TY - JOUR
T1 - Predicting survival in glioblastoma with multimodal neuroimaging and machine learning
AU - Luckett, Patrick H.
AU - Olufawo, Michael
AU - Lamichhane, Bidhan
AU - Park, Ki Yun
AU - Dierker, Donna
AU - Verastegui, Gabriel Trevino
AU - Yang, Peter
AU - Kim, Albert H.
AU - Chheda, Milan G.
AU - Snyder, Abraham Z.
AU - Shimony, Joshua S.
AU - Leuthardt, Eric C.
N1 - Publisher Copyright:
© 2023, This is a U.S. Government work and not under copyright protection in the US; foreign copyright protection may apply.
PY - 2023/9
Y1 - 2023/9
N2 - Purpose: Glioblastoma (GBM) is the most common and aggressive malignant glioma, with an overall median survival of less than two years. The ability to predict survival before treatment in GBM patients would lead to improved disease management, clinical trial enrollment, and patient care. Methods: GBM patients (N = 133, mean age 60.8 years, median survival 14.1 months, 57.9% male) were retrospectively recruited from the neurosurgery brain tumor service at Washington University Medical Center. All patients completed structural neuroimaging and resting state functional MRI (RS-fMRI) before surgery. Demographics, measures of cortical thickness (CT), and resting state functional network connectivity (FC) were used to train a deep neural network to classify patients based on survival (< 1y, 1-2y, >2y). Permutation feature importance identified the strongest predictors of survival based on the trained models. Results: The models achieved a combined cross-validation and hold out accuracy of 90.6% in classifying survival (< 1y, 1-2y, >2y). The strongest demographic predictors were age at diagnosis and sex. The strongest CT predictors of survival included the superior temporal sulcus, parahippocampal gyrus, pericalcarine, pars triangularis, and middle temporal regions. The strongest FC features primarily involved dorsal and inferior somatomotor, visual, and cingulo-opercular networks. Conclusion: We demonstrate that machine learning can accurately classify survival in GBM patients based on multimodal neuroimaging before any surgical or medical intervention. These results were achieved without information regarding presentation symptoms, treatments, postsurgical outcomes, or tumor genomic information. Our results suggest GBMs have a global effect on the brain’s structural and functional organization, which is predictive of survival.
AB - Purpose: Glioblastoma (GBM) is the most common and aggressive malignant glioma, with an overall median survival of less than two years. The ability to predict survival before treatment in GBM patients would lead to improved disease management, clinical trial enrollment, and patient care. Methods: GBM patients (N = 133, mean age 60.8 years, median survival 14.1 months, 57.9% male) were retrospectively recruited from the neurosurgery brain tumor service at Washington University Medical Center. All patients completed structural neuroimaging and resting state functional MRI (RS-fMRI) before surgery. Demographics, measures of cortical thickness (CT), and resting state functional network connectivity (FC) were used to train a deep neural network to classify patients based on survival (< 1y, 1-2y, >2y). Permutation feature importance identified the strongest predictors of survival based on the trained models. Results: The models achieved a combined cross-validation and hold out accuracy of 90.6% in classifying survival (< 1y, 1-2y, >2y). The strongest demographic predictors were age at diagnosis and sex. The strongest CT predictors of survival included the superior temporal sulcus, parahippocampal gyrus, pericalcarine, pars triangularis, and middle temporal regions. The strongest FC features primarily involved dorsal and inferior somatomotor, visual, and cingulo-opercular networks. Conclusion: We demonstrate that machine learning can accurately classify survival in GBM patients based on multimodal neuroimaging before any surgical or medical intervention. These results were achieved without information regarding presentation symptoms, treatments, postsurgical outcomes, or tumor genomic information. Our results suggest GBMs have a global effect on the brain’s structural and functional organization, which is predictive of survival.
KW - Cortical thickness
KW - Deep learning
KW - Functional MRI
KW - Glioblastoma
KW - Survival
UR - http://www.scopus.com/inward/record.url?scp=85169788841&partnerID=8YFLogxK
U2 - 10.1007/s11060-023-04439-8
DO - 10.1007/s11060-023-04439-8
M3 - Article
C2 - 37668941
AN - SCOPUS:85169788841
SN - 0167-594X
VL - 164
SP - 309
EP - 320
JO - Journal of Neuro-Oncology
JF - Journal of Neuro-Oncology
IS - 2
ER -