Deep Learning Guided Radiogenomic Signatures for Prognostic Stratification in Glioblastoma Multiforme

• Erkin Bilalov

  The Head of the Department of Ophthalmology, Tashkent State Medical University, Tashkent, Uzbekistan

• Dilshodjon Usarov

  Teacher, Gulistan State University, Uzbekistan

• Turabek Boyqulov

  Department of Medicine, Termez University of Economics and Service, Termez, Uzbekistan

• Marhabo Matniyozova

  Department of Psychological Sciences, Mamun University, Khiva, Uzbekistan

• Mohamed Hisham

  Department of Medical Analysis Technique, Medical College Technique, the Islamic University, Najaf, Iraq

• Neetish Kumar

  Department of Pharmacy, Kalinga University, Naya Raipur, Chhattisgarh, India

Glioblastoma multiforme (GBM) is the most aggressive and lethal primary brain tumor, with an average survival of no more than 15 months despite advances in surgery, chemotherapy, and radiotherapy. Linking imaging phenotypes with genomic frameworks can improve personalized prognosis and treatment planning. This study develops a deep learning-based radiogenomic framework that integrates high-dimensional imaging features extracted from multiparametric MRI using a convolutional neural network (CNN) with key molecular biomarkers, including EGFR amplification, IDH mutation, and MGMT promoter methylation. A multiomics fusion module combined imaging-derived features with genomic alterations to enable stratified survival prediction. The publicly available datasets were used to train and validate the framework, i.e., TCIA and TCGA-GBM. The CNN-based radiogenomic model was more successful than the traditional radiomic and dictionary learning -based approaches, with high prognostic accuracy. Survival stratification into high- and low-risk groups showed significant differences, as confirmed by Kaplan–Meier analysis, C-index, and AUC metrics. The radiogenomic markers based on the model obtained biologically meaningful information on tumor heterogeneity and a better predictive outcome than the traditional methods. Radiogenomic signatures based on deep learning make it possible to prognosticate GBM accurately, non-invasively, and biologically in a manner that is precise, relevant, and now more useful in the field of neuro-oncology. The next step in research involves future multi-institutional validation, explainable AI integration, and adding more omics data to make prognostics more accurate and clinically applicable.

[1] Karabacak M, Ozkara BB, Senparlak K, Bisdas S. Deep Learning-Based Radiomics for Prognostic Stratification of Low-Grade Gliomas Using a Multiple-Gene Signature. Applied Sciences [Internet] 2023 Mar 18 [cited 2025 Dec 5]; 13(6): 3873.

[2] Gatto L, Franceschi E, Tosoni A, Vincenzo Di Nunno, Tonon C, Lodi R, et al. Beyond Imaging and Genetic Signature in Glioblastoma: Radiogenomic Holistic Approach in Neuro-Oncology. Biomedicines 2022 Dec 9 [cited 2023 Nov 4]; 10(12): 3205-5.

[3] Qian X, Tan H, Liu X, Zhao W, Chan MD, Kim P, et al. Radiogenomics-Based Risk Prediction of Glioblastoma Multiforme with Clinical Relevance. Genes 2024 Jun 1 [cited 2024 Nov 26]; 15(6): 718-8.

[4] Poursaeed R, Mohammadzadeh M, Safaei AA. Survival prediction of glioblastoma patients using machine learning and deep learning: a systematic review. BMC Cancer 2024 Dec 27; 24(1).

[5] Ghimire P, Kinnersley B, Karami G, Arumugam P, Houlston R, Ashkan K, et al. Radiogenomic biomarkers for immunotherapy in glioblastoma: A systematic review of magnetic resonance imaging studies. Neuro-Oncology Advances 2024 Jan 1 [cited 2024 Nov 18]; 6(1).

[6] Le VH, Nguyen T, Kha QH, Le NQK. A transfer learning approach on MRI-based radiomics signature for overall survival prediction of low-grade and high-grade gliomas. Medical & Biological Engineering & Computing 2023 Jul 11 [cited 2025 Dec 5]; 61(10): 2699-712.

[7] Patel M, Zhan J, Natarajan K, Flintham R, Davies NP, Sanghera P, et al. Machine learning-based radiomic evaluation of treatment response prediction in glioblastoma. Clinical Radiology 2021 Aug 1 [cited 2024 Jan 15]; 76(8): 628.e17-27.

[8] Shyamala B, Vamsidhar DrY, Brahmananda DrSH. An Ensemble Multi-Fusion based U-Net with Short Learning Technique for Brain Tumor Classification. Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications 2024 Dec 12 [cited 2025 Dec 5]; 15(4): 226-42.

[9] Nuechterlein N, Li B, Feroze A, Holland EC, Shapiro L, Haynor D, et al. Radiogenomic modeling predicts survival-associated prognostic groups in glioblastoma. Neuro-Oncology Advances 2021 Jan 1; 3(1): vdab004.

[10] Yadav RK, Mishra AK, Saini DKJB, Pant H, Biradar RG, Waghodekar P. A Model for Brain Tumor Detection Using a Modified Convolution Layer ResNet-50. Indian Journal of Information Sources and Services 2024 Feb 16 [cited 2024 May 6]; 14(1): 29-38.

[11] Fathi Kazerooni A, Bakas S, Saligheh Rad H, Davatzikos C. Imaging signatures of glioblastoma molecular characteristics: A radiogenomics review. Journal of Magnetic Resonance Imaging 2019 Aug 27; 52(1): 54-69.

[12] Abd-Elhafiez WM. Automated Detection and Segmentation of Heterogeneous Brain Tumor Regions Via Transformer-Based Deeplabv3+. Journal of Internet Services and Information Security 2025 May 30; 15(2): 760-773.

[13] Liu D, Chen J, Ge H, Yan Z, Luo B, Hu X, et al. Radiogenomics to characterize the immune-related prognostic signature associated with biological functions in glioblastoma. European Radiology 2022 Jul 26; 33(1): 209-20.

[14] Sherlin D, Nikila I. Detection and Diagnosis of Brain Tumor Using Wavelet Transform and Machine Learning Model. IAJIR 2022 Mar. 30 [cited 2025 Dec. 5]; 9(1): 01-5.

[15] Liu D, Chen J, Hu X, Yang K, Liu Y, Hu G, et al. Imaging-Genomics in Glioblastoma: Combining molecular and imaging signatures. Frontiers in Oncology 2021 Jul 6; 11: 699265.

[16] Soumya M. Brain Tumor Image Analysis Using FCM with Enhanced BFA Algorithm. International Academic Journal of Science and Engineering 2022 Nov 7; 9(2): 74-82.

[17] Singh G, Manjila S, Sakla N, True A, Wardeh AH, Beig N, et al. Radiomics and radiogenomics in gliomas: a contemporary update. British Journal of Cancer 2021 May 6; 125(5): 641-57.

[18] Corr F, Grimm D, Saß B, Pojskić M, Bartsch JW, Carl B, et al. Radiogenomic Predictors of Recurrence in Glioblastoma—A Systematic Review. Journal of Personalized Medicine 2022 Mar 4; 12(3): 402.

[19] Karabacak M, Patil S, Gersey ZC, Komotar RJ, Margetis K. Radiomics-Based Machine Learning with Natural Gradient Boosting for Continuous Survival Prediction in Glioblastoma. Cancers 2024 Oct 26; 16(21): 3614.

[20] Guo J, Kazerooni AF, Toorens E, Akbari H, Yu F, Sako C, et al. Integrating imaging and genomic data for the discovery of distinct glioblastoma subtypes: a joint learning approach. Scientific Reports 2024 Feb 28; 14(1): 4922.

[21] Wang Z, Wang L, Wang Y. Radiomics in glioma: emerging trends and challenges. Annals of Clinical and Translational Neurology 2025 Feb 3; 12(3): 460-77.

[22] Qureshi SA, Hussain L, Ibrar U, Alabdulkreem E, Nour MK, Alqahtani MS, et al. Radiogenomic classification for MGMT promoter methylation status using multi-omics fused feature space for least invasive diagnosis through mpMRI scans. Scientific Reports 2023 Feb 25; 13(1): 3291.

[23] Guo Y, Li T, Gong B, Hu Y, Wang S, Yang L, et al. From Images to Genes: Radiogenomics based on Artificial Intelligence to achieve Non‐Invasive Precision Medicine in Cancer patients. Advanced Science 2024 Nov 13; 12(2): e2408069.

[24] Habibi MA, Tajabadi Z, Farsani AS, Omid R, Tajabadi Z, Shobeiri P. Predicting the survival of patients with glioblastoma using deep learning: a systematic review. The Egyptian Journal of Neurosurgery : The Official Publication of the Egyptian Society of Neurological Surgeons/Egyptian Journal of Neurosurgery 2025 Feb 11; 40(1).

[25] Wu X, Zhang S, Zhang Z, He Z, Xu Z, Wang W, et al. Biologically interpretable multi-task deep learning pipeline predicts molecular alterations, grade, and prognosis in glioma patients. Npj Precision Oncology 2024 Aug 16; 8(1): 181.

• PDF

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.