Share this content in WeChat
Diagnosis and prognosis prediction of glioma based on multimodal MRI radiomics and deep learning
WEI Huanhuan  YANG Yan  FU Fangfang  GAO Haiyan  CHEN Lijuan  WU Yaping  BAI Yan  YU Xuan  WANG Meiyun 


[Abstract] Glioma is the most common primary malignant tumor of the central nervous system, which has a rapid progression and poor prognosis. Different histopathological classification/grading and molecular phenotype information lead to the diversity and refractory of glioma. Multimodality MRI techniques such as magnetic resonance spectroscopy (MRS), magnetic resonance fingerprint imaging (MRF), chemical exchange saturation transfer (APT), diffusion-weighted imaging (DWI), diffusion tensor imaging (DTI), and diffusion kurtosis imaging (DKI) can provide information for glioma assessment from a variety of perspectives, and combined artificial intelligence computer-assisted diagnostic techniques can achieve more objective and accurate evaluation and analysis of gliomas and expand the clinical application value of MR techniques. In this paper, the research status of the diagnosis and prognosis prediction of glioma based on multimodal magnetic resonance techniques such as MRS, MRF, APT, DWI, DTI, DKI and radiomics and deep learning were discussed, in order to provide reference for the preoperative evaluation of glioma.
[Keywords] glioma;magnetic resonance;radiomics;multimodality magnetic resonance;radiomics;deep learning;diagnostics;prediction of prognosis

WEI Huanhuan1   YANG Yan1   FU Fangfang2   GAO Haiyan2   CHEN Lijuan2   WU Yaping2   BAI Yan2   YU Xuan2   WANG Meiyun2*  

1 Department of Imagingy, People's Hospital of Zhengzhou University, Zhengzhou 450003, China

2 Department of Imagingy, Henan Provincial People's Hospital, Zhengzhou 450003, China

Corresponding author: Wang MY, E-mail:

Conflicts of interest   None.

Received  2022-12-07
Accepted  2023-05-05
DOI: 10.12015/issn.1674-8034.2023.05.031

