Share：
Share this content in WeChat
X
[Chinese] [PDF] 51 1
• Reviews •
Advances in multimodal radiomics and deep learning for predicting TERT promoter status and assisting clinical decision-making in glioma
YANG Duo  LI Lixin  YAN Yuxin  WANG Xiaotong  JIANG Yingying  BAI Yuping 

Cite this article as YANG D, LI L X, YAN Y X, et al. Advances in multimodal radiomics and deep learning for predicting TERT promoter status and assisting clinical decision-making in glioma[J]. Chin J Magn Reson Imaging, 2026, 17(8): 154-160, 183. DOI:10.12015/issn.1674-8034.2026.08.017.


[Abstract] Telomerase reverse transcriptase promoter mutation is a core molecular event in the molecular classification of gliomas. Detecting these mutations provides crucial guidance for patient prognosis assessment and the development of individualized treatment plans. Traditional detection methods rely on invasive tissue biopsy, which has inherent limitations such as tumor spatiotemporal heterogeneity, sampling bias, and the inability to perform dynamic monitoring, making it difficult to meet the clinical needs of precise diagnosis and treatment.In recent years, radiomics based on multiparametric MRI and deep learning technology have developed rapidly and have become an important research direction for non-invasive preoperative prediction of TERT promoter mutation status in gliomas. Research shows that some multimodal fusion models demonstrate certain generalization ability in limited external validation, but performance degradation across centers remains a common challenge. Meanwhile, the translation of this technology into routine clinical practice still faces key challenges, including image standardization, cross-center data sharing, and insufficient model interpretability. Looking ahead, by promoting large-scale prospective clinical trials, establishing standardized cross-center imaging databases, integrating spatial multi-omics and liquid biopsy cross-modal information, and optimizing models with technologies such as federated learning and explainable AI, it is hoped that imaging AI prediction models can be transformed into reliable clinical decision-support tools, advancing intelligent and individualized glioma diagnosis and treatment. This review systematically summarizes the latest research progress in this field, focusing on the methodological construction, model performance optimization, and clinical translation value of multi-modal radiomics and deep learning models in predicting TERT promoter mutations in gliomas. It also analyzes core development features in current research, such as model refinement, multi-modal fusion, and interpretability exploration, aiming to provide methodological reference for non-invasive preoperative prediction of TERT promoter mutations in gliomas.
[Keywords] glioma；telomerase reverse transcriptase promoter mutation；radiomics；deep learning；magnetic resonance imaging；preoperative prediction

YANG Duo1, 2   LI Lixin1, 2   YAN Yuxin1, 2   WANG Xiaotong1   JIANG Yingying3   BAI Yuping1, 2*  

1 Second Clinical School, Lanzhou University, Lanzhou 730030, China

2 Department of Magnetic Resonance, Lanzhou University Second Hospital, Lanzhou 730030, China

3 Gansu University of Chinese Medicine, Lanzhou 730030, China

Corresponding author: BAI Y P, E-mail: 309131762@qq.com

Conflicts of interest   None.

Received  2026-04-13
Accepted  2026-07-14
DOI: 10.12015/issn.1674-8034.2026.08.017
Cite this article as YANG D, LI L X, YAN Y X, et al. Advances in multimodal radiomics and deep learning for predicting TERT promoter status and assisting clinical decision-making in glioma[J]. Chin J Magn Reson Imaging, 2026, 17(8): 154-160, 183. DOI:10.12015/issn.1674-8034.2026.08.017.

[1]
NICHOLSON J G, FINE H A. Diffuse Glioma Heterogeneity and Its Therapeutic Implications[J]. Cancer Discov, 2021, 11(3): 575-590. DOI: 10.1158/2159-8290.Cd-20-1474.
[2]
ŚLEDZIŃSKA P, BEBYN M G, FURTAK J, et al. Prognostic and Predictive Biomarkers in Gliomas[J/OL]. Int J Mol Sci, 2021, 22(19): 10373 [2026-04-13]. https://doi.org/10.3390/ijms221910373. DOI: 10.3390/ijms221910373.
[3]
BODUROĞLU A, ÖZCAN M, OCAK G A. TERT promoter mutations in meningiomas: associations with clinicopathological features and insights into spatial and temporal heterogeneity in a 165-case cohort[J/OL]. Pathol Res Pract, 2025, 274: 156191 [2026-04-13]. https://doi.org/10.1016/j.prp.2025.156191. DOI: 10.1016/j.prp.2025.156191.
[4]
SKOURAS P, MARKOULI M, KALAMATIANOS T, et al. Advances on Liqui,d Biopsy Analysis for Glioma Diagnosis[J/OL]. Biomedicines, 2023, 11(9): 2371 [2026-04-13]. https://doi.org/10.3390/biomedicines11092371. DOI: 10.3390/biomedicines11092371.
[5]
CEPEDA S. Machine Learning and Radiomics in Gliomas[J]. Adv Exp Med Biol, 2024, 1462: 231-243. DOI: 10.1007/978-3-031-64892-2_14.
[6]
REN S Y, CHEN H Y, WANG J N. Research progress of MRI radiomics in the diagnosis and treatment of glioma[J]. J Clin Radiol, 2025, 44(9): 1778-1783. DOI: 10.13437/j.cnki.jcr.2025.09.018.
[7]
TANG Y B, DI N N, XU C. Research progress of multimodal MRI radiomics in predicting molecular subtypes of glioma[J]. Chin J Magn Reson Imaging, 2026, 17(1): 175-181. DOI: 10.12015/issn.1674-8034.2026.01.027.
[8]
MCNEILL K A. Epidemiology of Brain Tumors[J]. Neurol Clin, 2016, 34(4): 981-998. DOI: 10.1016/j.ncl.2016.06.014.
[9]
KINNERSLEY B, JUNG J, CORNISH A J, et al. Genomic landscape of diffuse glioma revealed by whole genome sequencing[J/OL]. Nat Commun, 2025, 16(1): 4233 [2026-04-13]. https://doi.org/10.1038/s41467-025-59156-9. DOI: 10.1038/s41467-025-59156-9.
[10]
GISINA A, KHOLODENKO I, KIM Y, et al. Glioma Stem Cells: Novel Data Obtained by Single-Cell Sequencing[J/OL]. Int J Mol Sci, 2022, 23(22): 14224 [2026-04-13]. https://doi.org/10.3390/ijms232214224. DOI: 10.3390/ijms232214224.
[11]
MILLER K D, OSTROM Q T, KRUCHKO C, et al. Brain and other central nervous system tumor statistics, 2021[J]. CA Cancer J Clin, 2021, 71(5): 381-406. DOI: 10.3322/caac.21693.
[12]
LOUIS D N, PERRY A, WESSELING P, et al. The 2021 WHO Classification of Tumors of the Central Nervous System: a summary[J]. Neuro Oncol, 2021, 23(8): 1231-1251. DOI: 10.1093/neuonc/noab106.
[13]
IPPEN F M, HIELSCHER T, FRIEDEL D, et al. The prognostic impact of CDKN2A/B hemizygous deletions in IDH-mutant glioma[J]. Neuro Oncol, 2025, 27(3): 743-754. DOI: 10.1093/neuonc/noae238.
[14]
POLITIS A, STAVRINOU L, KALYVAS A, et al. Glioblastoma: Molecular features, emerging molecular targets and novel therapeutic strategies[J/OL]. Crit Rev Oncol Hematol, 2025, 212: 104764 [2026-04-13]. https://doi.org/10.1016/j.critrevonc.2025.104764. DOI: 10.1016/j.critrevonc.2025.104764.
[15]
STEVERS N O, KIM S, YUAN J B, et al. The immortality mechanism of TERT promoter mutant cancers is self-reinforcing and reversible[J/OL]. Mol Cell, 2025, 85(12): 2337-54.e9 [2026-04-13]. https://doi.org/10.1016/j.molcel.2025.05.026. DOI: 10.1016/j.molcel.2025.05.026.
[16]
MINAMI N, HONG D, STEVERS N, et al. Imaging biomarkers of TERT or GABPB1 silencing in TERT-positive glioblastoma[J]. Neuro Oncol, 2022, 24(11): 1898-1910. DOI: 10.1093/neuonc/noac112.
[17]
XING H, LIU D, LI J, et al. TERTp Mutation and its Prognostic Value in Glioma Patients Under the 2021 WHO Classification: A Real-World Study[J/OL]. Cancer Med, 2025, 14(2): e70533 [2026-04-13]. https://doi.org/10.1002/cam4.70533. DOI: 10.1002/cam4.70533.
[18]
HöLZL D, HUTAREW G, ZELLINGER B, et al. EGFR Amplification Is a Phenomenon of IDH Wildtype and TERT Mutated High-Grade Glioma: An Integrated Analysis Using Fluorescence In Situ Hybridization and DNA Methylome Profiling[J/OL]. Biomedicines, 2022, 10(4): 794 [2026-04-13]. https://doi.org/10.3390/biomedicines10040794. DOI: 10.3390/biomedicines10040794.
[19]
NOZZOLI F, RAHMANZADE R, SCHMID S, et al. Distinct molecular profile and outcome of oligodendroglioma, IDH-mutant, 1p/19q-codeleted, and TERTp-wildtype: A grade 1 oligodendroglioma of young patients?[J]. Neuro Oncol, 2025, 27(10): 2711-2725. DOI: 10.1093/neuonc/noaf141.
[20]
KACIMI S E O, DEHAIS C, FEUVRET L, et al. Survival Outcomes Associated With First-Line Procarbazine, CCNU, and Vincristine or Temozolomide in Combination With Radiotherapy in IDH-Mutant 1p/19q-Codeleted Grade 3 Oligodendroglioma[J]. J Clin Oncol, 2025, 43(3): 329-338. DOI: 10.1200/jco.24.00049.
[21]
CHEN C, HAN S, MENG L, et al. TERT promoter mutations lead to high transcriptional activity under hypoxia and temozolomide treatment and predict poor prognosis in gliomas[J/OL]. PLoS One, 2014, 9(6): e100297 [2026-04-13]. https://doi.org/10.1371/journal.pone.0100297. DOI: 10.1371/journal.pone.0100297.
[22]
FARAHANI S, HEJAZI M, MORADIZEYVEH S, et al. Diagnostic Accuracy of Deep Learning Models in Predicting Glioma Molecular Markers: A Systematic Review and Meta-Analysis[J/OL]. Diagnostics (Basel), 2025, 15(7): 797 [2026-04-13]. https://doi.org/10.3390/diagnostics15070797. DOI: 10.3390/diagnostics15070797.
[23]
SOWMYA V L, BHARATHI MALAKREDDY A, NATARAJAN S, et al. Spectral Entropic Radiomics Feature Extraction (SERFE): an adaptive approach for glioblastoma disease classification[J/OL]. Front Artif Intell, 2025, 8: 1583079 [2026-04-13]. https://doi.org/10.3389/frai.2025.1583079. DOI: 10.3389/frai.2025.1583079.
[24]
ABDELAZIZ N M, DAWOOD E A, TANTAWY A A. Integrating Deep Learning and Radiogenomics: A Novel Approach to Glioblastoma Segmentation and MGMT Methylation Prediction[J/OL]. J Imaging, 2025, 11(11): 403 [2026-04-13]. https://doi.org/10.3390/jimaging11110403. DOI: 10.3390/jimaging11110403.
[25]
ZHANG Z, LIU Y, ZHANG Z, et al. MRI-based radiomic clustering identifies a glioblastoma subtype enriched for neural stemness and proliferative programs[J/OL]. Front Oncol, 2025, 15: 1662401 [2026-04-13]. https://doi.org/10.3389/fonc.2025.1662401. DOI: 10.3389/fonc.2025.1662401.
[26]
YAN J, HAO M, WANG T, et al. Identification of Glioma Phenotypic Subtypes From Multimodal MRI Data Using Hierarchical Multi-Kernel Learning[J/OL]. Cancer Med, 2026, 15(2): e71572 [2026-04-13]. https://doi.org/10.1002/cam4.71572. DOI: 10.1002/cam4.71572.
[27]
MOREAU N N, VALABLE S, JAUDET C, et al. Early characterization and prediction of glioblastoma and brain metastasis treatment efficacy using medical imaging-based radiomics and artificial intelligence algorithms[J/OL]. Front Oncol, 2025, 15: 1497195 [2026-04-13]. https://doi.org/10.3389/fonc.2025.1497195. DOI: 10.3389/fonc.2025.1497195.
[28]
BADVE C, NIRAPPEL A, LO S, et al. Congress of neurological surgeons systematic review and evidence-based guidelines for the role of imaging in newly diagnosed WHO grade II diffuse glioma in adults: update[J]. J Neurooncol, 2025, 174(1): 7-52. DOI: 10.1007/s11060-025-05043-8.
[29]
GIHR G, HORVATH-RIZEA D, HEKELER E, et al. Diffusion weighted imaging in high-grade gliomas: A histogram-based analysis of apparent diffusion coefficient profile[J/OL]. PLoS One, 2021, 16(4): e0249878 [2026-04-13]. https://doi.org/10.1371/journal.pone.0249878. DOI: 10.1371/journal.pone.0249878.
[30]
MADOUR J, BESSETTE J, GU J Z, et al. Glioblastoma: Epidemiology and Imaging-Based Review[J/OL]. R I Med J (2013), 2025, 108(8): 50-56 [2026-04-13]. http://www.rimed.org/rimedicaljournal/2025/08/2025-08-50-study-madour.pdf.
[31]
SACLI-BILMEZ B, BAS A, ERŞEN DANYELI A, et al. Detecting IDH and TERTp mutations in diffuse gliomas using (1)H-MRS with attention deep-shallow networks[J/OL]. Comput Biol Med, 2025, 186: 109736 [2026-04-13]. https://doi.org/10.1016/j.compbiomed.2025.109736. DOI: 10.1016/j.compbiomed.2025.109736.
[32]
GAO S, ZHANG S, WANG Y, et al. Integrated Radiomics Model Combining Diffusion Kurtosis Imaging and Dynamic Contrast-Enhanced MRI for Predicting TERT Promoter Mutation Status in Gliomas[J/OL]. Hum Mutat, 2026, 2026: 6650170 [2026-04-13]. https://doi.org/10.1155/humu/6650170. DOI: 10.1155/humu/6650170.
[33]
LI X, LI Z, DUAN X, et al. Machine learning-based radiopathomics ensemble model for predicting multiple molecular subtypes of adult diffuse glioma: a multicenter retrospective study[J/OL]. BMC Cancer, 2026, 26: 355 [2026-04-13]. https://doi.org/10.1186/s12885-026-15645-8. DOI: 10.1186/s12885-026-15645-8.
[34]
ZHANG H, ZHOU B, ZHANG H, et al. MultiCubeNet: Multitask deep learning for molecular subtyping and prognostic prediction in gliomas[J/OL]. Neurooncol Adv, 2025, 7(1): vdaf079 [2026-04-13]. https://doi.org/10.1093/noajnl/vdaf079. DOI: 10.1093/noajnl/vdaf079.
[35]
NIU W, YAN J, HAO M, et al. MRI transformer deep learning and radiomics for predicting IDH wild type TERT promoter mutant gliomas[J/OL]. NPJ Precis Oncol, 2025, 9(1): 89 [2026-04-13]. https://doi.org/10.1038/s41698-025-00884-y. DOI: 10.1038/s41698-025-00884-y.
[36]
BUZ-YALUG B, TURHAN G, CETIN A I, et al. Identification of IDH and TERTp mutations using dynamic susceptibility contrast MRI with deep learning in 162 gliomas[J/OL]. Eur J Radiol, 2024, 170: 111257 [2026-04-13]. https://doi.org/10.1016/j.ejrad.2023.111257. DOI: 10.1016/j.ejrad.2023.111257.
[37]
ZHANG H, ZHOU B, ZHANG H, et al. Peritumoral Radiomics for Identification of Telomerase Reverse Transcriptase Promoter Mutation in Patients With Glioblastoma Based on Preoperative MRI[J]. Can Assoc Radiol J, 2024, 75(1): 143-152. DOI: 10.1177/08465371231183309.
[38]
TANG C, CHEN L, XU Y, et al. Prediction of TERT mutation status in gliomas using conventional MRI radiogenomic features[J/OL]. Front Neurol, 2024, 15: 1439598 [2026-04-13]. https://doi.org/10.3389/fneur.2024.1439598. DOI: 10.3389/fneur.2024.1439598.
[39]
BAI J, CUI B, LI F, et al. Multiparametric radiomics signature for predicting molecular genotypes in adult-type diffuse gliomas utilizing (18)F-FET PET/MRI[J/OL]. BMC Med Imaging, 2025, 25(1): 187 [2026-04-13]. https://doi.org/10.1186/s12880-025-01729-7. DOI: 10.1186/s12880-025-01729-7.
[40]
WANG J, QU D, ZHANG H, et al. The value of multi-parametric magnetic resonance imaging (MRI) radiomics in predicting isocitrate dehydrogenase (IDH) wildtype with telomerase reverse tranase (TERT) promoter mutation in glioma[J]. Quant Imaging Med Surg, 2025, 15(11): 10640-10653. DOI: 10.21037/qims-24-2192.
[41]
SU Y, GUO W, PAN Y, et al. Machine Learning-Based Preoperative Predicting TERT Promoter Mutation and EGFR Gene Amplification Phenotype in IDH Wild-Type Glioblastoma Using Advanced MR Habitat Imaging[J]. AJNR Am J Neuroradiol, 2026, 47(3): 686-694. DOI: 10.3174/ajnr.A9053.
[42]
ZHAO C, HUANG R, LI X, et al. Radiomics of T2-weighted MRI for pretreatment prediction of prognosis and temozolomide chemosensitivity in glioma[J/OL]. BMC Cancer, 2026, 26(1): 398 [2026-04-13]. https://doi.org/10.1186/s12885-026-15726-8. DOI: 10.1186/s12885-026-15726-8.
[43]
WU G, SHI Z, LI Z, et al. Study of radiochemotherapy decision-making for young high-risk low-grade glioma patients using a macroscopic and microscopic combined radiomics model[J]. Eur Radiol, 2024, 34(5): 2861-2872. DOI: 10.1007/s00330-023-10378-9.
[44]
ZHANG S, BAO J, WANG Y, et al. Integrating handcrafted and deep learning MRI signatures: an interpretable framework for predicting chemotherapy benefit in glioma[J/OL]. NPJ Precis Oncol, 2026 [2026-04-13]. https://doi.org/10.1038/s41698-026-01538-3. DOI: 10.1038/s41698-026-01538-3.
[45]
WANG Y, ZHANG Y, LIN L, et al. Dosiomic and radiomic features within radiotherapy target volume for predicting the treatment response in patients with glioma after radiotherapy[J/OL]. BMC Med Imaging, 2025, 25(1): 402 [2026-04-13]. https://doi.org/10.1186/s12880-025-01955-z. DOI: 10.1186/s12880-025-01955-z.
[46]
CHEN D, ZHANG R, HUANG X, et al. MRI-derived radiomics assessing tumor-infiltrating macrophages enable prediction of immune-phenotype, immunotherapy response and survival in glioma[J/OL]. Biomark Res, 2024, 12(1): 14 [2026-04-13]. https://doi.org/10.1186/s40364-024-00560-6. DOI: 10.1186/s40364-024-00560-6.
[47]
FATHI KAZEROONI A, KRAYA A, RATHI K S, et al. Multiparametric MRI along with machine learning predicts prognosis and treatment response in pediatric low-grade glioma[J/OL]. Nat Commun, 2025, 16(1): 340 [2026-04-13]. https://doi.org/10.1038/s41467-024-55659-z. DOI: 10.1038/s41467-024-55659-z.
[48]
BıYıKLı E, AYBAL T, ASLAN B, et al. Prognostic role of delta radiomics in pediatric pontine diffuse midline gliomas[J/OL]. J Neurooncol, 2026, 176(3): 206 [2026-04-13]. https://doi.org/10.1007/s11060-026-05457-y. DOI: 10.1007/s11060-026-05457-y.
[49]
AHRARI S, ZARAGORI T, ZINSZ A, et al. Application of PET imaging delta radiomics for predicting progression-free survival in rare high-grade glioma[J/OL]. Sci Rep, 2024, 14(1): 3256 [2026-04-13]. https://doi.org/10.1038/s41598-024-53693-x. DOI: 10.1038/s41598-024-53693-x.
[50]
LI X, SONG L, ZHANG H, et al. Predicting postoperative recurrence and survival in glioma patients using enhanced MRI-based delta habitat radiomics: an 8-year retrospective pilot study[J/OL]. World J Surg Oncol, 2025, 23: 104 [2026-04-13]. https://doi.org/10.1186/s12957-025-03760-y. DOI: 10.1186/s12957-025-03760-y.
[51]
