What question did this study set out to answer?

To introduce a comprehensive, standardized, and open-source dataset of multi-sequence post-treatment MRI scans with expert-validated tumor component segmentations and clinical features for glioma patients.

November 20, 2025Scientific DataOpen Access

MU-Glioma Post: A comprehensive dataset of automated MR multi-sequence segmentation and clinical features

View Full Paper

Ask AI

Bookmark

Authors

EMEsmat MahmoudCairo University JGJaime GassAnnual Reviews YDYaseen DhemeshWashington University in St. Louis

Discussion

Member takes

Implication

Observational dataset presents expert-validated multi-sequence MRI segmentations across 203 glioma patients, facilitating artificial intelligence evaluation of post-treatment outcomes.

Key Points

To introduce a comprehensive, standardized, and open-source dataset of multi-sequence post-treatment MRI scans with expert-validated tumor component segmentations and clinical features for glioma patients.
Assembled routine multi-sequence MRI scans (T1, T1 postcontrast, T2, FLAIR) and clinical history across 594 post-treatment timepoints from N=203 glioma patients.
Implemented a standardized deep-learning pipeline to automatically segment tumor components, including enhancing tumor, non-enhancing necrotic core, FLAIR hyperintensity, and resection cavity.
Engaged neuroradiologists to manually review, validate, and refine all automated segmentations to establish definitive ground truth labels.
Generated ground truth segmentations across 594 post-treatment longitudinal timepoints in 203 patients, accurately delineating four key post-treatment tumor compartments.
Established an open-source multimodal dataset combining standardized imaging and clinical histories to accelerate AI model training for differentiating tumor recurrence from radiation necrosis.

Cite This Study

Mahmoud et al. (2025) studied this question.

synapsesocial.com/papers/6a0f4fa2426db18b04ed161e https://doi.org/10.1038/s41597-025-06011-7

View Full Paper

Ask AI

Bookmark

Implication

Observational dataset presents expert-validated multi-sequence MRI segmentations across 203 glioma patients, facilitating artificial intelligence evaluation of post-treatment outcomes.

MU-Glioma Post: A comprehensive dataset of automated MR multi-sequence segmentation and clinical features

Discussion

Member takes

Implication

Key Points

Cite This Study

MU-Glioma Post: A comprehensive dataset of automated MR multi-sequence segmentation and clinical features

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider