggressive primary brain tumor in adults, with a median overall survival of 15 months. Longitudinal, multi-modal imaging datasets with comprehensive clinical and treatment data are essential to support the development of reproducible computational methods for treatment response prediction, disease progression modelling, and personalized medicine. We present CFB-GBM v2.0, an extension of our previously released CFB-GBM dataset comprising 264 GBM patients treated according to the standard Stupp protocol. The primary contribution of this release is the completion of Gross Tumour Volume (GTV) delineations across all available timepoints (t0 , t1 and t2 ), increasing the overall GTV completion rate from 35% to 97%. This was achieved using a nnU-Net model pre-trained on BraTS 2021 and fine-tuned on CFB-GBM ground-truth contours, with the generated segmentations validated by five radiation oncologists. From these longitudinal GTV annotations, volumetric RANO 2.0 response category labels were derived for all available temporality pairs (t0 → t1 , t0 → t2 and t1 → t2 ). To further ease dataset usability and reproducibility, brain masks computed with HD-BET and pre-computed radiomic features extracted with PyRadiomics are provided for each patient timepoint and MRI modality. Additionally, the WHO classification guideline (2016 vs. 2021) applicable to each patient’s diagnosis is now explicitly documented. CFB-GBM v2.0 is publicly available on The Cancer Imaging Archive (TCIA) at www.cancerimagingarchive.net/collection/cfb-gbm

Keywords

Glioblastoma · Multi-modal and longitudinal MRI · Medical Imaging · Tumor segmentation · RANO criteria · Radiomics

Bibtex

@article{melba:2026:038:leclerq,
    title = "CFB-GBM v2.0: An Augmented Longitudinal Dataset for Multi-Modal Glioblastoma Segmentation, Radiomics, and RANO Progression Tracking",
    author = "Leclerq, Alexandre G. and Moreau, Noémie N. and Audebert, Hugo and Nassar, Andros and Cochin, Thomas and Leleu, Thomas and Le Henaff, Loı̈c and Desmonts, Alexis and Poirier, Yoann and Dubru, Aurélie and Guillemette, Laura and Lecoeur, Pascal and Lemasson, Kévin and Jaudet, Cyril and Bougleux, Sébastien and Hérault, Romain and Brunaud, Carole and Valable, Samuel and Stefan, Dinu and Raboutet, Charlotte and Batalla, Alain and Lacroix, Joëlle and Rouzier, Roman and Corroyer-Dulmont, Aurélien",
    journal = "Machine Learning for Biomedical Imaging",
    volume = "2026",
    issue = "Special Issue on MICCAI Open Data 2026",
    year = "2026",
    pages = "763--771",
    issn = "2766-905X",
    doi = "https://doi.org/10.59275/j.melba.2026-dd48",
    url = "https://melba-journal.org/2026:038"
}

RIS

TY - JOUR
AU - Leclerq, Alexandre G.
AU - Moreau, Noémie N.
AU - Audebert, Hugo
AU - Nassar, Andros
AU - Cochin, Thomas
AU - Leleu, Thomas
AU - Le Henaff, Loı̈c
AU - Desmonts, Alexis
AU - Poirier, Yoann
AU - Dubru, Aurélie
AU - Guillemette, Laura
AU - Lecoeur, Pascal
AU - Lemasson, Kévin
AU - Jaudet, Cyril
AU - Bougleux, Sébastien
AU - Hérault, Romain
AU - Brunaud, Carole
AU - Valable, Samuel
AU - Stefan, Dinu
AU - Raboutet, Charlotte
AU - Batalla, Alain
AU - Lacroix, Joëlle
AU - Rouzier, Roman
AU - Corroyer-Dulmont, Aurélien
PY - 2026
TI - CFB-GBM v2.0: An Augmented Longitudinal Dataset for Multi-Modal Glioblastoma Segmentation, Radiomics, and RANO Progression Tracking
T2 - Machine Learning for Biomedical Imaging
VL - 2026
IS - Special Issue on MICCAI Open Data 2026
SP - 763
EP - 771
SN - 2766-905X
DO - https://doi.org/10.59275/j.melba.2026-dd48
UR - https://melba-journal.org/2026:038
ER -