Advertisement

Neuroradiology

, Volume 61, Issue 11, pp 1229–1237 | Cite as

Radiogenomic analysis of PTEN mutation in glioblastoma using preoperative multi-parametric magnetic resonance imaging

  • Yiming Li
  • Yuchao Liang
  • Zhiyan Sun
  • Kaibin Xu
  • Xing Fan
  • Shaowu Li
  • Zhong Zhang
  • Tao Jiang
  • Xing Liu
  • Yinyan WangEmail author
Diagnostic Neuroradiology

Abstract

Purpose

PTEN mutation status is a pivotal biomarker for glioblastoma. This study aimed to establish a radiomic signature to predict PTEN mutation status in patients with glioblastoma, and to investigate the genetic background behind this radiomic signature.

Methods

In this study, a total of 862 radiomic features were extracted from each patient. The training (n = 69) and validation (n = 40) sets were retrospectively collected from the Cancer Genome Atlas and the Chinese Glioma Genome Atlas, respectively. The minimum redundancy maximum relevance (mRMR) algorithm was used to select the best predictive features of PTEN status. A machine learning model was then built with the selected features using a support vector machine classifier. The predictive performance of each selected feature and the complete model were evaluated via the area under the curve from receiver operating characteristic analysis in both the training and validation sets. The genetic background underlying the radiomic signature was determined using radiogenomic analysis.

Results

Six features were selected using the mRMR algorithm, including two features derived from contrast-enhanced images and four features derived from T2-weighted images. The predictive performance of the machine learning model for the training and validation sets were 0.925 and 0.787, respectively, which were better than the individual features. Radiogenomics analysis revealed that the PTEN-associated biological processes could be described using the radiomic signature.

Conclusion

These results show that radiomic features derived from preoperative MRI can predict PTEN mutation status in glioblastoma patients, thus providing a novel noninvasive imaging biomarker.

Keywords

Glioblastoma Radiogenomics Phosphatase and tensin homolog (PTEN) Machine learning 

Abbreviations

PTEN

Phosphatase and tensin homolog

mRMR

Minimum redundancy maximum relevance

CE

Contrast enhancement

T2

T2-weighted

MR

Magnetic resonance

TCGA

The Cancer Genome Atlas

AUC

Area under the curve

SVM

Support vector machine

ROC

Receiver operating characteristic

DAVID

Database for Annotation, Visualization and Integrated Discovery

Notes

Funding

This study was funded by the National Natural Science Foundation of China (No. 81601452), the Beijing Natural Science Foundation (No. 7174295), the National Key Research and Development Plan (No. 2016YFC0902500) and the National Key Research and Development Program of China (2018YFC0115604).

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

All procedures performed in the studies involving human participants were in accordance with the ethical standards of the institutional research committee (Clinical Research Adoption Committee) and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.

Informed consent

Informed consent was obtained from all individual participants included in the study.

Supplementary material

234_2019_2244_MOESM1_ESM.xlsx (13 kb)
Supplementary Table 1 (XLSX 12 kb)
234_2019_2244_MOESM2_ESM.docx (23 kb)
Supplementary Table 2 (DOCX 23 kb)

References

  1. 1.
    Korfiatis P, Kline TL, Coufalova L, Lachance DH, Parney IF, Carter RE, Buckner JC, Erickson BJ (2016) MRI texture features as biomarkers to predict MGMT methylation status in glioblastomas. Med Phys 43(6):2835–2844.  https://doi.org/10.1118/1.4948668 CrossRefPubMedPubMedCentralGoogle Scholar
  2. 2.
    Chai RC, Liu YQ, Zhang KN, Wu F, Zhao Z, Wang KY, Jiang T, Wang YZ (2019) A novel analytical model of MGMT methylation pyrosequencing offers improved predictive performance in patients with gliomas. Mod Pathol 32(1):4–15.  https://doi.org/10.1038/s41379-018-0143-2 CrossRefPubMedGoogle Scholar
  3. 3.
    Jiang T, Mao Y, Ma W, Mao Q, You Y, Yang X, Jiang C, Kang C, Li X, Chen L, Qiu X, Wang W, Li W, Yao Y, Li S, Li S, Wu A, Sai K, Bai H, Li G, Chen B, Yao K, Wei X, Liu X, Zhang Z, Dai Y, Lv S, Wang L, Lin Z, Dong J, Xu G, Ma X, Cai J, Zhang W, Wang H, Chen L, Zhang C, Yang P, Yan W, Liu Z, Hu H, Chen J, Liu Y, Yang Y, Wang Z, Wang Z, Wang Y, You G, Han L, Bao Z, Liu Y, Wang Y, Fan X, Liu S, Liu X, Wang Y, Wang Q, Chinese Glioma Cooperative G (2016) CGCG clinical practice guidelines for the management of adult diffuse gliomas. Cancer Lett 375(2):263–273.  https://doi.org/10.1016/j.canlet.2016.01.024 CrossRefPubMedGoogle Scholar
  4. 4.
    Katsetos CD, Draberova E, Smejkalova B, Reddy G, Bertrand L, de Chadarevian JP, Legido A, Nissanov J, Baas PW, Draber P (2007) Class III beta-tubulin and gamma-tubulin are co-expressed and form complexes in human glioblastoma cells. Neurochem Res 32(8):1387–1398.  https://doi.org/10.1007/s11064-007-9321-1 CrossRefPubMedGoogle Scholar
  5. 5.
    Koul D (2008) PTEN signaling pathways in glioblastoma. Cancer Biol Ther 7(9):1321–1325CrossRefGoogle Scholar
  6. 6.
    Louis DN, Ohgaki H, Wiestler OD, Cavenee WK, Burger PC, Jouvet A, Scheithauer BW, Kleihues P (2007) The 2007 WHO classification of tumours of the central nervous system. Acta Neuropathol 114(2):97–109.  https://doi.org/10.1007/s00401-007-0243-4 CrossRefPubMedPubMedCentralGoogle Scholar
  7. 7.
    Myung JK, Cho HJ, Park C-K, Kim S-K, Phi JH, Park S-H (2012) IDH1 mutation of gliomas with long-term survival analysis. Oncol Rep 28(5):1639–1644.  https://doi.org/10.3892/or.2012.1994 CrossRefPubMedGoogle Scholar
  8. 8.
    Yang Y, Shao N, Luo G, Li L, Zheng L, Nilsson-Ehle P, Xu N (2010) Mutations of PTEN gene in gliomas correlate to tumor differentiation and short-term survival rate. Anticancer Res 30(3):981–985PubMedGoogle Scholar
  9. 9.
    Benitez JA, Ma J, D'Antonio M, Boyer A, Camargo MF, Zanca C, Kelly S, Khodadadi-Jamayran A, Jameson NM, Andersen M, Miletic H, Saberi S, Frazer KA, Cavenee WK, Furnari FB (2017) PTEN regulates glioblastoma oncogenesis through chromatin-associated complexes of DAXX and histone H3.3. Nat Commun 8:15223.  https://doi.org/10.1038/ncomms15223 CrossRefPubMedPubMedCentralGoogle Scholar
  10. 10.
    Xu PF, Yang JA, Liu JH, Yang X, Liao JM, Yuan FE, Liu BH, Chen QX (2019) PI3Kbeta inhibitor AZD6482 exerts antiproliferative activity and induces apoptosis in human glioblastoma cells. Oncol Rep 41(1):125–132.  https://doi.org/10.3892/or.2018.6845 CrossRefPubMedGoogle Scholar
  11. 11.
    Wu DM, Hong XW, Wen X, Han XR, Wang S, Wang YJ, Shen M, Fan SH, Zhuang J, Zhang ZF, Shan Q, Li MQ, Hu B, Sun CH, Lu J, Zheng YL (2019) MCL1 gene silencing promotes senescence and apoptosis of glioma cells via inhibition of the PI3K/Akt signaling pathway. IUBMB Life 71(1):81–92.  https://doi.org/10.1002/iub.1944 CrossRefPubMedGoogle Scholar
  12. 12.
    Gu J-J, Fan K-C, Zhang J-H, Chen H-J, Wang S-S (2017) Suppression of microRNA-130b inhibits glioma cell proliferation and invasion, and induces apoptosis by PTEN/AKT signaling. Int J Mol Med.  https://doi.org/10.3892/ijmm.2017.3233
  13. 13.
    Karsy M, Neil JA, Guan J, Mahan MA, Colman H, Jensen RL (2015) A practical review of prognostic correlations of molecular biomarkers in glioblastoma. Neurosurg Focus 38(3):E4.  https://doi.org/10.3171/2015.1.FOCUS14755 CrossRefPubMedGoogle Scholar
  14. 14.
    Nakamura JL, Karlsson A, Arvold ND, Gottschalk AR, Pieper RO, Stokoe D, Haas-Kogan DA (2005) PKB/Akt mediates radiosensitization by the signaling inhibitor LY294002 in human malignant gliomas. J Neuro-Oncol 71(3):215–222.  https://doi.org/10.1007/s11060-004-1718-y CrossRefGoogle Scholar
  15. 15.
    Abounader R (2009) Interactions between PTEN and receptor tyrosine kinase pathways and their implications for glioma therapy. Expert Rev Anticancer Ther 9(2):235–245.  https://doi.org/10.1586/14737140.9.2.235 CrossRefPubMedPubMedCentralGoogle Scholar
  16. 16.
    Luo S, Lei K, Xiang D, Ye K (2018) NQO1 is regulated by PTEN in glioblastoma, mediating cell proliferation and oxidative stress. Oxidative Med Cell Longev 2018:9146528.  https://doi.org/10.1155/2018/9146528 CrossRefGoogle Scholar
  17. 17.
    Wang Y, Fan X, Zhang C, Zhang T, Peng X, Qian T, Ma J, Wang L, Li S, Jiang T (2014) Identifying radiographic specificity for phosphatase and tensin homolog and epidermal growth factor receptor changes: a quantitative analysis of glioblastomas. Neuroradiology 56(12):1113–1120.  https://doi.org/10.1007/s00234-014-1427-y CrossRefPubMedGoogle Scholar
  18. 18.
    Ryoo I, Choi SH, Kim JH, Sohn CH, Kim SC, Shin HS, Yeom JA, Jung SC, Lee AL, Yun TJ, Park CK, Park SH (2013) Cerebral blood volume calculated by dynamic susceptibility contrast-enhanced perfusion MR imaging: preliminary correlation study with glioblastoma genetic profiles. PLoS One 8(8):e71704.  https://doi.org/10.1371/journal.pone.0071704 CrossRefPubMedPubMedCentralGoogle Scholar
  19. 19.
    Li Y, Ji F, Jiang Y, Zhao T, Xu C (2018) Correlation analysis of expressions of PTEN and p53 with the value obtained by magnetic resonance spectroscopy and apparent diffusion coefficient in the tumor and the tumor-adjacent area in magnetic resonance imaging for glioblastoma. J BUON 23(2):391–397PubMedGoogle Scholar
  20. 20.
    Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278(2):563–577.  https://doi.org/10.1148/radiol.2015151169 CrossRefGoogle Scholar
  21. 21.
    Zhang B, Chang K, Ramkissoon S, Tanguturi S, Bi WL, Reardon DA, Ligon KL, Alexander BM, Wen PY, Huang RY (2016) Multimodal MRI features predict isocitrate dehydrogenase genotype in high-grade gliomas. Neuro-oncology:now121.  https://doi.org/10.1093/neuonc/now121 CrossRefGoogle Scholar
  22. 22.
    Li Y, Liu X, Xu K, Qian Z, Wang K, Fan X, Li S, Wang Y, Jiang T (2017) MRI features can predict EGFR expression in lower grade gliomas: a voxel-based radiomic analysis. Eur Radiol 28:356–362.  https://doi.org/10.1007/s00330-017-4964-z CrossRefPubMedGoogle Scholar
  23. 23.
    Kickingereder P, Bonekamp D, Nowosielski M, Kratz A, Sill M, Burth S, Wick A, Eidel O, Schlemmer HP, Radbruch A, Debus J, Herold-Mende C, Unterberg A, Jones D, Pfister S, Wick W, von Deimling A, Bendszus M, Capper D (2016) Radiogenomics of glioblastoma: machine learning-based classification of molecular characteristics by using multiparametric and multiregional MR imaging features. Radiology 281(3):907–918.  https://doi.org/10.1148/radiol.2016161382 CrossRefPubMedGoogle Scholar
  24. 24.
    Zinn PO, Singh SK, Kotrotsou A, Abrol S, Thomas G, Mosley J, Elakkad A, Hassan I, Kumar A, Colen RR (2017) Distinct radiomic phenotypes define glioblastoma TP53-PTEN-EGFR mutational landscape. Neurosurgery 64(CN_suppl_1):203–210.  https://doi.org/10.1093/neuros/nyx316 CrossRefPubMedPubMedCentralGoogle Scholar
  25. 25.
    Hu LS, Ning S, Eschbacher JM, Baxter LC, Gaw N, Ranjbar S, Plasencia J, Dueck AC, Peng S, Smith KA, Nakaji P, Karis JP, Quarles CC, Wu T, Loftus JC, Jenkins RB, Sicotte H, Kollmeyer TM, O'Neill BP, Elmquist W, Hoxworth JM, Frakes D, Sarkaria J, Swanson KR, Tran NL, Li J, Mitchell JR (2016) Radiogenomics to characterize regional genetic heterogeneity in glioblastoma. Neuro-oncology. 19:128–137.  https://doi.org/10.1093/neuonc/now135 CrossRefPubMedPubMedCentralGoogle Scholar
  26. 26.
    McCann SM, Jiang Y, Fan X, Wang J, Antic T, Prior F, VanderWeele D, Oto A (2016) Quantitative multiparametric MRI features and PTEN expression of peripheral zone prostate cancer: a pilot study. Am J Roentgenol 206(3):559–565.  https://doi.org/10.2214/ajr.15.14967 CrossRefGoogle Scholar
  27. 27.
    Louis DN, Perry A, Reifenberger G, von Deimling A, Figarella-Branger D, Cavenee WK, Ohgaki H, Wiestler OD, Kleihues P, Ellison DW (2016) The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary. Acta Neuropathol 131(6):803–820.  https://doi.org/10.1007/s00401-016-1545-1 CrossRefPubMedPubMedCentralGoogle Scholar
  28. 28.
    Aerts HJ, Velazquez ER, Leijenaar RT, Parmar C, Grossmann P, Carvalho S, Bussink J, Monshouwer R, Haibe-Kains B, Rietveld D, Hoebers F, Rietbergen MM, Leemans CR, Dekker A, Quackenbush J, Gillies RJ, Lambin P (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:4006.  https://doi.org/10.1038/ncomms5006 CrossRefPubMedPubMedCentralGoogle Scholar
  29. 29.
    Brennan CW, Verhaak RG, McKenna A, Campos B, Noushmehr H, Salama SR, Zheng S, Chakravarty D, Sanborn JZ, Berman SH, Beroukhim R, Bernard B, Wu CJ, Genovese G, Shmulevich I, Barnholtz-Sloan J, Zou L, Vegesna R, Shukla SA, Ciriello G, Yung WK, Zhang W, Sougnez C, Mikkelsen T, Aldape K, Bigner DD, Van Meir EG, Prados M, Sloan A, Black KL, Eschbacher J, Finocchiaro G, Friedman W, Andrews DW, Guha A, Iacocca M, O'Neill BP, Foltz G, Myers J, Weisenberger DJ, Penny R, Kucherlapati R, Perou CM, Hayes DN, Gibbs R, Marra M, Mills GB, Lander E, Spellman P, Wilson R, Sander C, Weinstein J, Meyerson M, Gabriel S, Laird PW, Haussler D, Getz G, Chin L, Network TR (2013) The somatic genomic landscape of glioblastoma. Cell 155(2):462–477.  https://doi.org/10.1016/j.cell.2013.09.034 CrossRefPubMedPubMedCentralGoogle Scholar
  30. 30.
    De Jay N, Papillon-Cavanagh S, Olsen C, El-Hachem N, Bontempi G, Haibe-Kains B (2013) mRMRe: an R package for parallelized mRMR ensemble feature selection. Bioinformatics 29(18):2365–2368.  https://doi.org/10.1093/bioinformatics/btt383 CrossRefPubMedGoogle Scholar
  31. 31.
    Prasanna P, Patel J, Partovi S, Madabhushi A, Tiwari P (2016) 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. Eur Radiol 27:4188–4197.  https://doi.org/10.1007/s00330-016-4637-3 CrossRefPubMedPubMedCentralGoogle Scholar
  32. 32.
    Orru G, Pettersson-Yeo W, Marquand AF, Sartori G, Mechelli A (2012) Using support vector machine to identify imaging biomarkers of neurological and psychiatric disease: a critical review. Neurosci Biobehav Rev 36(4):1140–1152.  https://doi.org/10.1016/j.neubiorev.2012.01.004 CrossRefPubMedGoogle Scholar
  33. 33.
    Huang DW, Sherman BT, Lempicki RA (2009) Systematic and integrative analysis of large gene lists using DAVID bioinformatics resources. Nat Protoc 4(1):44–57.  https://doi.org/10.1038/nprot.2008.211 CrossRefGoogle Scholar
  34. 34.
    Huang d W, Sherman BT, Lempicki RA (2009) Bioinformatics enrichment tools: paths toward the comprehensive functional analysis of large gene lists. Nucleic Acids Res 37(1):1–13.  https://doi.org/10.1093/nar/gkn923 CrossRefGoogle Scholar
  35. 35.
    Aerts HJ, Grossmann P, Tan Y, Oxnard GG, Rizvi N, Schwartz LH, Zhao B (2016) Defining a radiomic response phenotype: a pilot study using targeted therapy in NSCLC. Sci Rep 6:33860.  https://doi.org/10.1038/srep33860 CrossRefPubMedPubMedCentralGoogle Scholar
  36. 36.
    Lehrer M, Bhadra A, Ravikumar V, Chen JY, Wintermark M, Hwang SN, Holder CA, Huang EP, Fevrier-Sullivan B, Freymann JB, Rao A, Group TGPR (2017) Multiple-response regression analysis links magnetic resonance imaging features to de-regulated protein expression and pathway activity in lower grade glioma. Oncoscience 4(5–6):57–66.  https://doi.org/10.18632/oncoscience.353 CrossRefPubMedPubMedCentralGoogle Scholar
  37. 37.
    Kini V, Chavez A, Mehta D (2010) A new role for PTEN in regulating transient receptor potential canonical channel 6-mediated Ca2+ entry, endothelial permeability, and angiogenesis. J Biol Chem 285(43):33082–33091.  https://doi.org/10.1074/jbc.M110.142034 CrossRefPubMedPubMedCentralGoogle Scholar
  38. 38.
    Ng F, Ganeshan B, Kozarski R, Miles KA, Goh V (2013) Assessment of primary colorectal cancer heterogeneity by using whole-tumor texture analysis: contrast-enhanced CT texture as a biomarker of 5-year survival. Radiology 266(1):177–184.  https://doi.org/10.1148/radiol.12120254 CrossRefPubMedGoogle Scholar
  39. 39.
    Yuan F, Zhang Y-H, Kong X-Y, Cai Y-D (2017) Identification of candidate genes related to inflammatory bowel disease using minimum redundancy maximum relevance, incremental feature selection, and the shortest-path approach. Biomed Res Int 2017:1–15.  https://doi.org/10.1155/2017/5741948 CrossRefGoogle Scholar
  40. 40.
    Xu Y, Ding Y-X, Ding J, Wu L-Y, Xue Y (2016) Mal-Lys: prediction of lysine malonylation sites in proteins integrated sequence-based features with mRMR feature selection. Sci Rep 6(1).  https://doi.org/10.1038/srep38318
  41. 41.
    Mortazavi A, Moattar MH (2016) Robust feature selection from microarray data based on cooperative game theory and qualitative mutual information. Adv Bioinforma 2016:1–16.  https://doi.org/10.1155/2016/1058305 CrossRefGoogle Scholar
  42. 42.
    Huang MW, Chen CW, Lin WC, Ke SW, Tsai CF (2017) SVM and SVM ensembles in breast Cancer prediction. PLoS One 12(1):e0161501.  https://doi.org/10.1371/journal.pone.0161501 CrossRefPubMedPubMedCentralGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  • Yiming Li
    • 1
  • Yuchao Liang
    • 2
  • Zhiyan Sun
    • 1
  • Kaibin Xu
    • 3
  • Xing Fan
    • 1
  • Shaowu Li
    • 4
  • Zhong Zhang
    • 2
  • Tao Jiang
    • 5
    • 6
  • Xing Liu
    • 1
  • Yinyan Wang
    • 2
    Email author
  1. 1.Beijing Neurosurgical InstituteCapital Medical UniversityBeijingChina
  2. 2.Department of Neurosurgery, Beijing Tiantan HospitalCapital Medical UniversityBeijingChina
  3. 3.Institute of AutomationChinese Academy of SciencesBeijingChina
  4. 4.Neurological Imaging Center, Beijing Neurosurgical InstituteCapital Medical UniversityBeijingChina
  5. 5.Chinese Glioma Genome Atlas Network (CGGA) and Asian Glioma Genome Atlas Network (AGGA)BeijingChina
  6. 6.China National Clinical Research Center for Neurological DiseasesBeijingChina

Personalised recommendations