Predicting survival in glioblastoma with multimodal neuroimaging and machine learning

Keyphrases

• Glioblastoma 100%
• Survival Prediction 100%
• Machine Learning 100%
• Multimodal Neuroimaging 100%
• Patient-centered 40%
• Cortical Thickness 40%
• Functional Networks 40%
• Patient-completed 20%
• Patient Care 20%
• Age at Diagnosis 20%
• Disease Management 20%
• Surgical Intervention 20%
• Superior Temporal Sulcus 20%
• University of Washington 20%
• Neurosurgery 20%
• Cingulo-opercular Network 20%
• Before Surgery 20%
• University Medical Centre 20%
• Median Survival 20%
• Strong Predictor 20%
• Resting-state Functional Magnetic Resonance Imaging (rs-fMRI) 20%
• Resting-state Functional Connectivity (rs-FC) 20%
• Brain Tumor 20%
• Functional Organization 20%
• Medical Intervention 20%
• Malignant Glioma 20%
• Tumor Genomics 20%
• Clinical Trial Participation 20%
• Somatomotor 20%
• Genomic Information 20%
• Deep Neural Network 20%
• Structural Organization 20%
• Temporal Region 20%
• Connectivity Features 20%
• Overall Median Survival 20%
• Global Effect 20%
• Training Model 20%
• Middle Temporal 20%
• Parahippocampal Gyrus 20%
• Structural Neuroimaging 20%
• Demographic Predictors 20%
• Pars Triangularis 20%
• Permutation Importance 20%
• Postsurgical Outcomes 20%

Neuroscience

• Functional Magnetic Resonance Imaging 100%
• Neural Network 100%
• Superior Temporal Sulcus 100%
• Neurosurgery 100%
• Parahippocampal Gyrus 100%
• Intracranial Tumor 100%