Multimodal MRI radiomics based on habitat subregions of the tumor microenvironment for predicting risk stratification in glioblastoma

• Published in: PloS one Vol. 20; no. 6; p. e0326361
• Main Author: Wang, Han
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 27.06.2025; Public Library of Science (PLoS)
• Subjects: Adult; Aged; Algorithms; Automation; Brain Neoplasms - diagnostic imaging; Brain Neoplasms - mortality; Brain Neoplasms - pathology; Data mining; Datasets; Deep learning; Development and progression; Disease Progression; Feature extraction; Female; Glioblastoma; Glioblastoma - diagnostic imaging; Glioblastoma - genetics; Glioblastoma - mortality; Glioblastoma - pathology; Glioblastoma multiforme; Glioma; Hazard identification; Health risks; Humans; Image acquisition; Isocitrate dehydrogenase; Kaplan-Meier Estimate; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Medical prognosis; Methods; Middle Aged; Multimodal Imaging - methods; Nomograms; Patients; Predictions; Prognosis; Proportional Hazards Models; Radiomics; Rank tests; Regression analysis; Retrospective Studies; Risk Assessment; Risk groups; Software; Statistical analysis; Survival; Survival analysis; Therapeutic applications; Tumor Microenvironment; China

Accurate prediction of glioblastoma (GBM) progression is essential for improving therapeutic interventions and outcomes. This study aimed to develop and validate an integrated clinical-radiomics model to predict overall survival (OS) and evaluate the risk of disease progression in patients with isoc...