Share：
Share this content in WeChat
X
[Chinese][PDF]3574
• Clinical Article •
Risk stratification prediction of glioblastoma based on multi-sequence MRI radiomics analysis
NIU Wenju  XU Huaiwen  GAO Yuxiang  WANG Xiaochun  TAN Yan  ZHANG Hui  YANG Guoqiang 

Cite this article as: NIU W J, XU H W, GAO Y X, et al. Risk stratification prediction of glioblastoma based on multi-sequence MRI radiomics analysis[J]. Chin J Magn Reson Imaging, 2024, 15(3): 31-36, 42. DOI:10.12015/issn.1674-8034.2024.03.006.


[Abstract] Objective To develop a glioblastoma (GBM) overall survival (OS) prediction model using multi-sequence MRI radiomics method.Materials and Methods This study retrospectively collected data from 309 patients with GBM in the TCIA/TCGA (The Cancer Imaging Archive/The Cancer Genome Atlas) public database, and extracted 10 128 radiomics features from preoperative post-contrast enhanced T1-weighted (T1CE) and T2-weighted fluid attenuation inversion recovery (T2 FLAIR) sequences for three regions of interest: necrosis area, tumor area, and edema area. Correlation analysis, principal component analysis (PCA) for dimensionality reduction, and least absolute shrinkage and selection operator-cox proportional-hazards (LASSO-Cox) regression were used to screen radiomics features significantly related to OS and calculate a Risk-score as a radiomics signature. Kaplan-Meier (KM) survival analysis and Log-rank test were used to compare the survival differences between high-risk and low-risk groups. A clinical-radiomics combined model and nomogram were constructed using multivariate Cox proportional-hazards (Cox) regression and evaluated using concordance index (C-index), which was compared with the clinical model.Results Based on the 16 radiomics features selected from the training set, a Risk-score was calculated and patients were divided into high- and low-risk groups based on this Risk-score, using both the training and testing sets. Log-rank testing showed a significant difference in survival probability between the high- and low-risk groups. Univariate Cox regression identified Risk-score, age, and O6-methylguanine-DNA methyltransferase (MGMT) status as significant risk factors for OS in GBM. Multivariate Cox regression was used to build clinical model and a clinical-radiomics combined model, and it was found that the clinical-radiomics combined model (training set: C-index=0.768, testing set: C-index=0.724) outperformed the radiomics model (training set: C-index=0.744, testing set: C-index=0.710) and the clinical model (training set: C-index=0.659, testing set: C-index=0.653).Conclusions Radiomics signature can serve as independent prognostic factor for OS of GBM, and the combined model constructed by combining clinical pathological information and radiomics signature can better assist in risk stratification and survival prediction of GBM, which holds significant clinical value.
[Keywords] glioblastoma；magnetic resonance imaging；overall survival；radiomics；prediction model

NIU Wenju1   XU Huaiwen1   GAO Yuxiang1   WANG Xiaochun2, 1   TAN Yan2, 1   ZHANG Hui2, 1   YANG Guoqiang2, 1*  

1 School of Medical Imaging, Shanxi Medical University, Taiyuan 030001, China

2 Department of Radiology, First Hospital of Shanxi Medical University, Taiyuan 030001, China

Corresponding author: YANG G Q, E-mail: doctor_ygq@163.com

Conflicts of interest   None.

Received  2023-10-07
Accepted  2024-01-31
DOI: 10.12015/issn.1674-8034.2024.03.006
Cite this article as: NIU W J, XU H W, GAO Y X, et al. Risk stratification prediction of glioblastoma based on multi-sequence MRI radiomics analysis[J]. Chin J Magn Reson Imaging, 2024, 15(3): 31-36, 42. DOI:10.12015/issn.1674-8034.2024.03.006.

[1]
OSTROM Q T, CIOFFI G, WAITE K, et al. CBTRUS Statistical Report: Primary Brain and Other Central Nervous System Tumors Diagnosed in the United States in 2014-2018[J]. Neuro Oncol, 2021, 23(12Suppl 2): iii1-iii105.
[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 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/34638714/. DOI: 10.3390/ijms221910373.
[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]
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 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/35873825/. DOI: 10.3389/fnins.2022.911065.
[5]
HEGI M E, DISERENS A C, GORLIA T, et al. MGMT gene silencing and benefit from temozolomide in glioblastoma[J]. N Engl J Med, 2005, 352(10): 997-1003. DOI: 10.1056/NEJMoa043331.
[6]
LIU D, CHEN J, GE H, et al. Radiogenomics to characterize the immune-related prognostic signature associated with biological functions in glioblastoma[J]. Eur Radiol, 2023, 33(1): 209-220. DOI: 10.1007/s00330-022-09012-x.
[7]
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 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/35406550/. DOI: 10.3390/cancers14071778.
[8]
HASS R, VON DER OHE J, Ungefroren H. Impact of the Tumor Microenvironment on Tumor Heterogeneity and Consequences for Cancer Cell Plasticity and Stemness[J/OL]. Cancers (Basel), 2020, 12(12): 3716 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/33322354/. DOI: 10.3390/cancers12123716.
[9]
ZENG C, SONG X, ZHANG Z, et al. Dissection of transcriptomic and epigenetic heterogeneity of grade 4 gliomas: implications for prognosis[J/OL]. Acta Neuropathol Commun, 2023, 11(1): 133 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/37580817/. DOI: 10.1186/s40478-023-01619-5.
[10]
HAGIWARA A, TATEKAWA H, YAO J, et al. Visualization of tumor heterogeneity and prediction of isocitrate dehydrogenase mutation status for human gliomas using multiparametric physiologic and metabolic MRI[J/OL]. Sci Rep, 2022, 12(1): 1078 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/35058510/. DOI: 10.1038/s41598-022-05077-2.
[11]
LUO J, PAN M, MO K, et al. Emerging role of artificial intelligence in diagnosis, classification and clinical management of glioma[J]. Semin Cancer Biol, 2023, 91: 110-123. DOI: 10.1016/j.semcancer.2023.03.006.
[12]
LI C, LI W, LIU C, et al. Artificial intelligence in multiparametric magnetic resonance imaging: A review[J/OL]. Med Phys, 2022, 49(10): e1024-e1054 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/35980348/. DOI: 10.1002/mp.15936.
[13]
PAPP L, PÖTSCH N, GRAHOVAC M, et al. Glioma Survival Prediction with Combined Analysis of In Vivo (11)C-MET PET Features, Ex Vivo Features, and Patient Features by Supervised Machine Learning[J]. J Nucl Med, 2018, 59(6): 892-899. DOI: 10.2967/jnumed.117.202267.
[14]
KHALILI N, KAZEROONI A F, FAMILIAR A, et al. Radiomics for characterization of the glioma immune microenvironment[J/OL]. NPJ Precis Oncol, 2023, 7(1): 59 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/37337080/. DOI: 10.1038/s41698-023-00413-9.
[15]
TOMASZEWSKI M R, GILLIES R J. The biological meaning of radiomic features[J]. Radiology, 2021, 298(3): 505-516. DOI: 10.1148/radiol.2021202553.
[16]
LIU X, LI Y, QIAN Z, et al. A radiomic signature as a non-invasive predictor of progression-free survival in patients with lower-grade gliomas[J]. Neuroimage Clin, 2018, 20: 1070-1077. DOI: 10.1016/j.nicl.2018.10.014.
[17]
PRASANNA P, PATEL J, PARTOVI S, et al. Radiomic features from the peritumoral brain parenchyma on treatment-naïve multi-parametric MR imaging predict long versus short-term survival in glioblastoma multiforme: Preliminary findings[J]. Eur Radiol, 2017, 27(10): 4188-4197. DOI: 10.1007/s00330-016-4637-3.
[18]
ZHOU H, VALLIÈRES M, BAI H X, et al. MRI features predict survival and molecular markers in diffuse lower-grade gliomas[J]. Neuro Oncol, 2017, 19(6): 862-870. DOI: 10.1093/neuonc/now256.
[19]
QIN J B, LIU Z, ZHANG H, et al. Grading of gliomas by using radiomic features on multiple magnetic resonance imaging (MRI) sequences[J]. Med Sci Monit, 2017, 23: 2168-2178. DOI: 10.12659/msm.901270.
[20]
TAN Y, MU W, WANG X C, et al. Improving survival prediction of high-grade glioma via machine learning techniques based on MRI radiomic, genetic and clinical risk factors[J/OL]. Eur J Radiol, 2019, 120: 108609 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/31606714/. DOI: 10.1016/j.ejrad.2019.07.010.
[21]
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 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/35777079/. DOI: 10.1016/j.ejrad.2022.110423.
[22]
YAN J, ZHANG B, ZHANG S, et al. Quantitative MRI-based radiomics for noninvasively predicting molecular subtypes and survival in glioma patients[J/OL]. NPJ Precis Oncol, 2021, 5(1): 72 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/34312469/. DOI: 10.1038/s41698-021-00205-z.
[23]
MISHRA D, DASH R, RATH A K, et al. Feature selection in gene expression data using principal component analysis and rough set theory[J]. Adv Exp Med Biol, 2011, 696: 91-100. DOI: 10.1007/978-1-4419-7046-6_10.
[24]
NASRULLAH N, SANG J, ALAM M S, et al. Automated lung nodule detection and classification using deep learning combined with multiple strategies[J/OL]. Sensors (Basel), 2019, 19(17): 3722 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/31466261/. DOI: 10.3390/s19173722.
[25]
ZHU X, SUK H I, LEE S W, et al. Subspace regularized sparse multitask learning for multiclass neurodegenerative disease identification[J]. IEEE Trans Biomed Eng, 2016, 63(3): 607-618. DOI: 10.1109/TBME.2015.2466616.
[26]
LE V H, MINH T, KHA Q H, et al. A transfer learning approach on MRI-based radiomics signature for overall survival prediction of low-grade and high-grade gliomas[J]. Med Biol Eng Comput, 2023, 61(10): 2699-2712. DOI: 10.1007/s11517-023-02875-2.
[27]
MAO X, QIN X, LI L, et al. A 15-long non-coding RNA signature to improve prognosis prediction of cervical squamous cell carcinoma[J]. Gynecol Oncol, 2018, 149(1): 181-187. DOI: 10.1016/j.ygyno.2017.12.011.
[28]
XUE M, SHANG J, CHEN B, et al. Identification of prognostic signatures for predicting the overall survival of uveal melanoma patients[J]. J Cancer, 2019, 10(20): 4921-4931. DOI: 10.7150/jca.30618.
[29]
HUANG H, ZHANG W, FANG Y, et al. Overall survival prediction for gliomas using a novel compound approach[J/OL]. Front Oncol, 2021, 11: 724191 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/34490121/. DOI: 10.3389/fonc.2021.724191.
[30]
JABERIPOUR M, SOLIMAN H, SAHGAL A, et al. A priori prediction of local failure in brain metastasis after hypo-fractionated stereotactic radiotherapy using quantitative MRI and machine learning[J/OL]. Sci Rep, 2021, 11(1): 21620 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/34732781/. DOI: 10.1038/s41598-021-01024-9.
[31]
CHOI Y, NAM Y, JANG J, et al. Radiomics may increase the prognostic value for survival in glioblastoma patients when combined with conventional clinical and genetic prognostic models[J]. Eur Radiol, 2021, 31(4): 2084-2093. DOI: 10.1007/s00330-020-07335-1.
[32]
CHOUGULE T, GUPTA R K, SAINI J, et al. Radiomics signature for temporal evolution and recurrence patterns of glioblastoma using multimodal magnetic resonance imaging[J/OL]. NMR Biomed, 2022, 35(3): e4647 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/34766380/. DOI: 10.1002/nbm.4647.
[33]
GONG J, ZHANG W, HUANG W, et al. CT-based radiomics nomogram may predict local recurrence-free survival in esophageal cancer patients receiving definitive chemoradiation or radiotherapy: A multicenter study[J]. Radiother Oncol, 2022, 174: 8-15. DOI: 10.1016/j.radonc.2022.06.010.
[34]
HAN W, QIN L, BAY C, et al. Deep transfer learning and radiomics feature prediction of survival of patients with high-grade gliomas[J]. AJNR Am J Neuroradiol, 2020, 41(1): 40-48. DOI: 10.3174/ajnr.A6365.
[35]
NERO C, BOLDRINI L, LENKOWICZ J, et al. Deep-learning to predict BRCA mutation and survival from digital H&E slides of epithelial ovarian cancer[J/OL]. Int J Mol Sci, 2022, 23(19): 11326 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/36232628/. DOI: 10.3390/ijms231911326.
[36]
WANG R, DAI W, GONG J, et al. Development of a novel combined nomogram model integrating deep learning-pathomics, radiomics and immunoscore to predict postoperative outcome of colorectal cancer lung metastasis patients[J/OL]. J Hematol Oncol, 2022, 15(1): 11 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/35073937/. DOI: 10.1186/s13045-022-01225-3.
[37]
ZHANG X, ZHANG Y, ZHANG G, et al. Deep learning with radiomics for disease diagnosis and treatment: Challenges and potential[J/OL]. Front Oncol, 2022, 12: 773840 [2023-10-07]. https://pubmed.ncbi.nlm.nih.gov/35251962/. DOI: 10.3389/fonc.2022.773840.
[38]
CURRIE G, HAWK K E, ROHREN E, et al. Machine learning and deep learning in medical imaging: Intelligent imaging[J]. J Med Imaging Radiat Sci, 2019, 50(4): 477-487. DOI: 10.1016/j.jmir.2019.09.005.
[39]
GORE S, CHOUGULE T, JAGTAP J, et al. A review of radiomics and deep predictive modeling in glioma characterization[J]. Acad Radiol, 2021, 28(11): 1599-1621. DOI: 10.1016/j.acra.2020.06.016.

PREV The correlation between symptomatic carotid atherosclerotic plaques and short-term mRS score after ischemic stroke
NEXT Differential diagnosis of angiomatous meningioma and atypical meningioma based on contrast enhanced T1-weighted images histogram analysis
  


LINK


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