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">10.1093/neuonc/noab106">10.1093/neuonc/noab106.
BUDA M, ALBADAWY E A, SAHA A, et al. Deep Radiogenomics of Lower-Grade Gliomas:Convolutional Neural Networks Predict Tumor Genomic Subtypes Using MR Images[J/OL]. Radiol Artif Intell, 2020, 2(1): e180050 [2022-12-06]. DOI: 10.1148/ryai.2019180050">10.1148/ryai.2019180050">10.1148/ryai.2019180050.
MATSUI Y, MARUYAMA T, NITTA M, et al. Prediction of lower-grade glioma molecular subtypes using deep learning[J]. J Neurooncol, 2020, 146(2): 321-327. DOI: 10.1007/s11060-019-03376-9">10.1007/s11060-019-03376-9">10.1007/s11060-019-03376-9.
ATTENBERGER U I, LANGS G. How does Radiomics actually work?-Review[J]. Wie geht Radiomics eigentlich?-Review[J]. Rofo, 2021, 193(6): 652-657. DOI: 10.1055/a-1293-8953">10.1055/a-1293-8953">10.1055/a-1293-8953.
LIN K, CIDAN W, QI Y, et al. Glioma grading prediction using multiparametric magnetic resonance imaging-based radiomics combined with proton magnetic resonance spectroscopy and diffusion tensor imaging[J]. Med Phys, 2022, 49(7): 4419-4429. DOI: 10.1002/mp.15648">10.1002/mp.15648">10.1002/mp.15648.
SHEN G, WANG R, GAO B, et al. The MRI features and prognosis of gliomas associated with IDH1 mutation: a single center study in Southwest China[J]. Front Oncol, 2020, 10: 852. DOI: 10.3389/fonc.2020.00852">10.3389/fonc.2020.00852">10.3389/fonc.2020.00852.
ZOU H, LI C, WANGGOU S, et al. Survival risk prediction models of gliomas based on IDH and 1p/19q[J]. J Cancer, 2020, 11(15): 4297-4307. DOI: 10.7150/jca.43805">10.7150/jca.43805">10.7150/jca.43805.
BUMES E, WIRTZ F P, FELLNER C, et al. Non-Invasive Prediction of IDH Mutation in Patients with Glioma WHO Ⅱ/Ⅲ/Ⅳ Based on F-18-FET PET-Guided In Vivo 1H-Magnetic Resonance Spectroscopy and Machine Learning[J]. Cancers (Basel), 2020, 12(11): 3406. DOI: 10.3390/cancers12113406">10.3390/cancers12113406">10.3390/cancers12113406.
BUMES E, FELLNER C, FELLNER F A, et al. Validation Study for Non-Invasive Prediction of IDH Mutation Status in Patients with Glioma Using In Vivo 1H-Magnetic Resonance Spectroscopy and Machine Learning[J]. Cancers (Basel), 2022, 14(11): 2762. DOI: 10.3390/cancers14112762">10.3390/cancers14112762">10.3390/cancers14112762.
DASTMALCHIAN S, KILINC O, ONYEWADUME L, et al. Radiomic analysis of magnetic resonance fingerprinting in adult brain tumors[J]. Eur J Nucl Med Mol Imaging, 2021, 48: 683-693. DOI: 10.1007/s00259-020-05037-w">10.1007/s00259-020-05037-w">10.1007/s00259-020-05037-w.
TIPPAREDDY C, ONYEWADUME L, SLOAN A E, et al. Novel 3D magnetic resonance fingerprinting radiomics in adult brain tumors: a feasibility study[J]. Eur Radiol, 2023, 33(2): 836-844. DOI: 10.1007/s00330-022-09067-w">10.1007/s00330-022-09067-w">10.1007/s00330-022-09067-w.
RAY K J, SIMARD M A, LARKIN J R, et al. Tumor pH and Protein Concentration Contribute to the Signal of Amide Proton Transfer Magnetic Resonance Imaging Tumor pH and Protein Concentration Contribute to APT MRI[J]. Cancer Res, 2019, 79(7): 1343-1352. DOI: 10.1158/0008-5472.CAN-18-2168">10.1158/0008-5472.CAN-18-2168">10.1158/0008-5472.CAN-18-2168.
JIANG S, ZOU T, EBERHART C G, et al. Predicting IDH mutation status in grade Ⅱ gliomas using amide proton transfer-weighted (APTw) MRI[J]. Magn Reson Med, 2017, 78(3): 1100-1109. DOI: 10.1002/mrm.26820">10.1002/mrm.26820">10.1002/mrm.26820.
HAN Y, WANG W, YANG Y, et al. Amide proton transfer imaging in predicting isocitrate dehydrogenase 1 mutation status of grade Ⅱ/Ⅲ gliomas based on support vector machine[J]. Front Neurosci, 2020, 14: 144. DOI: 10.3389/fnins.2020.00144">10.3389/fnins.2020.00144">10.3389/fnins.2020.00144.
KAMIMURA K, NAKAJO M, YONEYAMA T, et al. Histogram analysis of amide proton transfer-weighted imaging: Comparison of glioblastoma and solitary brain metastasis in enhancing tumors and peritumoral regions[J]. Eur Radiol, 2019, 29: 4133-4140. DOI: 10.1007/s00330-018-5832-1">10.1007/s00330-018-5832-1">10.1007/s00330-018-5832-1.
STEFFEN P, BEYER L S, MCDONOUGH R, et al. Improved detectability of brain stem Ischemia by combining axial and coronal diffusionweighted imaging[J]. Stroke, 2021, 52(5): 1843-1846. DOI: 10.1161/STROKEAHA.120.032457">10.1161/STROKEAHA.120.032457">10.1161/STROKEAHA.120.032457.
HU R, HOCH M J. Application of diffusion weighted imaging and diffusion tensor imaging in the pretreatment and post-treatment of brain tumor[J]. Radiol Clin North Am, 2021, 59(3): 335-347. DOI: 10.1016/j.rcl.2021.01.003">10.1016/j.rcl.2021.01.003">10.1016/j.rcl.2021.01.003.
GIHR G, HORVATH-RIZEA D, KOHLHOF-MEINECKE P, et al. Diffusion weighted imaging in gliomas: a histogram-based approach for tumor characterization[J]. Cancers (Basel), 2022, 14(14): 3393. DOI: 10.3390/cancers14143393">10.3390/cancers14143393">10.3390/cancers14143393.
SOLIMAN R K, ESSA A A, ELHAKEEM A A S, et al. Texture analysis of apparent diffusion coefficient (ADC) map for glioma grading: Analysis of whole tumoral and peri-tumoral tissue[J]. Diagn Interv Imaging, 2021, 102(5): 287-295. DOI: 10.1016/j.diii.2020.12.001">10.1016/j.diii.2020.12.001">10.1016/j.diii.2020.12.001.
SAKAI Y, YANG C, KIHIRA S, et al. MRI radiomic features to predict IDH1 mutation status in gliomas: A machine learning approach using gradient tree boosting[J]. Int J Mol Sci, 2020, 21(21): 8004. DOI: 10.3390/ijms21218004">10.3390/ijms21218004">10.3390/ijms21218004.
TORNIFOGLIO B, STONE A J, JOHNSTON R D, et al. Diffusion tensor imaging and arterial tissue: establishing the influence of arterial tissue microstructure on fractional anisotropy, mean diffusivity and tractography[J]. Sci Rep, 2020, 10(1): 20718-20724. DOI: 10.1038/s41598-020-77675-x">10.1038/s41598-020-77675-x">10.1038/s41598-020-77675-x.
SAMANI Z R, PARKER D, WOLF R, et al. Distinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases[J]. Sci Rep, 2021, 11(1): 1-9. DOI: 10.1038/s41598-021-93804-6">10.1038/s41598-021-93804-6">10.1038/s41598-021-93804-6.
ZHANG Z, XIAO J, WU S, et al. Deep convolutional radiomic features on diffusion tensor images for classification of glioma grades[J]. J Digit Imaging, 2020, 33: 826-837. DOI: 10.1007/s10278-020-00322-4">10.1007/s10278-020-00322-4">10.1007/s10278-020-00322-4.
JELLISON B J, FIELD A S, MEDOW J, et al. Diffusion tensor imaging of cerebral white matter: a pictorial review of physics, fiber tract anatomy, and tumor imaging patterns[J]. AJNR Am J Neuroradiol, 2004, 25(3): 356-369. DOI: 10.1007/s00062-008-8019-3">10.1007/s00062-008-8019-3">10.1007/s00062-008-8019-3.
KUMAR R, SHIJITH K P, DHANALAKSHMI B, et al. Role of regional diffusion tensor imaging (DTI)-derived tensor metrics in the evaluation of intracranial gliomas and its histopathological correlation[J]. Med J Armed Forces India, 2023, 79(2): 173-180. DOI: 10.1016/j.mjafi.2021.05.020">10.1016/j.mjafi.2021.05.020">10.1016/j.mjafi.2021.05.020.
HENDERSON F, ABDULLAH K G, VERMA R, et al. Tractography and the connectome in neurosurgical treatment of gliomas: the premise, the progress, and the potential[J]. Neurosurg Focus, 2020, 48(2): 6-12. DOI: 10.3171/2019.11.FOCUS19785">10.3171/2019.11.FOCUS19785">10.3171/2019.11.FOCUS19785.
YAN J, ZHAO Y, CHEN Y, et al. Deep learning features from diffusion tensor imaging improve glioma stratification and identify risk groups with distinct molecular pathway activities[J]. EBioMedicine, 2021, 72: 103583. DOI: 10.1016/j.ebiom.2021.103583">10.1016/j.ebiom.2021.103583">10.1016/j.ebiom.2021.103583.
XU Z, KE C, LIU J, et al. Diagnostic performance between MR amide proton transfer(APT)and diffusion kurtosis imaging (DKI) in glioma grading and IDH mutation status prediction at 3 T[J]. Eur J Radiol, 2021, 134: 109466. DOI: 10.1016/j.ejrad.2020.109466">10.1016/j.ejrad.2020.109466">10.1016/j.ejrad.2020.109466.
YIN D, CHEN G D, SHENG Y R, et al. Prediction of glioma grading by conventional MRI combined with diffusion kurtosis imaging based on radiomics model[J]. Chinese Imaging Journal of Integrated Traditional and Western Medicine, 2022, 20(2): 117-121, 136. DOI: 10.3969/j.issn.1672-0512.2022.02.004">10.3969/j.issn.1672-0512.2022.02.004">10.3969/j.issn.1672-0512.2022.02.004.
WANG Y F, SHI F X. Value of diffusion kurtosis imaging histogram in grading diagnosis of glioma[J]. Zhejiang Medical Journal, 2022, 44(6): 646-648. DOI: 10.12056/j.issn.1006-2785.2022.44.6.2021-3213">10.12056/j.issn.1006-2785.2022.44.6.2021-3213">10.12056/j.issn.1006-2785.2022.44.6.2021-3213.
VOICU I P, NAPOLITANO A, CAULO M, et al. Developing a Predictive Grading Model for Children with Gliomas Based on Diffusion Kurtosis Imaging Metrics: Accuracy and Clinical Correlations with Patient Survival[J]. Cancers (Basel), 2022, 14(19): 4778. DOI: 10.3390/cancers14194778">10.3390/cancers14194778">10.3390/cancers14194778.
FALK DELGADO A, NILSSON M, VAN WESTEN D, et al. Glioma grade discrimination with MR diffusion kurtosis imaging: a meta-analysis of diagnostic accuracy[J]. Radiology, 2018, 287(1): 119-127. DOI: 10.1148/radiol.2017171315">10.1148/radiol.2017171315">10.1148/radiol.2017171315.
SHI M, MA Y H, REN J, et al. A nomogram model for low-grade glioma prognosis based on diffusion kurtosis imaging histograms[J]. Chin J Magn Reson Imaging, 2022, 13(8): 7-12, 18. DOI: 10.12015/issn.1674-8034.2022.08.002">10.12015/issn.1674-8034.2022.08.002">10.12015/issn.1674-8034.2022.08.002.
LI X, FU P, JIANG M, et al. The diagnostic performance of dynamic contrast-enhanced MRI and its correlation with subtypes of breast cancer[J/OL]. Medicine (Baltimore), 2021, 100(51): e28109 [2022-12-06]. DOI: 10.1097/MD.0000000000028109">10.1097/MD.0000000000028109">10.1097/MD.0000000000028109.
GAUSTAD J V, ROFSTAD E K. Assessment of Intratumor Heterogeneity in Parametric Dynamic Contrast-Enhanced MR Images:A Comparative Study of Novel and Established Methods[J]. Front Oncol, 2021, 11: 722773. DOI: 10.3389/fonc.2021.722773">10.3389/fonc.2021.722773">10.3389/fonc.2021.722773
LI C, SONG L, YIN J. Intratumoral and Peritumoral Radiomics Based on Functional Parametric Maps from Breast DCE-MRI for Prediction of HER-2 and Ki-67 Status[J]. J Magn Reson Imaging, 2021, 54(3): 703-714. DOI: 10.1002/jmri.27651">10.1002/jmri.27651">10.1002/jmri.27651.
WAQAR M, LEWIS D, AGUSHI E, et al. Cerebral and tumoral blood flow in adult gliomas: a systematic review of results from magnetic resonance imaging[J/OL]. Br J Radiol, 2021, 94(1125): 20201450 [2022-12-06]. DOI: 10.1259/bjr.20201450">10.1259/bjr.20201450">10.1259/bjr.20201450.
JING H, YAN X, LI J, et al. The Value of Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) in the Differentiation of Pseudo progression and Recurrence of Intracranial Gliomas[J/OL]. Contrast Media Mol Imaging, 2022, 2022: 5680522 [2022-12-06]. DOI: 10.1155/2022/5680522">10.1155/2022/5680522">10.1155/2022/5680522.
LI S H, SHEN N X, WU D, et al. A Comparative Study Between Tumor Blood Vessels and Dynamic Contrast-enhanced MRI for Identifying Isocitrate Dehydrogenase Gene 1 (IDH1) Mutation Status in Glioma[J]. Curr Med Sci, 2022, 42(3): 650-657. DOI: 10.1007/s11596-022-2563-y">10.1007/s11596-022-2563-y">10.1007/s11596-022-2563-y.
AHN S H, AHN S S, PARK Y W, et al. Association of dynamic susceptibility contrast- and dynamic contrast-enhanced magnetic resonance imaging parameters with molecular marker status in lower-grade gliomas: A retrospective study[J]. Neuroradiol J, 2023, 36(1): 49-58. DOI: 10.1177/19714009221098369">10.1177/19714009221098369">10.1177/19714009221098369.
BRESSLER I, BASHAT D BEN, BUCHSWEILER Y, et al. Model-free dynamic contrast-enhanced MRI analysis: differentiation between active tumor and necrotic tissue in patients with glioblastoma[J]. MAGMA, 2023, 36(1): 33-42. DOI: 10.1007/s10334-022-01045-z">10.1007/s10334-022-01045-z">10.1007/s10334-022-01045-z.
ZHANG J, WANG Y, WANG Y, et al. Perfusion magnetic resonance imaging in the differentiation between glioma recurrence and pseudo progression: a systematic review, meta-analysis and meta-regression[J]. Quant Imaging Med Surg, 2022, 12(10): 4805-4822. DOI: 10.21037/qims-22-32">10.21037/qims-22-32">10.21037/qims-22-32.
QIU J, TAO Z C, DENG K X, et al. Diagnostic accuracy of dynamic contrast-enhanced magnetic resonance imaging for distinguishing pseudo progression from glioma recurrence: a meta-analysis[J]. Chin Med J (Engl), 2021, 134(21): 2535-2543. DOI: 10.1097/CM9.0000000000001445">10.1097/CM9.0000000000001445">10.1097/CM9.0000000000001445.
DÜNDAR T T, CETINKAYA E, YURTSEVER İ, et al. Follow-Up of High-Grade Glial Tumor; Differentiation of Posttreatment Enhancement and Tumoral Enhancement by DCE-MR Perfusion[J/OL]. Contrast Media Mol Imaging, 2022, 2022: 6948422 [2022-12-06]. DOI: 10.1155/2022/6948422">10.1155/2022/6948422">10.1155/2022/6948422.
WU J, LIANG Z, DENG X, et al. Glioma grade discrimination with dynamic contrast-enhanced MRI: An accurate analysis based on MRI guided stereotactic biopsy[J]. Magn Reson Imaging, 2023, 99: 91-97. DOI: 10.1016/j.mri.2023.02.003">10.1016/j.mri.2023.02.003">10.1016/j.mri.2023.02.003.
HU Y, ZHANG N, YU M H, et al. Volume-based histogram analysis of dynamic contrast-enhanced MRI for estimation of gliomas IDH1 mutation status[J]. Eur J Radiol, 2020, 131: 109247. DOI: 10.1016/j.ejrad.2020.109247">10.1016/j.ejrad.2020.109247">10.1016/j.ejrad.2020.109247
ZHANG H W, LYU G W, HE W J, et al. DSC and DCE Histogram Analyses of Glioma Biomarkers, Including IDH, MGMT, and TERT, on Differentiation and Survival[J/OL]. Acad Radiol, 2020, 27(12): e263-e271 [2022-12-06]. DOI: 10.1016/j.acra.2019.12.010">10.1016/j.acra.2019.12.010">10.1016/j.acra.2019.12.010.
WANG J, HU Y, ZHOU X, et al. A radiomics model based on DCE-MRI and DWI may improve the prediction of estimating IDH1 mutation and angiogenesis in gliomas[J]. Eur J Radiol, 2022, 147: 110141. DOI: 10.1016/j.ejrad.2021.110141">10.1016/j.ejrad.2021.110141">10.1016/j.ejrad.2021.110141.
ZHANG H W, LYU G W, HE W J, et al. Differential diagnosis of central lymphoma and high-grade glioma: dynamic contrast-enhanced histogram[J]. Acta Radiol, 2020, 61(9): 1221-1227. DOI: 10.1177/0284185119896519">10.1177/0284185119896519">10.1177/0284185119896519.
PAK E, CHOI K S, CHOI S H, et al. Prediction of Prognosis in Glioblastoma Using Radiomics Features of Dynamic Contrast-Enhanced MRI[J]. Korean J Radiol, 2021, 22(9): 1514-1524. DOI: 10.3348/kjr.2020.1433">10.3348/kjr.2020.1433">10.3348/kjr.2020.1433.

PREV Advances in rs-fMRI combined with machine learning toward the gut-brain axis
NEXT Research status of hypertrophic cardiomyopathy complicated with atrial fibrillation based on cardiac magnetic resonance imaging technology

Tel & Fax: +8610-67113815    E-mail: