Treffer: Radiogenomics for Glioblastoma Survival Prediction: Integrating Radiomics, Clinical, and Genomic Features Using Artificial Intelligence.
Ohgaki H, Kleihues P., "Epidemiology and etiology of gliomas," Acta Neuropathol, vol. 109, p. 93, 2005. (PMID: 10.1007/s00401-005-0991-y15685439)
Omuro A, DeAngelis LM., "Glioblastoma and other malignant gliomas: a clinical review," J Am Med Assoc, vol. 310, p. 1842–50, 2013. (PMID: 10.1001/jama.2013.280319)
Thakkar JP, Dolecek TA, Horbinski C, et al, "Epidemiologic and molecular prognostic review of glioblastoma," Cancer Epidemiol Biomarkers Prev, vol. 23, pp. 1985-96, 2014. (PMID: 10.1158/1055-9965.EPI-14-0275250537114185005)
Stupp R, Hegi ME, Gilbert MR, et al, "Chemoradiotherapy in malignant glioma: standard of care and future directions," Neuro-Oncology, vol. 9, pp. 1-8, 2007.
"IDH1 Mutation Testing," 2024. [Online]. Available: https://genomics.ucsf.edu/content/idh1-mutation-testing .
Bleeker FE, Molenaar RJ, Leenstra S, "Recent advances in the molecular understanding of glioblastoma," J Neurooncol, vol. 108, no. 1, p. 11–27, 2012. (PMID: 10.1007/s11060-011-0793-0222708503337398)
Gue R, Lakhani DA, "The 2021 World Health Organization Central Nervous System Tumor Classification: The Spectrum of Diffuse Gliomas," Biomedicines, vol. 12, no. 6, p. 1349, 2024. (PMID: 10.3390/biomedicines120613493892755611202067)
Jadoon SS, Ilyas U, Zafar H, Paiva-Santos AC, Khan S, Khan SA, Ahmed T, Rasool Y, Altaf R, Raza F, Abbas M, "Genomic and Epigenomic Features of Glioblastoma Multiforme and its Biomarkers," J Oncol, 2022.
Shui L, Ren H, Yang X, Li J, Chen Z, Yi C, Zhu H, Shui P, "The Era of Radiogenomics in Precision Medicine: An Emerging Approach to Support Diagnosis, Treatment Decisions, and Prognostication in Oncology," Front Oncol, vol. 10, 2020.
Tomoszková S, Škarda J, Lipina R, "Potential Diagnostic and Clinical Significance of Selected Genetic Alterations in Glioblastoma," Int. J. Mol. Sci, vol. 25, no. 8, 2024.
Yu W, Zhang L, Wei Q, Shao A, "O6-Methylguanine-DNA Methyltransferase (MGMT): Challenges and New Opportunities in Glioma Chemotherapy," Front Oncol, vol. 9, p. 1547, 2019. (PMID: 10.3389/fonc.2019.0154732010632)
Mareike M, Staub-Bartelt F, Ehrmann J, Hänggi D, Sabel M, Felsberg J, Rapp M, "Does positive MGMT methylation outbalance the limitation of subtotal resection in glioblastoma IDH-wildtype patients?," J Neurooncol, vol. 153, no. 3, pp. 537-545, 2021. (PMID: 10.1007/s11060-021-03794-8341852588279995)
Dharmaiah S, Huse JT, "The epigenetic dysfunction underlying malignant glioma pathogenesis," Laboratory Investigation, vol. 102, no. 7, pp. 682-690, 2022. (PMID: 10.1038/s41374-022-00741-735152274)
Decraene B, Vanmechelen M, Clement P, Daisne JF, Vanden Bempt I, Sciot R, Garg AD, Agostinis P, De Smet F, De Vleeschouwer S, "Cellular and molecular features related to exceptional therapy response and extreme long-term survival in glioblastoma," Cancer Medicine, 2023.
Bodalal Z, Trebeschi S, Nguyen-Kim TDL, et al., "Radiogenomics: bridging imaging and genomics," Abdom Radiol, vol. 44, pp. 1960-1984, 2019. (PMID: 10.1007/s00261-019-02028-w)
Li S, Zhou B, "A review of radiomics and genomics applications in cancers: the way towards precision medicine," Radiat Oncol, vol. 17, p. 217, 2022. (PMID: 10.1186/s13014-022-02192-2365857169801589)
Jena B, Saxena S, Nayak GK, Balestrieri A, Gupta N, Khanna NN, Laird JR, Kalra MK, Fouda MM, Saba L, Suri JS, "Brain Tumor Characterization Using Radiogenomics in Artificial Intelligence Framework," Cancers (Basel), vol. 14, no. 16, p. 4052, 2022. (PMID: 10.3390/cancers1416405236011048)
Qian X, Tan H, Liu X, Zhao W, Chan MD, Kim P, Zhou X, "Radiogenomics-Based Risk Prediction of Glioblastoma Multiforme with Clinical Relevance," Genes, vol. 15, no. 6, p. 718, 2024. (PMID: 10.3390/genes150607183892765411202835)
Grimm LJ, Mazurowski MA, "Breast Cancer Radiogenomics: Current Status and Future Directions," Academic Radiology, vol. 27, no. 1, pp. 39-46, 2020. (PMID: 10.1016/j.acra.2019.09.01231818385)
Sohn B, An C, Kim D, Ahn SS, Han K, Kim SH, Kang SG, Chang JH, Lee SK, "Radiomics-based prediction of multiple gene alteration incorporating mutual genetic information in glioblastoma and grade 4 astrocytoma, IDH-mutant," J Neurooncol, vol. 155, no. 3, pp. 267-276, 2021. (PMID: 10.1007/s11060-021-03870-z346481158651601)
Hajianfar G, Haddadi Avval A, Hosseini SA, et al, "Time-to-event overall survival prediction in glioblastoma multiforme patients using magnetic resonance imaging radiomics," Radiol Med, vol. 128, pp. 1521-1534, 2023. (PMID: 10.1007/s11547-023-01725-33775110210700216)
Wijethilake N, Islam M, Ren H, "Radiogenomics model for overall survival prediction of glioblastoma," Med Biol Eng Comput, vol. 58, no. 8, pp. 1767-1777, 2020. (PMID: 10.1007/s11517-020-02179-932488372)
Calabrese, Evan; Rudie, Jeffrey D; Rauschecker, Andreas M; Villanueva-Meyer, Javier E; Clarke, Jennifer L; Solomon, David A; Cha, Soonmee , "Combining radiomics and deep convolutional neural network features from preoperative MRI for predicting clinically relevant genetic biomarkers in glioblastoma," Neuro-Oncology Advances , vol. 4, no. 1, 2022.
Reuben Dorent, Zhuocheng Li, "MRIPreprocessor," 2020. [Online]. Available: https://github.com/ReubenDo/MRIPreprocessor .
Mayerhoefer ME, Materka A, Langs G, Häggström I, Szczypiński P, Gibbs P, Cook G., "Introduction to Radiomics," J Nucl Med, vol. 61, no. 4, pp. 488-495, 2020. (PMID: 10.2967/jnumed.118.222893320602199374044)
Mahmoudi, K., Kim, D. H., Tavakkol, E., Kihira, S., Bauer, A., Tsankova, N., Khan, F., Hormigo, A., Yedavalli, V., Nael, K, "Multiparametric radiogenomic model to predict survival in patients with glioblastoma," Cancers, vol. 16, no. 3, p. 589, 2024.
Babaei Rikan, Samin; Sorayaie Azar, Amir; Naemi, Amin; Bagherzadeh Mohasefi, Jamshid; Pirnejad, Habibollah; Wiil, Uffe Kock, "Survival prediction of glioblastoma patients using modern deep learning and machine learning techniques," Scientific Reports , vol. 14, 2024.
Cerono, G., Melaiu, O., Chicco, D., "Clinical Feature Ranking Based on Ensemble Machine Learning Reveals Top Survival Factors for Glioblastoma Multiforme," J Healthc Inform Res, vol. 8, pp. 1-18, 2024. (PMID: 10.1007/s41666-023-00138-138273986)
Lao, Jiangwei; Chen, Yinsheng; Li, Zhi-Cheng; Li, Qihua; Zhang, Ji; Liu, Jing; Zhai, Guangtao , "A Deep Learning-Based Radiomics Model for Prediction of Survival in Glioblastoma Multiforme," Scientific Reports , vol. 7, no. 1, p. 10353, 2017. (PMID: 10.1038/s41598-017-10649-8288711105583361)
Baid, U., Ghodasara, S., Bilello, M., et al. , "Combining radiomics and deep convolutional neural network features for glioblastoma genetic biomarker prediction," Radiology: Artificial Intelligence, vol. 2, no. 4, 2020.
