Share：
Share this content in WeChat
X
[Chinese] [PDF] 8 1
• Review •
Research progress in multimodal MRI radiomics for predicting molecular typing of gliomas
TANG Yuanbiao  DI Ningning  XU Chang 

DOI:10.12015/issn.1674-8034.2026.01.027.


[Abstract] Glioma, as the most common primary malignant tumor in the central nervous system (CNS), is characterized by high heterogeneity. Accurate molecular subtyping is conducive to formulating treatment strategies and improving prognosis for glioma patients. Although glioma can be diagnosed through surgical procedures or biopsies, such methods are invasive, carrying risks of sampling bias and postoperative complications. Multimodal MRI radiomics, a prominent area of research in disease diagnosis, is capable of integrating the strengths of various MRI imaging techniques. By extracting high-throughput imaging features spanning morphology, texture, functional metabolism and other dimensions, and leveraging machine learning, deep learning as well as statistical analysis tools to build predictive models, this technique has demonstrated significant potential for non-invasive assessment of glioma molecular markers. This paper reviews the recent advances in multimodal MRI radiomics for non-invasively predicting glioma molecular subtypes, points out current research limitations, and suggests future research directions, with the aim of ultimately providing imaging evidence and clinical guidance for preoperative precise diagnosis and the formulation of personalized treatment regimens for glioma patents.
[Keywords] glioma；multimodal；radiomics；magnetic resonance imaging；molecular typing

TANG Yuanbiao   DI Ningning   XU Chang*  

Department of Radiology, Binzhou Medical University Hospital, Binzhou 256603, China

Corresponding author: XU C, E-mail: xuchang3183@126.com

Conflicts of interest   None.

Received  2025-09-01
Accepted  2025-10-31
DOI: 10.12015/issn.1674-8034.2026.01.027
DOI:10.12015/issn.1674-8034.2026.01.027.

[1]
SCHAFF L R, MELLINGHOFF I K. Glioblastoma and Other Primary Brain Malignancies in Adults: A Review[J]. JAMA, 2023, 329(7): 574-587. DOI: 10.1001/jama.2023.0023.
[2]
LOUIS D N, PERRY A, REIFENBERGER G, et al. The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary[J]. Acta Neuropathol, 2016, 131(6): 803-820. DOI: 10.1007/s00401-016-1545-1.
[3]
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.
[4]
HORBINSKI C, BERGER T, PACKER R J, et al. Clinical implications of the 2021 edition of the WHO classification of central nervous system tumours[J]. Nat Rev Neurol, 2022, 18(9): 515-529. DOI: 10.1038/s41582-022-00679-w.
[5]
HAUBOLD J, HOSCH R, PARMAR V, et al. Fully Automated MR Based Virtual Biopsy of Cerebral Gliomas[J/OL]. Cancers (Basel), 2021, 13(24): 6186 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/34944806/. DOI: 10.3390/cancers13246186.
[6]
REDDY S, LUNG T, MUNIYAPPA S, et al. Radiomics and Radiogenomics in Differentiating Progression, Pseudoprogression, and Radiation Necrosis in Gliomas[J/OL]. Biomedicines, 2025, 13(7): 1778 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/40722849/. DOI: 10.3390/biomedicines13071778.
[7]
WANG R, GAO Y. Research progress of multimodal MRI radiomics and deep learning in diagnosis and treatment of glioma[J]. Chin J Magn Reson Imaging, 2024, 15(7): 165-172. DOI: 10.12015/issn.1674-8034.2024.07.028.
[8]
LIANG Q, ZHANG H. Research progress of MRI radiomics in brain glioma[J]. Chin J Magn Reson Imaging, 2024, 15(2): 192-197. DOI: 10.12015/issn.1674-8034.2024.02.031.
[9]
DU P, GENG D Y. Research progress of multimodal MRI radiomics in precise diagnosis and treatment of glioma[J]. Int J Med Radiol, 2023, 46(6): 672-679. DOI: 10.19300/j.2023.Z20681.
[10]
LAMBIN P, RIOS-VELAZQUEZ E, LEIJENAAR R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446. DOI: 10.1016/j.ejca.2011.11.036.
[11]
GILLIES R J, KINAHAN P E, HRICAK H. Radiomics: Images Are More than Pictures, They Are Data[J]. Radiology, 2016, 278(2): 563-577. DOI: 10.1148/radiol.2015151169.
[12]
LIU Z, WANG S, DONG D, et al. The Applications of Radiomics in Precision Diagnosis and Treatment of Oncology: Opportunities and Challenges[J]. Theranostics, 2019, 9(5): 1303-1322. DOI: 10.7150/thno.30309.
[13]
BHAVYA B, ANAND C R, MADHUSOODANAN U K, et al. To be Wild or Mutant: Role of Isocitrate Dehydrogenase 1 (IDH1) and 2-Hydroxy Glutarate (2-HG) in Gliomagenesis and Treatment Outcome in Glioma[J]. Cell Mol Neurobiol, 2020, 40(1): 53-63. DOI: 10.1007/s10571-019-00730-3.
[14]
VILLANUEVA-MEYER J E, WOOD M D, CHOI B S, et al. MRI Features and IDH Mutational Status of Grade II Diffuse Gliomas: Impact on Diagnosis and Prognosis[J]. AJR Am J Roentgenol, 2018, 210(3): 621-628. DOI: 10.2214/AJR.17.18457.
[15]
LIANG H, WANG Z, LI Y, et al. The application value of support vector machine model based on multimodal MRI in predicting IDH-1mutation and Ki-67 expression in glioma[J/OL]. BMC Med Imaging, 2024, 24(1): 244 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/39285364/. DOI: 10.1186/s12880-024-01414-1.
[16]
ZHU Z, SHEN J, LIANG X, et al. Radiomics for predicting grades, isocitrate dehydrogenase mutation, and oxygen 6-methylguanine-DNA methyltransferase promoter methylation of adult diffuse gliomas: combination of structural MRI, apparent diffusion coefficient, and susceptibility-weighted imaging[J]. Quant Imaging Med Surg, 2024, 14(12): 9276-9289. DOI: 10.21037/qims-24-1110.
[17]
YE M, CAO Z, ZHU Z, et al. Integrating quantitative DCE-MRI parameters and radiomic features for improved IDH mutation prediction in gliomas[J/OL]. Front Oncol, 2025, 15: 1530144 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/40134593/. DOI: 10.3389/fonc.2025.1530144.
[18]
YUAN J, SIAKALLIS L, LI H B, et al. Structural- and DTI- MRI enable automated prediction of IDH Mutation Status in CNS WHO Grade 2-4 glioma patients: a deep Radiomics Approach[J/OL]. BMC Med Imaging, 2024, 24(1): 104 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/38702613/. DOI: 10.1186/s12880-024-01274-9.
[19]
BRAT D J, VERHAAK R G W, ALDAPE K D, et al. Comprehensive, Integrative Genomic Analysis of Diffuse Lower-Grade Gliomas[J]. N Engl J Med, 2015, 372(26): 2481-2498. DOI: 10.1056/NEJMoa1402121.
[20]
LI Y, AMMARI S, LAWRANCE L, et al. Radiomics-Based Method for Predicting the Glioma Subtype as Defined by Tumor Grade, IDH Mutation, and 1p/19q Codeletion[J/OL]. Cancers (Basel), 2022, 14(7): 1778 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/35406550/. DOI: 10.3390/cancers14071778.
[21]
VAN DER VOORT S R, INCEKARA F, WIJNENGA M M J, et al. Combined molecular subtyping, grading, and segmentation of glioma using multi-task deep learning[J]. Neuro Oncol, 2023, 25(2): 279-289. DOI: 10.1093/neuonc/noac166.
[22]
LI F, LI Z, XU H, et al. Prediction of 1p/19q state in glioma by integrated deep learning method based on MRI radiomics[J/OL]. BMC Cancer, 2025, 25(1): 1228 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/40722008/. DOI: 10.1186/s12885-025-14454-9.
[23]
BUTLER M, PONGOR L, SU Y, et al. MGMT Status as a Clinical Biomarker in Glioblastoma[J]. Trends Cancer, 2020, 6(5): 380-391. DOI: 10.1016/j.trecan.2020.02.010.
[24]
LIU Y, ZHU Z, ZHOU J, et al. Radiomics prediction of MGMT promoter methylation in adult diffuse gliomas: a combination of structural MRI, DCE, and DTI[J/OL]. Front Neurol, 2025, 16: 1493666 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/39944537/. DOI: 10.3389/fneur.2025.1493666.
[25]
CHEN S, XU Y, YE M, et al. Predicting MGMT Promoter Methylation in Diffuse Gliomas Using Deep Learning with Radiomics[J/OL]. J Clin Med, 2022, 11(12): 3445 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/35743511/. DOI: 10.3390/jcm11123445.
[26]
AGARWAL A, EDGAR M A, DESAI A, et al. Molecular GBM versus Histopathological GBM: Radiology-Pathology-Genetic Correlation and the New WHO 2021 Definition of Glioblastoma[J]. AJNR Am J Neuroradiol, 2024, 45(8): 1006-1012. DOI: 10.3174/ajnr.A8225.
[27]
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 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/11727134/. DOI: 10.1002/cam4.70533.
[28]
LI Y, CHEN L, HUANG L, et al. A radiomics-based nomogram may be useful for predicting telomerase reverse transcriptase promoter mutation status in adult glioblastoma[J/OL]. Brain Behav, 2024, 14(5): e3528 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/11128771/. DOI: 10.1002/brb3.3528.
[29]
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.
[30]
WANG H, ZHANG S, XING X, et al. Radiomic study on preoperative multi-modal magnetic resonance images identifies IDH-mutant TERT promoter-mutant gliomas[J]. Cancer Med, 2023, 12(3): 2524-2537. DOI: 10.1002/cam4.5097.
[31]
WANG H, ZHANG X, LIU J, et al. Clinical roles of EGFR amplification in diffuse gliomas: a real-world study using the 2021 WHO classification of CNS tumors[J/OL]. Front Neurosci, 2024, 18: 1308627 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/38595969/. DOI: 10.3389/fnins.2024.1308627.
[32]
WANG D, HAN Q, YANG S, et al. A DTI-based radiomics model for predicting epidermal growth factor receptor (EGFR) amplification in adult IDH1-wild glioblastomas[J]. Acta Radiol, 2024, 65(10): 1291-1299. DOI: 10.1177/02841851241265164.
[33]
PEASE M, GERSEY Z C, AK M, et al. Pre-operative MRI radiomics model non-invasively predicts key genomic markers and survival in glioblastoma patients[J]. J Neurooncol, 2022,160(1): 253-263. DOI: 10.1007/s11060-022-04150-0.
[34]
SENHAJI N, SQUALLI HOUSSAINI A, LAMRABET S, et al. Molecular and Circulating Biomarkers in Patients with Glioblastoma[J/OL]. Int J Mol Sci, 2022, 23(13): 7474 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/9267689/. DOI: 10.3390/ijms23137474.
[35]
KONG X, MAO Y, XI F, et al. Development of a nomogram based on radiomics and semantic features for predicting chromosome 7 gain/chromosome 10 loss in IDH wild-type histologically low-grade gliomas[J/OL]. Front Oncol, 2023, 13: 1196614 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/37781185/. DOI: 10.3389/fonc.2023.1196614.
[36]
CALABRESE E, RUDIE J D, RAUSCHECKER A M, et al. Combining radiomics and deep convolutional neural network features from preoperative MRI for predicting clinically relevant genetic biomarkers in glioblastoma[J/OL]. Neurooncol Adv, 2022, 4(1): vdac060 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/35611269/. DOI: 10.1093/noajnl/vdac060.
[37]
WETZEL E A, NOHMAN A I, HSIEH A L, et al. A multi-center, clinical analysis of IDH-mutant gliomas, WHO Grade 4: implications for prognosis and clinical trial design[J]. J Neurooncol, 2025, 171(2): 373-381. DOI: 10.1007/s11060-024-04852-7.
[38]
YANG J, LI L, LUO T, et al. Cyclin-Dependent Kinase Inhibitor 2A/B Homozygous Deletion Prediction and Survival Analysis[J/OL]. Brain Sci, 2023, 13(4): 548 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/37190513/. DOI: 10.3390/brainsci13040548.
[39]
ZHANG L, WANG R, GAO J, et al. A novel MRI-based deep learning networks combined with attention mechanism for predicting CDKN2A/B homozygous deletion status in IDH-mutant astrocytoma[J]. Eur Radiol, 2024, 34(1): 391-399. DOI: 10.1007/s00330-023-09944-y.
[40]
GAO J, LIU Z, PAN H, et al. Preoperative Discrimination of CDKN2A/B Homozygous Deletion Status in Isocitrate Dehydrogenase-Mutant Astrocytoma: A Deep Learning-Based Radiomics Model Using MRI[J]. J Magn Reson Imaging, 2024, 59(5): 1655-1664. DOI: 10.1002/jmri.28945.
[41]
PARK Y W, HAN K, KIM S H. Response to "Medical Statistics Unlock the Gateway to Further Research: Using Deep Learning to Predict CDKN2A/B Homozygous Deletion in Isocitrate Dehydrogenase-Mutant Astrocytoma"[J]. Korean J Radiol, 2023, 24(12): 1306-1308. DOI: 10.3348/kjr.2023.0940.
[42]
HARIHARAN S, WHITFIELD B T, PIROZZI C J, et al. Interplay between ATRX and IDH1 mutations governs innate immune responses in diffuse gliomas[J/OL]. Nat Commun, 2024, 15(1): 730 [2025-08-10]. https://doi.org/10.1038/s41467-024-44932-w. DOI: 10.1038/s41467-024-44932-w.
[43]
PLADEVALL-MORERA D, CASTEJÓN-GRIÑÁN M, AGUILERA P, et al. ATRX-Deficient High-Grade Glioma Cells Exhibit Increased Sensitivity to RTK and PDGFR Inhibitors[J/OL]. Cancers (Basel), 2022, 14(7): 1790 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/35406561/. DOI: 10.3390/cancers14071790.
[44]
NACUL MORA N G, AKKURT B H, KASAP D, et al. Comparison of MRI Sequences to Predict ATRX Status Using Radiomics-Based Machine Learning[J/OL]. Diagnostics (Basel), 2023, 13(13): 2216 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/10341337/. DOI: 10.3390/diagnostics13132216.
[45]
LIN X, WANG C, ZHENG J, et al. Image Omics Nomogram Based on Incoherent Motion Diffusion-Weighted Imaging in Voxels Predicts ATRX Gene Mutation Status of Brain Glioma Patients[J]. J Imaging Inform Med, 2024, 37(4): 1336-1345. DOI: 10.1007/s10278-024-00984-4.
[46]
CALABRESE E, VILLANUEVA-MEYER J E, CHA S. A fully automated artificial intelligence method for non-invasive, imaging-based identification of genetic alterations in glioblastomas[J/OL]. Sci Rep, 2020, 10(1): 11852 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/7366666/. DOI: 10.1038/s41598-020-68857-8.
[47]
LIU Z, XU X, ZHANG W, et al. A fusion model integrating magnetic resonance imaging radiomics and deep learning features for predicting alpha-thalassemia X-linked intellectual disability mutation status in isocitrate dehydrogenase-mutant high-grade astrocytoma: a multicenter study[J]. Quant Imaging Med Surg, 2024, 14(1): 251-263. DOI: 10.21037/qims-23-807.
[48]
MUGIARTO T S, MALUEKA R G, CEMPAKA R, et al. The Association between p53 Expression and Histopathology Grade of Astrocytoma[J]. Asian Pac J Cancer Prev, 2025, 26(7): 2521-2526. DOI: 10.31557/APJCP.2025.26.7.2521.
[49]
LI J, LAN Z, ZHANG X, et al. Predicting p53 Status in IDH-Mutant Gliomas Using MRI-Based Radiomic Model[J/OL]. Cancer Med, 2025, 14(15): e71063 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/40747552/. DOI: 10.1002/cam4.71063.
[50]
SINGH G, SINGH A, BAE J, et al. New frontiers in domain-inspired radiomics and radiogenomics: increasing role of molecular diagnostics in CNS tumor classification and grading following WHO CNS-5 updates[J/OL]. Cancer Imaging, 2024, 24(1): 133 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/11460168/. DOI: 10.1186/s40644-024-00769-6.
[51]
SHAO H, GONG J, SU X, et al. MRI characteristics of H3 G34-mutant diffuse hemispheric gliomas and possible differentiation from IDH-wild-type glioblastomas in adolescents and young adults[J]. J Neurosurg Pediatr, 2024, 33(3): 236-244. DOI: 10.3171/2023.10.PEDS23235.
[52]
CHIANG J, DIAZ A K, MAKEPEACE L, et al. Clinical, imaging, and molecular analysis of pediatric pontine tumors lacking characteristic imaging features of DIPG[J/OL]. Acta Neuropathol Commun, 2020, 8(1): 57 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/7181591/. DOI: 10.1186/s40478-020-00930-9.
[53]
LV K, CHEN H, CAO X, et al. Development and validation of a machine learning algorithm for predicting diffuse midline glioma, H3 K27-altered, H3 K27 wild-type high-grade glioma, and primary CNS lymphoma of the brain midline in adults[J]. J Neurosurg, 2023, 139(2): 393-401. DOI: 10.3171/2022.11.JNS221544.
[54]
GUO W, SHE D, XING Z, et al. Multiparametric MRI-Based Radiomics Model for Predicting H3 K27M Mutant Status in Diffuse Midline Glioma: A Comparative Study Across Different Sequences and Machine Learning Techniques[J/OL]. Front Oncol, 2022, 12: 796583 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/35311083/. DOI: 10.3389/fonc.2022.796583.
[55]
XING Y L, PANOVSKA D, PARK J, et al. BRAF/MEK inhibition induces cell state transitions boosting immune checkpoint sensitivity in BRAF(V600E)-mutant glioma[J/OL]. Cell Rep Med, 2025, 6(6): 102183 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/40505659/. DOI: 10.1016/j.xcrm.2025.102183.
[56]
KUDUS K, WAGNER M W, NAMDAR K, et al. Increased confidence of radiomics facilitating pretherapeutic differentiation of BRAF-altered pediatric low-grade glioma[J]. Eur Radiol, 2024, 34(4): 2772-2781. DOI: 10.1007/s00330-023-10267-1.
[57]
KUDUS K, WAGNER M W, NAMDAR K, et al. Beyond hand-crafted features for pretherapeutic molecular status identification of pediatric low-grade gliomas[J/OL]. Sci Rep, 2024, 14(1): 19102 [2025-08-10]. https://pubmed.ncbi.nlm.nih.gov/39154039/. DOI: 10.1038/s41598-024-69870-x.

PREV Research progress of convolutional neural network and vision transformer in gliomas
NEXT Advances in artificial intelligence for MRI of carotid artery vulnerable plaques​
  


LINK


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