Share：
Share this content in WeChat
X
[Chinese] [PDF] 172 8
• Review •
Research progress in segmentation methods for heterogeneity of the microenvironment in glioma based on multimodal magnetic resonance imaging
HU Mingxue  GAO Yang 

DOI:10.12015/issn.1674-8034.2025.08.026.


[Abstract] Adult-type diffuse glioma, the most common primary malignant tumor of the central nervous system, exhibits complex tumor heterogeneity, leading to treatment resistance and poor prognosis. Precise segmentation techniques for multi-parametric MRI provide a crucial means of visualizing the heterogeneity of the tumor microenvironment. Traditional imaging segmentation relies on the subjective judgment of neuroradiologists, which is often labor-intensive, time-consuming, and prone to bias. However, with the expanding development of deep learning, these methods have demonstrated superior robustness and accuracy in segmentation performance. Nevertheless, most current models still primarily focus on segmenting the gross tumor region, with limited capability in capturing fine-scale heterogeneous features within the tumor. In recent years, as an emerging heterogeneity analysis method, habitat imaging leverages multi-modal MRI to partition tumors into biologically distinct subregions, further revealing their spatial and temporal heterogeneity. This review summarizes the latest research progress in segmentation methods for the heterogeneous microenvironment of gliomas. First, we outline the common techniques and approaches in the field of glioma subregion segmentation. Subsequently, we emphasize the clinical applications of tumor microenvironment heterogeneity analysis in multi-sequence MRI. Finally, we critically analyze the limitations of existing tumor subregion segmentation approaches and provide insights into future research directions, aiming provide theoretical basis and technical support for individualized precision treatment of adult diffuse glioma.
[Keywords] glioma；magnetic resonance imaging；heterogeneity segmentation；deep learning；habitat imaging；radiomics

HU Mingxue   GAO Yang*  

Department of Radiology, Affiliated Hospital of Inner Mongolia Medical University, Hohhot 010059, China

Corresponding author: GAO Y, E-mail: 1390903990@qq.com

Conflicts of interest   None.

Received  2025-05-12
Accepted  2025-08-08
DOI: 10.12015/issn.1674-8034.2025.08.026
DOI:10.12015/issn.1674-8034.2025.08.026.

[1]
WELLER M, WEN P Y, CHANG S M, et al. Glioma[J/OL]. Nat Rev Dis Primers, 2024, 10(1): 33 [2025-05-10]. https://doi.org/10.1038/s41572-024-00516-y. DOI: 10.1038/s41572-024-00516-y.
[2]
VARN F S, JOHNSON K C, MARTINEK J, et al. Glioma progression is shaped by genetic evolution and microenvironment interactions[J/OL]. Cell, 2022, 185(12): 2184-2199. e16 [2025-05-10]. https://doi.org/10.1016/j.cell.2022.04.038. DOI: 10.1016/j.cell.2022.04.038.
[3]
KHAN F, PANG L, DUNTERMAN M, et al. Macrophages and microglia in glioblastoma: heterogeneity, plasticity, and therapy[J/OL]. J Clin Invest, 2023, 133(1): e163446 [2025-05-10]. https://doi.org/10.1172/JCI163446. DOI: 10.1172/JCI163446.
[4]
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.
[5]
LIU Y H, GAO Y. Implications of habitat imaging-based multisequence MRI in adult-type diffuse glioma[J]. Chin J Magn Reson Imaging, 2023, 14(9): 119-124. DOI: 10.12015/issn.1674-8034.2023.09.022.
[6]
SHOUSHTARI F K, ELAHI R, VALIZADEH G, et al. Current trends in glioma tumor segmentation: A survey of deep learning modules[J/OL]. Physica Medica, 2025, 135: 104988 [2025-05-12]. https://doi.org/10.1016/j.ejmp.2025.104988. DOI: 10.1016/j.ejmp.2025.104988.
[7]
LIU Y, WANG P, WANG S, et al. Heterogeneity matching and IDH prediction in adult-type diffuse gliomas: a DKI-based habitat analysis[J/OL]. Front Oncol, 2023, 13: 1202170 [2025-05-10]. https://doi.org/10.3389/fonc.2023.1202170. DOI: 10.3389/fonc.2023.1202170.
[8]
NI J, ZHANG H, YANG Q, et al. Machine-learning and radiomics-based preoperative prediction of Ki-67 expression in glioma using MRI data[J]. Acad Radiol, 2024, 31(8): 3397-3405. DOI: 10.1016/j.acra.2024.02.009.
[9]
ZHANG T, XU D, LIU J, et al. Prolonged hypoxia alleviates prolyl hydroxylation-mediated suppression of RIPK1 to promote necroptosis and inflammation[J]. Nat Cell Biol, 2023, 25(7): 950-962. DOI: 10.1038/s41556-023-01170-4.
[10]
ERBANI J, BOON M, AKKARI L. Therapy-induced shaping of the glioblastoma microenvironment: macrophages at play[C]//Semin Cancer Biol. Academic Press, 2022, 86: 41-56. DOI: 10.1016/j.semcancer.2022.05.003.
[11]
EKICI M A, BULUT T, TUCER B, et al. Analysis of the mortality probability of preoperative MRI features in malignant astrocytomas[J]. Turk Neurosurg, 2011, 21(3): 271-279. DOI: 10.5137/1019-5149.JTN.3321-10.3.
[12]
REES J H, SMIRNIOTOPOULOS J G, JONES R V, et al. Glioblastoma multiforme: radiologic-pathologic correlation[J]. Radiographics, 1996, 16(6): 1413-1438. DOI: 10.1148/radiographics.16.6.8946545.
[13]
TREVISI G, MANGIOLA A. Current knowledge about the peritumoral microenvironment in glioblastoma[J/OL]. Cancers (Basel), 2023, 15(22): 5460 [2025-05-10]. https://doi.org/10.3390/cancers15225460. DOI: 10.3390/cancers15225460.
[14]
SOLAR P, HENDRYCH M, BARAK M, et al. Blood-brain barrier alterations and edema formation in different brain mass lesions[J/OL]. Front Cell Neurosci, 2022, 16: 922181 [2025-05-10]. https://doi.org/10.3389/fncel.2022.922181. DOI: 10.3389/fncel.2022.922181.
[15]
PETRECCA K, GUIOT M C, PANET-RAYMOND V, et al. Failure pattern following complete resection plus radiotherapy and temozolomide is at the resection margin in patients with glioblastoma[J]. J Neurooncol, 2013, 111: 19-23. DOI: 10.1007/s11060-012-0983-4.
[16]
BEIG N, BERA K, PRASANNA P, et al. Radiogenomic-based survival risk stratification of tumor habitat on Gd-T1w MRI is associated with biological processes in glioblastoma[J]. Clin Cancer Res, 2020, 26(8): 1866-1876. DOI: 10.1158/1078-0432.CCR-19-2556.
[17]
LONG H, ZHANG P, BI Y, et al. MRI radiomic features of peritumoral edema may predict the recurrence sites of glioblastoma multiforme[J/OL]. Front Oncol, 2023, 12: 1042498 [2025-05-10]. https://doi.org/10.3389/fonc.2022.1042498. DOI: 10.3389/fonc.2022.1042498.
[18]
MAZZARA G P, VELTHUIZEN R P, PEARLMAN J L, et al. Brain tumor target volume determination for radiation treatment planning through automated MRI segmentation[J]. Int J Radiat Oncol Biol Phys, 2004, 59(1): 300-312. DOI: 10.1016/j.ijrobp.2004.01.026.
[19]
LIU Z, TONG L, CHEN L, et al. Deep learning based brain tumor segmentation: a survey[J]. Complex Intell Syst, 2023, 9(1): 1001-1026. DOI: 10.1007/s40747-022-00815-5.
[20]
SUN K K, CHEN W, LI Q X, et al. Research progress of multimodal MRI brain tumor image segmentation methods[J]. Chin J Magn Reson Imaging, 2023, 14(11): 164-169, 176. DOI: 10.1007/s40747-022-00815-5.
[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]
PENG S, CHEN W, SUN J, et al. Multi‐scale 3d u‐nets: an approach to automatic segmentation of brain tumor[J]. Int J Imaging Syst Tech, 2020, 30(1): 5-17. DOI: 10.1002/ima.22368.
[23]
LIANG J, YANG C, ZENG L. 3D PSwinBTS: An efficient transformer-based Unet using 3D parallel shifted windows for brain tumor segmentation[J/OL]. Digital Signal Processing, 2022, 131: 103784 [2025-05-10]. https://www.sciencedirect.com/science/article/abs/pii/S1051200422004018. DOI: 10.3390/brainsci12060797.
[24]
LUU H M, PARK S H. Extending nn-UNet for Brain Tumor Segmentation[M]. International MICCAI brainlesion workshop. Cham: Springer International Publishing, 2021: 173-186.
[25]
LI Y, ZHENG K, LI S, et al. A transformer-based multi-task deep learning model for simultaneous infiltrated brain area identification and segmentation of gliomas[J/OL]. Cancer Imaging, 2023, 23(1): 105 [2025-05-10]. https://doi.org/10.1186/s40644-023-00615-1. DOI: 10.1186/s40644-023-00615-1.
[26]
LIU Z, MAO H, WU C Y, et al. A convnet for the 2020s[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022: 11976-11986. DOI: 10.48550/arXiv.2201.03545.
[27]
IQBAL M S, BAJWA U I, RAZA R, et al. Integrated brain tumor segmentation and MGMT promoter methylation status classification from multimodal MRI data using deep learning[J/OL]. Digital Health, 2025, 11: 20552076251332018 [2025-05-12]. https://doi.org/10.1177/20552076251332018. DOI: 10.1177/20552076251332018.
[28]
YU J, LIU Q, XU C, et al. Deep learning-driven modality imputation and subregion segmentation to enhance high-grade glioma grading[J/OL]. BMC Medical Informatics and Decision Making, 2025, 25(1): 200 [2025-05-12]. https://doi.org/10.1186/s12911-025-03029-0. DOI: 10.1186/s12911-025-03029-0.
[29]
ZHANG M. A Brain Tumor Segmentation Method Based on CLIP and 3D U-Net with Cross-Modal Semantic Guidance and Multi-Level Feature Fusion[J/OL]. arxiv preprint arxiv:2507.09966, 2025 [2025-05-12]. https://arxiv.org/abs/2507.09966v1.
[30]
GATENBY R A, GROVE O, GILLIES R J. Quantitative imaging in cancer evolution and ecology[J]. Radiology, 2013, 269(1): 8-14. DOI: 10.1148/radiol.13122697.
[31]
FOLTYN-DUMITRU M, KESSLER T, SAHM F, et al. Cluster-based prognostication in glioblastoma: Unveiling heterogeneity based on diffusion and perfusion similarities[J]. Neuro Oncol, 2024, 26(6): 1099-1108. DOI: 10.1093/neuonc/noad259.
[32]
YE Z, PRICE R L, LIU X, et al. Diffusion histology imaging combining diffusion basis spectrum imaging (DBSI) and machine learning improves detection and classification of glioblastoma pathology[J]. Clin Cancer Res, 2020, 26(20): 5388-5399. DOI: 10.1158/1078-0432.CCR-20-0736.
[33]
LI S, DAI Y, CHEN J, et al. MRI-based habitat imaging in cancer treatment: current technology, applications, and challenges[J/OL]. Cancer Imaging, 2024, 24(1): 107 [2025-05-10]. https://doi.org/10.1186/s40644-024-00758-9. DOI: 10.1186/s40644-024-00758-9.
[34]
SLAVKOVA K P, PATEL S H, CACINI Z, et al. Mathematical modelling of the dynamics of image-informed tumor habitats in a murine model of glioma[J/OL]. Sci Rep, 2023, 13(1): 2916 [2025-05-10]. https://doi.org/10.1038/s41598-023-30010-6. DOI: 10.1038/s41598-023-30010-6.
[35]
WEI R, LU S, LAI S, et al. A subregion-based RadioFusionOmics model discriminates between grade 4 astrocytoma and glioblastoma on multisequence MRI[J/OL]. J Cancer Res Clin Oncol, 2024, 150(2): 73 [2025-05-10]. https://doi.org/10.1007/s00432-023-05603-3. DOI: 10.1007/s00432-023-05603-3.
[36]
WAQAR M, VAN HOUDT P J, HESSEN E, et al. Visualising spatial heterogeneity in glioblastoma using imaging habitats[J/OL]. Front Oncol, 2022, 12: 1037896 [2025-05-10]. https://doi.org/10.3389/fonc.2022.1037896. DOI: 10.3389/fonc.2022.1037896.
[37]
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.
[38]
WANG H, ZENG L, WU H, et al. Preoperative vascular heterogeneity based on dynamic susceptibility contrast MRI in predicting spatial pattern of locally recurrent high-grade gliomas[J]. Eur Radiol, 2024, 34(3): 1982-1993. DOI: 10.1007/s00330-023-10149-6.
[39]
WANG R, GAO Y. Research progress of multimodal MRI radiomics and deep learning in glioma[J]. Chin J Magn Reson Imaging, 2024, 15(7): 165-172. DOI: 10.12015/issn.1674-8034.2024.07.028.
[40]
LI L, XIAO F, WANG S, et al. Preoperative prediction of MGMT promoter methylation in glioblastoma based on multiregional and multi-sequence MRI radiomics analysis[J/OL]. Sci Rep, 2024, 14(1): 16031 [2025-05-10]. https://doi.org/10.1038/s41598-024-66653-2. DOI: 10.1038/s41598-024-66653-2.
[41]
ZHANG H, OUYANG Y, ZHANG Y, et al. Sub-region based radiomics analysis for prediction of isocitrate dehydrogenase and telomerase reverse transcriptase promoter mutations in diffuse gliomas[J/OL]. Clin Radiol, 2024, 79(5): e682-e691 [2025-05-10]. https://doi.org/10.1016/j.crad.2024.01.030. DOI: 10.1016/j.crad.2024.01.030.
[42]
MILLER J J, GONZALEZ CASTRO L N, MCBRAYER S, et al. Isocitrate dehydrogenase (IDH) mutant gliomas: a Society for Neuro-Oncology (SNO) consensus review on diagnosis, management, and future directions[J]. Neuro Oncol, 2023, 25(1): 4-25. DOI: 10.1093/neuonc/noac207.
[43]
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 [2025-05-10]. https://doi.org/10.3390/ijms221910373. DOI: 10.3390/ijms221910373.
[44]
ZHENG J, DONG H, LI M, et al. Prediction of IDH1 gene mutation by a nomogram based on multiparametric and multiregional MR images[J/OL]. Clinics, 2023, 78: 100238 [2025-05-10]. https://doi.org/10.1016/j.clinsp.2023.100238. DOI: 10.1016/j.clinsp.2023.100238.
[45]
LIN D, LIU J, KE C, et al. Radiomics Analysis of Quantitative Maps from Synthetic MRI for Predicting Grades and Molecular Subtypes of Diffuse Gliomas[J]. Clin Neuroradiol, 2024, 34(4): 817-826. DOI: 10.1007/s00062-024-01421-3.
[46]
ÁLVAREZ‐TORRES M M, LÓPEZ‐CERDÁN A, ANDREU Z, et al. Vascular differences between IDH‐wildtype glioblastoma and astrocytoma IDH‐mutant grade 4 at imaging and transcriptomic levels[J/OL]. NMR Biomed, 2023, 36(11): e5004 [2025-05-10]. https://doi.org/10.1002/nbm.5004. DOI: 10.1002/nbm.5004.
[47]
ZHAI X Y, REN J F, CHENG S J, et al. A preliminary study on predicting glioblastoma recurrence and postoperative survival time through MRI imaging radiomics[J]. Chin J Magn Reson Imaging, 2023, 14(12): 26-32. DOI: 10.12015/issn.1674-8034.2023.12.005.
[48]
ELIAS A F, LIN B C, PIGGOTT B J. Ion channels in gliomas—from molecular basis to treatment[J/OL]. Int J Mol Sci, 2023, 24(3): 2530 [2025-05-10]. https://doi.org/10.3390/ijms24032530. DOI: 10.3390/ijms24032530.
[49]
REN J, ZHAI X, YIN H, et al. Multimodality MRI radiomics based on machine learning for identifying true tumor recurrence and treatment-related effects in patients with postoperative glioma[J]. Neurol Ther, 2023, 12(5): 1729-1743. DOI: 10.1007/s40120-023-00524-2.
[50]
KIM M, PARK J E, KIM H S, et al. Spatiotemporal habitats from multiparametric physiologic MRI distinguish tumor progression from treatment-related change in post-treatment glioblastoma[J]. Eur Radiol, 2021, 31: 6374-6383. DOI: 10.1007/s00330-021-07718-y.
[51]
MOON H H, PARK J E, KIM N Y, et al. Prospective longitudinal analysis of physiologic MRI-based tumor habitat predicts short-term patient outcomes in IDH-wildtype glioblastoma[J/OL]. Neuro Oncol, 2024: noae227 [2025-05-10]. https://doi.org/10.1093/neuonc/noae227. DOI: 10.1093/neuonc/noae227.
[52]
GALBÁN C J, CHENEVERT T L, MEYER C R, et al. Prospective analysis of parametric response map-derived MRI biomarkers: identification of early and distinct glioma response patterns not predicted by standard radiographic assessment[J]. Clin Cancer Res, 2011, 17(14): 4751-4760. DOI: 10.1158/1078-0432.CCR-10-2098.
[53]
SHAHEEN A, BUKHARI S T, NADEEM M, et al. Overall survival prediction of glioma patients with multiregional radiomics[J/OL]. Front Neurosci, 2022, 16: 911065 [2025-05-10]. https://doi.org/10.3389/fnins.2022.911065. DOI: 10.3389/fnins.2022.911065.
[54]
GAO M, CHENG J, QIU A, et al. Magnetic resonance imaging (MRI)-based intratumoral and peritumoral radiomics for prognosis prediction in glioma patients[J/OL]. Clin Radiol, 2024, 79(11): e1383-e1393 [2025-05-10]. https://doi.org/10.1016/j.crad.2024.08.005. DOI: 10.1016/j.crad.2024.08.005.
[55]
YANG Y, HAN Y, ZHAO S, et al. Spatial heterogeneity of edema region uncovers survival-relevant habitat of Glioblastoma[J/OL]. Eur J Radiol, 2022, 154: 110423 [2025-05-10]. https://doi.org/10.1016/j.ejrad.2022.110423. DOI: 10.1016/j.ejrad.2022.110423.
[56]
CHO H, KIM H, NAM S Y, et al. Measurement of perfusion heterogeneity within tumor habitats on magnetic resonance imaging and its association with prognosis in breast cancer patients[J/OL]. Cancers, 2022, 14(8): 1858 [2025-05-10]. https://doi.org/10.3390/cancers14081858. DOI: 10.3390/cancers14081858.

PREV Research progress on imaging-based prediction of recurrent risk after thrombectomy in ischemic stroke
NEXT Research progress of Transformer in MRI image segmentation of brain tumors
  


LINK


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