Tang, Y., et al., "Deep Learning of Imaging Phenotype and Genotype for Predicting Overall Survival Time of Glioblastoma Patients," Scientific Reports, vol. 10, 2020.
Pei, Linmin; Vidyaratne, Lasitha; Rahman, Md Monibor; Iftekharuddin, Khan M. , "Context aware deep learning for brain tumor segmentation, subtype classification, and survival prediction using radiology images," Scientific Reports , vol. 10, 2020.
Luckett, P. H., Olufawo, M., Lamichhane, B., Park, K. Y., Dierker, D., Verastegui, G. T., Yang, P., Kim, A. H., Chheda, M. G., Snyder, A. Z., Shimony, J. S., Leuthardt, E. C., "Predicting survival in glioblastoma with multimodal neuroimaging and machine learning," Journal of Neuro-Oncology, vol. 164, no. 3, pp. 309-320, 2023. (PMID: 10.1007/s11060-023-04439-83766894110522528)
Weitere Informationen
Glioblastoma (GBM) remains one of the most formidable brain malignancies, characterized by a heterogeneous genetic profile that significantly influences patient prognosis. Per the 2021 WHO central nervous system classification, GBM is defined as an isocitrate dehydrogenase (IDH) wild-type diffuse astrocytic tumor. We analyzed two multi-institutional cohorts, UPENN-GBM (644 patients) and UCSF-PDGM (420 patients); after excluding the 116 and 42 IDH-mutant records, 528 and 378 wild-type cases remained for modelling. MGMT promoter methylation, present in 43% of GBM cases, correlates with enhanced survival outcomes, demonstrating a median survival of 504 days versus 329 days in unmethylated cases. In this study, we present a novel integration of imaging phenotypes, clinical characteristics, and molecular markers through the application of advanced machine learning methodologies, including Random Forest, XGBoost, LightGBM, and an optimized dense neural network (Dense NN). This integrative approach aims to refine survival prediction in GBM patients. MRI data were meticulously processed using the MRIPreprocessor tool and the radiomics Python library, facilitating the extraction of high-dimensional radiomic features. Our findings reveal that the proposed custom Dense NN model outperformed traditional tree-based algorithms, with the Dense NN achieving a concordance index (CI) of 0.86 on the UPENN-GBM dataset and 0.83 on the UCSF-PDGM dataset. The optimized Dense NN architecture features three hidden layers with 256, 128, and 64 units respectively, employing ReLU activation, L1/L2 regularization to mitigate overfitting, batch normalization to stabilize training, and dropout for improved generalization. This specific configuration was determined through hyperparameter tuning using techniques like RandomizedSearchCV. This integrative, non-invasive methodology provides a more nuanced assessment of tumor biology, thereby advancing the development of personalized therapeutic strategies. Our results underscore the transformative potential of artificial intelligence in delineating disease trajectories and optimizing treatment paradigms. Moreover, this research establishes a robust framework for future investigations in glioblastoma survival prediction, illustrating the efficacy of combining clinical, genetic, and imaging data to enhance prognostic accuracy within precision medicine paradigms for GBM patients.
(© 2025. The Author(s).)
Declarations. Ethics Approval: This study involved secondary analysis of existing, publicly available, and anonymized patient datasets (UPENN-GBM and UCSF-PDGM). The original data collection protocols for these datasets received approval from their respective Institutional Review Boards (IRBs) or Ethics Committees. As this study used only previously collected, de-identified data from public sources, separate ethics approval for this specific analysis was not required. Consent to Participate: Informed consent was obtained from all individual participants included in the original studies from which the UPENN-GBM and UCSF-PDGM datasets were derived. Consent for this secondary analysis of anonymized data was not applicable. Competing interests: The authors declare no competing interests.