YANG X, NIU W, WU K, et al. Diffusion kurtosis imaging-based habitat analysis identifies high-risk molecular subtypes and heterogeneity matching in diffuse gliomas[J]. Ann Clin Transl Neurol, 2024, 11(8): 2073-2087. DOI: 10.1002/acn3.52128.
[52]
ZHU F Y, CHEN W J, CHEN H Y, et al. A novel multimodal framework combining habitat radiomics, deep learning, and conventional radiomics for predicting MGMT gene promoter methylation in Glioma: Superior performance of integrated models[J/OL]. Eur J Radiol, 2025, 192: 112406 [2026-04-13]. https://doi.org/10.1016/j.ejrad.2025.112406. DOI: 10.1016/j.ejrad.2025.112406.
[53]
LIANG W, ZHOU J, HUANG Y, et al. Advancing precision risk stratification in adult diffuse gliomas through DSC-MRI-based habitat analysis[J/OL]. BMC Med Imaging, 2026 [2026-04-13]. https://doi.org/10.1186/s12880-026-02509-7. DOI: 10.1186/s12880-026-02509-7.
[54]
WANG Y, LIN L, HU Z, et al. Global Habitat Analysis With Multi-Graph Fusion Framework of Postoperative MRI for Predicting Radiotherapy Treatment Response in Glioma Patients[J]. IEEE J Biomed Health Inform, 2026, 30(6): 4658-4671. DOI: 10.1109/jbhi.2025.3592811.
[55]
CHENG M, BAI D, LIU W, et al. Clinical value of habitat radiomics within the 2-cm edema zone surrounding the postoperative residual cavity in predicting glioma recurrence[J/OL]. Front Oncol, 2026, 16: 1786939 [2026-04-13]. https://doi.org/10.3389/fonc.2026.1786939. DOI: 10.3389/fonc.2026.1786939.
[56]
MOON H H, PARK J E, KIM N, et al. Prospective longitudinal analysis of physiologic MRI-based tumor habitat predicts short-term patient outcomes in IDH-wildtype glioblastoma[J]. Neuro Oncol, 2025, 27(3): 841-853. DOI: 10.1093/neuonc/noae227.
[57]
WANG Y, LIN L, HU Z, et al. Habitat-Derived Radiomic Features of Planning Target Volume to Determine the Local Recurrence After Radiotherapy in Patients with Gliomas: A Feasibility Study[J]. J Imaging Inform Med, 2026, 39(2): 1632-1644. DOI: 10.1007/s10278-025-01591-7.
[58]
LUO W, CHENG Y, PANG C, et al. Cluster habitat-based diffusion MRI radiomics for differentiation of glioblastoma from solitary brain metastasis[J/OL]. Eur Radiol Exp, 2026, 10: 56 [2026-04-13]. https://doi.org/10.1186/s41747-026-00717-y. DOI: 10.1186/s41747-026-00717-y.
[59]
SUN M N, WANG H, YANG Y Y, et al. Tumor Habitats Based on Multiparametric MRI Distinguish Atypical Glioblastoma From Primary Central Nervous System Lymphoma: Imaging-Pathologic Correlation[J]. J Magn Reson Imaging, 2026, 63(1): 142-154. DOI: 10.1002/jmri.70080.
[60]
JEONG S Y, LEE J, CHOI Y, et al. Tumor habitat analysis using multiparametric MRI as a noninvasive correlate of longitudinal changes in telomerase activity in recurrent IDH-wildtype glioblastoma[J/OL]. Sci Rep, 2026, 16: 16051 [2026-04-13]. https://doi.org/10.1038/s41598-026-47185-3. DOI: 10.1038/s41598-026-47185-3.
[61]
QIAO J, KANG H, RAN Q, et al. Metabolic habitat imaging with hemodynamic heterogeneity predicts individual progression-free survival in high-grade glioma[J/OL]. Clin Radiol, 2024, 79(6): e842-e853 [2026-04-13]. https://doi.org/10.1016/j.crad.2024.02.011. DOI: 10.1016/j.crad.2024.02.011.

PREV Research progress on the correlation between intracranial arterial remodeling and white matter hyperintensities
NEXT Research progress of amide proton transfer imaging in the diagnosis and efficacy evaluation of brain metastases
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn