High-order radiomics features based on T2 FLAIR MRI predict multiple glioma immunohistochemical features: A more precise and personalized gliomas management

Autoři: Jing Li aff001;  Siyun Liu aff003;  Ying Qin aff003;  Yan Zhang aff001;  Ning Wang aff001;  Huaijun Liu aff001
Působiště autorů: Department of Radiology, The Second Hospital of Hebei Medical University, Shijiazhuang, Hebei, China aff001;  Department of Radiology, Tangshan Women and Children’s Hospital, Tangshan, Hebei, China aff002;  Life Science, GE Healthcare, Beijing, China aff003
Vyšlo v časopise: PLoS ONE 15(1)
Kategorie: Research Article
doi: https://doi.org/10.1371/journal.pone.0227703



To investigate the performance of high-order radiomics features and models based on T2-weighted fluid-attenuated inversion recovery (T2 FLAIR) in predicting the immunohistochemical biomarkers of glioma, in order to execute a non-invasive, more precise and personalized glioma disease management.


51 pathologically confirmed gliomas patients committed in our hospital from March 2015 to June 2018 were retrospective analysis, and Ki-67, vimentin, S-100 and CD34 immunohistochemical data were collected. The volumes of interest (VOIs) were manually sketched and the radiomics features were extracted. Feature reduction was performed by ANOVA+ Mann-Whiney, spearman correlation analysis, least absolute shrinkage and selection operator (LASSO) and Gradient descent algorithm (GBDT). SMOTE technique was used to solve the data bias between two groups. Comprehensive binary logistic regression models were established. Area under the ROC curves (AUC), sensitivity, specificity and accuracy were used to evaluate the predict performance of models. Models reliability were decided according to the standard net benefit of the decision curves.


Four clusters of significant features were screened out and four predicting models were constructed. AUC of Ki-67, S-100, vimentin and CD34 models were 0.713, 0.923, 0.854 and 0.745, respectively. The sensitivities were 0.692, 0.893, 0.875 and 0.556, respectively. The specificities were: 0.667, 0.905, 0.722, and 0.875, with accuracy of 0.660, 0.898, 0.738, and 0.667, respectively. According to the decision curves, the Ki-67, S-100 and vimentin models had reference values.


The radiomics features based on T2 FLAIR can potentially predict the Ki-67, S-100, vimentin and CD34 expression. Radiomics model were expected to be a computer-intelligent, non-invasive, accurate and personalized management method for gliomas.

Klíčová slova:

Biomarkers – Cancer detection and diagnosis – Forecasting – Glioblastoma multiforme – Glioma – Magnetic resonance imaging – Prognosis – Vimentin


1. Patel SH, Bansal AG, Young EB, Batchala PP, Patrie JT, Lopes MB, et al. Extent of Surgical Resection in Lower-Grade Gliomas: Differential Impact Based on Molecular Subtype. AJNR Am J Neuroradiol.2019,40(7):1149–1155. doi: 10.3174/ajnr.A6102 31248860

2. Harat M, Blok M, Harat A, Soszyńska K. The impact of adjuvant radiotherapy on molecular prognostic markers in gliomas. Onco Targets Ther.2019,12:2215–2224. doi: 10.2147/OTT.S200818 30988626

3. Habberstad AH, Gulati S, Torp SH. Evaluation of the proliferation marker ki-67/mib-1, mitosin, survivin, phh3, and DNA topoisomerase iialpha in human anaplastic astrocytomas-an immunohistochemical study. Diagn Pathol. 2011, 6:43.

4. Unique Molecular Landscapes Distinguish Low- and High-Grade NF1Gliomas. Cancer Discov.2019,9(2):165.

5. Pujadas E, Chen L, Rodriguez FJ. Pathologic and molecular aspects of anaplasia in circumscribed gliomas and glioneuronal tumors. Brain Tumor Pathol.2019,36(2):40–51. doi: 10.1007/s10014-019-00336-z 30859342

6. Korfiatis P, Erickson B. Deep learning can see the unseeable: predicting molecular markers from MRI of brain gliomas. Clin Radiol.2019,74(5):367–373. doi: 10.1016/j.crad.2019.01.028 30850092

7. Venneti S, Huse JT. The evolving molecular genetics of low-grade glioma. Adv Anat Pathol. 2015,22(2):94–101. doi: 10.1097/PAP.0000000000000049 25664944

8. Stupp R, Hegi ME, van den Bent MJ, Mason WP, Weller M, Mirimanoff RO, et al. Changing paradigms—an update on the multidisciplinary management of malignant glioma. Oncologist.2006,11(2):165–180. doi: 10.1634/theoncologist.11-2-165 16476837

9. Khanna G, Pathak P, Suri V, Sharma MC, Chaturvedi S, Ahuja A, et al. Immunohistochemical and molecular genetic study on epithelioid glioblastoma: Series of seven cases with review of literature. Pathol Res Pract.2018,214(5):679–685. doi: 10.1016/j.prp.2018.03.019 29615337

10. Ioan Florian Ș, Șuşman S. Diffuse Astrocytoma and Oligodendroglioma: An Integrated Diagnosis and Management. Glioma—Contemporary Diagnostic and Therapeutic Approaches, Ibrahim Omerhodžić and Kenan Arnautović. IntechOpen. 2018,27(6):96–147.

11. Su C, Jiang J, Zhang S, Shi J, Xu K, Shen N, et al. Radiomics based on multicontrast MRI can precisely differentiate among glioma subtypes and predict tumour-proliferative behaviour. Eur Radiol.2019,29(4):1986–1996. doi: 10.1007/s00330-018-5704-8 30315419

12. Lin L, Wang G, Ming J, Meng X, Han B, Sun B, et al. Analysis of expression and prognostic significance of vimentin and the response to temozolomide in glioma patients. Tumour Biol.2016,37(11):15333–15339. doi: 10.1007/s13277-016-5462-7 27704357

13. Nagaishi M, Yokoo H, Nobusawa S, Sugiura Y, Suzuki R, Tanaka Y, et al. A distinctive pediatric case of low-grade glioma with extensive expression of CD34. Brain Tumor Pathol.2016,33(1):71–74. doi: 10.1007/s10014-015-0236-2 26496909

14. Gates EDH, Lin JS, Weinberg JS, Hamilton J, Prabhu SS, Hazle JD. Guiding the first biopsy in glioma patients using estimated Ki67 maps derived from MRI: conventional versus advanced imaging. Neuro Oncol.2019,21(4):527–536. doi: 10.1093/neuonc/noz004 30657997

15. Van Eldik LJ, Zimmer DB. Secretion of S-100 from rat C6 glioma cells. Brain Res.1987,436(2):367–370. doi: 10.1016/0006-8993(87)91681-7 3435834

16. Chen WJ, He DS, Tang RX, Ren FH, Chen G. Ki-67 is a valuable prognostic factor in gliomas: evidence from a systematic review and meta-analysis. Asian Pac J Cancer Prev.2015,16(2):411–420. doi: 10.7314/apjcp.2015.16.2.411 25684464

17. De Souza PC, Katz SG. Coexpression of cytokeratin and vimentinin mice trophoblastic giant cells. Tissue & cell. 2001,33(1):40–45.

18. Hilbig A, Barbosa-Coutinho LM, Toscani N, Ribeiro Mde C, da Cunha BS. Expression of nestin and vimentin in gliomatosis cerebri. Arq Neuropsiquiatr.2006,64(3B):781–786. doi: 10.1590/s0004-282x2006000500015 17057885

19. Kong X, Guan Y, Ma W, Li Y, Xing B, Yang Y, et al. CD34 Over-Expression is Associated With Gliomas’ Higher WHO Grade. Medicine (Baltimore):e2830. doi: 10.1097/MD.0000000000002830 26886640

20. Michaelsen SR, Urup T, Olsen LR, Broholm H, Lassen U, Poulsen HS. Molecular profiling of short-term and long-term surviving patients identifies CD34 mRNA level as prognostic for glioblastoma survival. J Neurooncol.2018,137(3):533–542. doi: 10.1007/s11060-017-2739-7 29305787

21. Jackson RJ, Fuller GN, Abi-Said D, Lang FF, Gokaslan ZL, Shi WM, et al. Limitations of stereotactic biopsy in the initial management of gliomas. Neuro Oncol.2001,3:193–200. doi: 10.1093/neuonc/3.3.193 11465400

22. Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images Are More than Pictures, They Are Data. Radiology.2016, 278(2):563–577. doi: 10.1148/radiol.2015151169 26579733

23. Tian Q, Yan LF, Zhang X, Zhang X, Hu YC, Han Y, et al. Radiomics Strategy for Glioma Grading Using Texture Features From Multiparametric MRI. J Magn Reson Imaging.2018,48(6):1518–1528. doi: 10.1002/jmri.26010 29573085

24. Ryu YJ, Choi SH, Park SJ, Yun TJ, Kim JH, Sohn CH. Glioma: application of whole-tumor texture analysis of diffusion-weighted imaging for the evaluation of tumor heterogeneity. PLoS One.2014,9(9):e108335. doi: 10.1371/journal.pone.0108335 25268588

25. Chaddad A, Daniel P, Sabri S, Desrosiers C, Abdulkarim B. Integration of Radiomic and Multi-omic Analyses Predicts Survival of Newly Diagnosed IDH1 Wild-Type Glioblastoma. Cancers(Basel).2019,11(8):1148.

26. Chaddad A, Kucharczyk MJ, Daniel P, Sabri S, Jean-Claude BJ, Niazi T, et al. Radiomics in Glioblastoma: Current Status and Challenges Facing Clinical Implementation. Front Oncol.2019,9:374. doi: 10.3389/fonc.2019.00374 31165039

27. Chaddad A, Desrosiers C, Niazi T. Predicting the Gene Status and Survival Outcome of Lower Grade Glioma Patients with Multimodal MRI Features. IEEE Access.2019.2920396.PP.1-1.10.1109.

28. Fathallah-Shaykh HM, DeAtkine A, Coffee E, Khayat E, Bag AK, Han X, et al. Diagnosing growth in low-grade gliomas with and without longitudinal volume measurements: A retrospective observational study. PLoS Med.2019,16(5): e1002810. doi: 10.1371/journal.pmed.1002810 31136584

29. Grier JT, Batchelor T. Low-Grade Gliomas in Adults. Oncologist.2006,11(6):681–693. doi: 10.1634/theoncologist.11-6-681 16794247

30. Jakola AS, Zhang YH, Skjulsvik AJ, Solheim O, Bø HK, Berntsen EM, et al. Quantitative texture analysis in the prediction of IDH status in low-grade gliomas. Clin Neurol Neurosurg. 2018,164:114–120. doi: 10.1016/j.clineuro.2017.12.007 29220731

31. Rui W, Ren Y, Wang Y, Gao X, Xu X, Yao Z. MR textural analysis on T2 FLAIR images for the prediction of true oligodendroglioma by the 2016 WHO genetic classification. J Magn Reson Imaging.2018,48(1):74–83. doi: 10.1002/jmri.25896 29140606

32. Bahrami N, Hartman SJ, Chang YH, Delfanti R, White N, Karunamuni R, et al. Molecular classification of patients with grade II/III glioma using quantitative MRI characteristics. J Neurooncol.2018,139(3):633–642. doi: 10.1007/s11060-018-2908-3 29860714

33. Ismail M, Hill V, Statsevych V, Huang R, Prasanna P, Correa R, et al. Shape features of the lesion habitat to differentiate brain tumor progression from pseudoprogression on routine multiparametric MRI: a multisite study. AJNR Am J Neuroradiol.2018,39(12):2187–2193. doi: 10.3174/ajnr.A5858 30385468

34. Bahrami N, Piccioni D, Karunamuni R, Chang YH, White N, Delfanti R, et al. Edge contrast of the FLAIR hyperintense region predicts survival in patients with high-grade gliomas following treatment with bevacizumab. AJNR Am J Neuroradiol.2018,39(6):1017–1024. doi: 10.3174/ajnr.A5620 29622553

35. Fouke SJ, Benzinger T, Gibson D, Ryken TC, Kalkanis SN, Olson JJ. The role of imaging in the management of adults with diffuse low grade glioma: A systematic review and evidence-based clinical practice guideline. J Neurooncol.2015,125(3):457–479. doi: 10.1007/s11060-015-1908-9 26530262

36. Li Y, Qian Z, Xu K, Wang K, Fan X, Li S, et al. Radiomic features predict Ki-67 expression level and survival in lower grade gliomas. J Neurooncol.2017,135(2):317–324. doi: 10.1007/s11060-017-2576-8 28900812

37. Beesley MF, McLaren KM. Cytokeratin 19 and galectin-3 immunohistochemistry in the differential diagnosis of solitary thyroid nodules. Histopathology.2002,41(3): 236–243. doi: 10.1046/j.1365-2559.2002.01442.x 12207785

38. Yang Y, Yan LF, Zhang X, Nan HY, Hu YC, Han Y, et al. Optimizing Texture Retrieving Model for Multimodal MR Image-Based Support Vector Machine for Classifying Glioma. J Magn Reson Imaging.2019,49(5):1263–1274. doi: 10.1002/jmri.26524 30623514

39. Emaminejad N, Wang Y, Qian W, Zheng B. Applying a radiomics approach to predict prognosis of lung cancer patients. In: Medical imaging 2016: computer-aided diagnosis. 2016, 97851E.

40. Maciejewski T, Stefanowski J. Local neighbourhood extension of SMOTE for mining imbalanced data. In: Proceeding of the IEEE symposium on computational intelligence and data mining. Paris, France: IEEE.2011,104–111.

41. Pang H, Jung SH. Sample size considerations of prediction‐validation methods in high‐dimensional data for survival outcomes. Genet Epidemiol.2013,37(3):276–282. doi: 10.1002/gepi.21721 23471879

42. Wang LY, Lee WC. One-step extrapolation of the prediction performance of a gene signature derived from a small study. BMJ Open.2015,5(4): e007170. doi: 10.1136/bmjopen-2014-007170 25888476

43. Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, van Stiphout RG, Granton P, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer.2012,48(4):441–446. doi: 10.1016/j.ejca.2011.11.036 22257792

44. Brynolfsson P, Nilsson D, Henriksson R, Hauksson J, Karlsson M, Garpebring A, et al. ADC texture-an imaging biomarker for high-grade glioma? Med Phys.2014,41(10):101903. doi: 10.1118/1.4894812 25281955

45. Skogen K, Schulz A, Dormagen JB, Ganeshan B, Helseth E, Server A. Diagnostic performance of texture analysis on MRI in grading cerebral gliomas. Eur J Radiol.2016,85:824–829. doi: 10.1016/j.ejrad.2016.01.013 26971430

46. Jaiswal S. Role of immunohistochemistry in the diagnosis of central nervous system tumors. Neurol India.2016,64(3):502–512. doi: 10.4103/0028-3886.181547 27147160

47. Nabors LB, Portnow J, Ammirati M, Baehring J, Brem H, Brown P, et al. Central Nervous System Cancers, Version 1. 2015. J Natl Compr Cancer Netw.2015,13:1191–1202.

48. Lambin P, Leijenaar RT, Deist TM, Peerlings J, de Jong EEC, van Timmeren J, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol.2017,14(12):749–762. doi: 10.1038/nrclinonc.2017.141 28975929

49. Limkin EJ, Sun R, Dercle L, Zacharaki EI, Robert C, Reuzé S, et al. Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology. Ann Oncol.2017,28(6):1191–1206. doi: 10.1093/annonc/mdx034 28168275

50. Verma V, Simone CB, Krishnan S, Lin SH, Yang J, Hahn SM. The Rise of Radiomics and Implications for Oncologic Management. J Natl Cancer Inst.2017,109(7):djx055.

51. Lee J, Narang S, Martinez J, Rao G, Rao A. Spatial Habitat Features Derived from Multiparametric Magnetic Resonance Imaging Data Are Associated with Molecular Subtype and 12-Month Survival Status in Glioblastoma Multiforme. PLoS One.2015,10(9):e0136557. doi: 10.1371/journal.pone.0136557 26368923

52. Grossmann P, Gutman DA, Dunn WD, Holder CA, Aerts HJ. Imaging-genomics reveals driving pathways of MRI derived volumetric tumor phenotype features in Glioblastoma. BMC Cancer. 2016,16:611. doi: 10.1186/s12885-016-2659-5 27502180

53. Zinn PO, Mahajan B, Majadan B, Sathyan P, Singh SK, Majumder S, et al. Radiogenomic mapping of edema/cellular invasion MRIphenotypes in glioblastoma multiforme. PLoS One. 2011,6(10):e25451. doi: 10.1371/journal.pone.0025451 21998659

54. Chen H, Xu C, Jin Q, Liu Z. S100 protein family in human cancer. Am J Cancer Res.2014,4(2):89–115. 24660101

55. Camby l, Nagy N, Lopes MB, Schäfer BW, Maurage CA, Ruchoux MM, et al. Supratentorial pilocytic astrocytomas, astrocytomas, anaplastic astrocytomas and glioblastomas are characterized by a differential expression of S100 proteins. Brain Pathol.1999,9(1):1–19. doi: 10.1111/j.1750-3639.1999.tb00205.x 9989446

56. Liang L, Piao Y, Holmes L, Fuller GN, Henry V, Tiao N, et al. Neutrophils promote the malignant glioma phenotype through S100A4. Clin Cancer Res.2014,20(1):187–198. doi: 10.1158/1078-0432.CCR-13-1279 24240114

57. Holla FK, Postma TJ, Blankenstein MA, van Mierlo TJM, Vos MJ, Sizoo EM, et al. Prognostic value of the S100B protein in newly diagnosed and recurrent glioma patients: a serial analysis. J Neurooncol.2016,129(3):525–532. doi: 10.1007/s11060-016-2204-z 27401156

58. Arora A, Patil V, Kundu P, Kondaiah P, Hegde AS, Arivazhagan A, et al. Serum biomarkers identification by iTRAQ and verification by MRM: S100A8/S100A9 levels predict tumor-stroma involvement and prognosis in Glioblastoma. Sci Rep.2019,9(1):2749. doi: 10.1038/s41598-019-39067-8 30808902

59. Nguemgo Kouam P, Rezniczek GA, Kochanneck A, Priesch-Grzeszkowiak B, Hero T, Adamietz IA, et al. Robo1 and vimentin regulate radiation-induced motility of human glioblastoma cells. PLoS One.2018,13(6):e0198508. doi: 10.1371/journal.pone.0198508 29864155

60. Komura K, Ise H, Akaike T. Dynamic behaviors of vimentin induced by interaction with GlcNAc molecules. Glycobiology.2012,22(12):1741–1759. doi: 10.1093/glycob/cws118 22846177

61. Viallon M, Cuvinciuc V, Delattre B, Merlini L, Barnaure-Nachbar I, Toso-Patel S, et al. State-of-the-art MRI techniques in neuroradiology: Principles, pitfalls, and clinical applications. Neuroradiology.2015,57:441–467. doi: 10.1007/s00234-015-1500-1 25859832

62. Nagaishi M, Yokoo H, Nobusawa S, Fujii Y, Sugiura Y, Suzuki R, et al. A distinctive pediatric case of low-grade glioma with extensive expression of CD34. Brain Tumor Pathol.2016,33(1):71–74. doi: 10.1007/s10014-015-0236-2 26496909

63. McGahan BG, Neilsen BK, Kelly DL, McComb RD, Kazmi SA, White ML, et al. Assessment of vascularity in glioblastoma and its implications on patient outcomes. J Neurooncol.2017,132(1):35–44. doi: 10.1007/s11060-016-2350-3 28102487

Článek vyšel v časopise


2020 Číslo 1
Nejčtenější tento týden