Некоторые аспекты радиомики и радиогеномики глиобластом: что лежит за пределами изображения?

Радиогеномика — это относительно новое и перспективное направление, связывающее многообразие возможностей визуализации с различными геномными событиями. Достижения в области геномики, предоставленные проектами «Атлас Ракового Генома» и «Геном человека», позволили интегрировать данную информацию с визуализационными фенотипами злокачественных новообразований головного мозга для более детального понимания их биологии. Радиомика в свою очередь лежит на стыке радиологии, компьютерных наук и математической статистики. В отличие от радиогеномики, она не сосредоточена на конкретной взаимосвязи радиофенотипа и генотипа опухоли, а представляет собой скорее методологию анализа. С ее помощью из медицинских изображений извлекаются недоступные невооруженному глазу количественные признаки, устанавливая связи между генотипом пациента и фенотипом визуализации. Это способствует стратификации пациентов в клинических испытаниях, мониторингу ответа на терапию и, как следствие, улучшению ее результатов. В статье рассматриваются некоторые актуальные аспекты радиомики и радиогеномики глиобластом и их применение в нейроонкологии.

Ранее несколькими группами исследователей была показана взаимосвязь визуализационных особенностей глиобластом и прогноза течения заболевания.

Одной из современных проблем радиомики является поиск визуализационных признаков, которые смогут выполнять функцию ключевых прогностических маркеров для стратификации риска пациентов с глиобластомами с помощью инструментов машинного обучения.

Таким образом, перспективы развития методов радиомики и радиогеномики включают в себя прогнозирование выживаемости пациентов, дифференциальную диагностику глиобластом, определение степеней злокачественности, идентификацию мутаций и амплификаций, выявление опухолевой прогрессии, псевдопрогрессии и др.

1. Thrall JH. Moreton Lecture: Imaging in the Age of Precision Medicine. J Am Coll Radiol. 2015; 12(10):1106–1111. DOI: 10.1016/j.jacr.2015.06.003.

2. Sun X, Gierach GL, Sandhu R, et al. Relationship of mammographic density and gene expression: analysis of normal breast tissue surrounding breast cancer. Clin Cancer Res. 2013; 19(18):4972–4982. DOI: 10.1158/1078-0432.CCR-13-0029.

3. Kelly PJ, Daumas-Duport C, Kispert DB, et al. Imaging-based stereotaxic serial biopsies in untreated intracranial glial neoplasms. J Neurosurg. 1987; 66(6):865–874. DOI: 10.3171/jns.1987.66.6.0865.

4. Zinn PO, Sathyan P, Mahajan B, et al. A novel volume-age-KPS (VAK) glioblastoma classification identifies a prognostic cognate microRNA-gene signature. PLoS One. 2012; 7(8):e41522. DOI: 10.1371/journal.pone.0041522.

5. Colen RR, Wang J, Singh SK, et al. Glioblastoma: imaging genomic mapping reveals sex-specific oncogenic associations of cell death. Radiology. 2015; 275(1):215–227. DOI: 10.1148/radiol.14141800.

6. Colen RR, Vangel M, Wang J, et al. Imaging genomic mapping of an invasive MRI phenotype predicts patient outcome and metabolic dysfunction: a TCGA glioma phenotype research group project. BMC Med Genomics. 2014; 7:30. DOI: 10.1186/1755-8794-7-30.

7. Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images Are More than Pictures, They Are Data. Radiology. 2016; 278(2):563–77. DOI: 10.1148/radiol.2015151169.

8. Osborn AG, Salzman KL, Jhaveri MD, et al. Diagnostic Imaging: Brain. Philadelphia. PA. USA: Elsevier Health Sciences, 2015. p.1300

9. Zinn PO, Mahajan B, Sathyan P, et al. Radiogenomic mapping of edema/cellular invasion MRI-phenotypes in glioblastoma multiforme. PLoS One. 2011; 6(10):e25451. DOI: 10.1371/journal.pone.0025451.

10. Naeini KM, Pope WB, Cloughesy TF, et al. Identifying the mesenchymal molecular subtype of glioblastoma using quantitative volumetric analysis of anatomic magnetic resonance images. Neuro Oncol. 2013; 15(5):626–634. DOI: 10.1093/neuonc/not008.

11. Phillips HS, Kharbanda S, Chen R, et al. Molecular subclasses of high-grade glioma predict prognosis, delineate a pattern of disease progression, and resemble stages in neurogenesis. Cancer Cell. 2006; 9(3):157–573. DOI: 10.1016/j.ccr.2006.02.019.

12. Ellingson BM, Lai A, Harris RJ, et al. Probabilistic radiographic atlas of glioblastoma phenotypes. AJNR Am J Neuroradiol. 2013; 34(3):533–540. DOI: 10.3174/ajnr.A3253.

13. Hegi ME, Diserens AC, Gorlia T, et al. MGMT gene silencing and benefit from temozolomide in glioblastoma. N Engl J Med. 2005; 352(10):997–1003. DOI: 10.1056/NEJMoa043331.

14. Aghi M, Gaviani P, Henson JW, et al. Magnetic resonance imaging characteristics predict epidermal growth factor receptor amplification status in glioblastoma. ClinCancer Res. 2005; 11(24 Pt 1):8600–8605. DOI: 10.1158/1078-0432.CCR-05-0713.

15. Pope WB, Chen JH, Dong J, et al. Relationship between gene expression and enhancement in glioblastoma multiforme: exploratory DNA microarray analysis. Radiology. 2008; 249(1):268–277. DOI: 10.1148/radiol.2491072000.

16. Diehn M, Nardini C, Wang DS, et al. Identification of noninvasive imaging surrogates for brain tumor geneexpression modules. Proc Natl Acad Sci U S A. 2008; 105(13):5213–8. DOI: 10.1073/pnas.0801279105.

17. Wangaryattawanich P, Hatami M, Wang J, et al. Multicenter imaging outcomes study of The Cancer Genome Atlas glioblastoma patient cohort: imaging predictors of overall and progression-free survival. Neuro Oncol. 2015; 17(11):1525–1537. DOI: 10.1093/neuonc/nov117.

18. Barajas RF Jr, Phillips JJ, Parvataneni R, et al. Regional variation in histopathologic features of tumor specimens from treatment-naive glioblastoma correlates with anatomic and physiologic MR Imaging. Neuro Oncol. 2012; 14(7):942–954. DOI: 10.1093/neuonc/nos128.

19. Ribas A, Chmielowski B, Glaspy JA. Do we need a different set of response assessment criteria for tumor immunotherapy? ClinCancer Res. 2009; 15(23):7116–7118. DOI: 10.1158/1078-0432.CCR-09-2376.

20. Andronesi OC, Loebel F, Bogner W, et al. Treatment Response Assessment in IDH-Mutant Glioma Patients by Noninvasive 3D Functional Spectroscopic Mapping of 2-Hydroxyglutarate. Clin Cancer Res. 2016; 22(7):1632–1641. DOI: 10.1158/1078-0432.CCR-15-0656.

21. Elshafeey N, Hassan I, Zinn PO, Colen RR. From K-space to Nucleotide: Insights Into the Radiogenomics of Brain Tumors. Top Magn Reson Imaging. 2017; 26(1):33–41. DOI: 10.1097/RMR.0000000000000114.

22. Yan H, Parsons DW, Jin G, et al. IDH1 and IDH2 mutations in gliomas. N Engl J Med. 2009; 360(8):765–773. DOI: 10.1056/NEJMoa0808710.

23. Cancer Genome Atlas Research Network, Brat DJ, Verhaak RG, et al. Comprehensive, Integrative Genomic Analysis of Diffuse Lower-Grade Gliomas. N Engl J Med. 2015; 372(26):2481–2498. DOI: 10.1056/NEJMoa1402121.

24. Reitman ZJ, Yan H. Isocitrate dehydrogenase 1 and 2 mutations in cancer: alterations at a crossroads of cellular metabolism. J Natl Cancer Inst. 2010; 102(13):932–941. DOI: 10.1093/jnci/djq187.

25. Bledea R, Vasudevaraja V, Patel S, et al. Functional and topographic effects on DNA methylation in IDH1/2 mutant cancers. Sci Rep. 2019; 9(1):16830. DOI: 10.1038/s41598-019-53262-7.

26. Chaddad A, Kucharczyk MJ, Daniel P, et al. Radiomics in Glioblastoma: Current Status and Challenges Facing Clinical Implementation. Front Oncol. 2019; 9:374. DOI: 10.3389/fonc.2019.00374.

27. Tateishi K, Wakimoto H, Cahill DP. IDH1 Mutation and World Health Organization 2016 Diagnostic Criteria for Adult Diffuse Gliomas: Advances in Surgical Strategy. Neurosurgery. 2017; 64(CN_suppl_1):134–138. DOI: 10.1093/neuros/nyx247.

28. Тюрина А.Н. 3D протонная магнитно-резонансная спектроскопия в диагностике глиальных опухолей головного мозга (диссертация). Москва, 2019.

29. Öz G, Deelchand DK, Wijnen JP, et al. Advanced single voxel ¹H magnetic resonance spectroscopy techniques in humans: Experts’ consensus recommendations. NMR Biomed. 2020; e4236. DOI: 10.1002/nbm.4236.

30. Andronesi OC. Precision oncology in the era of radiogenomics: the case of D-2HG as an imaging biomarker for mutant IDH gliomas. Neuro Oncol. 2018; 20(7):865–867. DOI: 10.1093/neuonc/noy085.

31. Suh CH, Kim HS, Jung SC, et al. 2-Hydroxyglutarate MR spectroscopy for prediction of isocitrate dehydrogenase mutant glioma: a systemic review and meta-analysis using individual patient data. Neuro Oncol. 2018; 20(12):1573–1583. DOI: 10.1093/neuonc/noy113.

32. Bhandari A, Sharma C, Ibrahim M, et al. The role of 2-hydroxyglutarate magnetic resonance spectroscopy for the determination of isocitrate dehydrogenase status in lower grade gliomas versus glioblastoma: a systematic review and meta-analysis of diagnostic test accuracy. Neuroradiology. 2021; 63(11):1823–1830. DOI: 10.1007/s00234-021-02702-1.

33. Lasocki A, Rosenthal MA, Roberts-Thomson SJ, et al. Neuro-Oncology and Radiogenomics: Time to Integrate? AJNR Am J Neuroradiol. 2020; 41(11):1982–1988. DOI: 10.3174/ajnr.A6769.

34. Louis DN, Perry A, Reifenberger G, et al. The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary. Acta Neuropathol. 2016; 131(6):803–820. DOI: 10.1007/s00401-016-1545-1.

35. Li ZC, Bai H, Sun Q, et al. Multiregional radiomics profiling from multiparametric MRI: Identifying an imaging predictor of IDH1 mutation status in glioblastoma. Cancer Med. 2018; 7(12):5999–6009. DOI: 10.1002/cam4.1863.

36. Brownlee J. How to use ROC curves and precision-recall curves for classification in Python. Machine learning mastery. 2018. https://machinelearningmastery.com/roccurves-and-precision-recall-curves-for-classification-in-python/ (January 2021).

37. Kesler SR, Harrison RA, Petersen ML, et al. Presurgical connectome features predict IDH status in diffuse gliomas. Oncotarget. 2019; 10(60):6484–6493. DOI: 10.18632/oncotarget.27301.

38. Han L, Wang S, Miao Y, et al. MRI texture analysis based on 3D tumor measurement reflects the IDH1 mutations in gliomas — A preliminary study. Eur J Radiol. 2019; 112:169–179. DOI: 10.1016/j.ejrad.2019.01.025.

39. Lewis MA, Ganeshan B, Barnes A, et al. Filtration-histogram based magnetic resonance texture analysis (MRTA) for glioma IDH and 1p19q genotyping. Eur J Radiol. 2019; 113:116–123. DOI: 10.1016/j.ejrad.2019.02.014.

40. Yu J, Shi Z, Lian Y, et al. Noninvasive IDH1 mutation estimation based on a quantitative radiomics approach for grade II glioma. Eur Radiol. 2017; 27(8):3509–3522. DOI: 10.1007/s00330-016-4653-3.

41. Sudre CH, Panovska-Griffiths J, Sanverdi E, et al. Machine learning assisted DSC-MRI radiomics as a tool for glioma classification by grade and mutation status. BMC Med Inform Decis Mak. 2020; 20(1):149. DOI: 10.1186/s12911-020-01163-5.

42. Kickingereder P, Sahm F, Radbruch A, et al. IDH mutation status is associated with a distinct hypoxia/ angiogenesis transcriptome signature which is noninvasively predictable with rCBV imaging in human glioma. Sci Rep. 2015; 5:16238. DOI: 10.1038/srep16238.

43. Brendle C, Hempel JM, Schittenhelm J, et al. Glioma Grading and Determination of IDH Mutation Status and ATRX loss by DCE and ASL Perfusion. Clin Neuroradiol. 2018; 28(3):421–428. DOI: 10.1007/s00062-017-0590-z.

44. Lu HT, Xing W, Zhang YW, et al. The value of DCE-MRI in predicting IDH gene mutation of high-grade gliomas. Zhonghua Yi Xue Za Zhi. 2019; 99(39):3105–3109. In Chinese. DOI: 10.3760/cma.j.issn.0376-2491.2019.39.013.

45. Alis D, Bagcilar O, Senli YD, et al. Machine learning-based quantitative texture analysis of conventional MRI combined with ADC maps for assessment of IDH1 mutation in high-grade gliomas. Jpn J Radiol. 2020; 38(2):135–143. DOI: 10.1007/s11604-019-00902-7.

46. Bisdas S, Shen H, Thust S, et al. Texture analysis- and support vector machine-assisted diffusional kurtosis imaging may allow in vivo gliomas grading and IDH-mutation status prediction: a preliminary study. Sci Rep. 2018; 8(1):6108. DOI: 10.1038/s41598-018-24438-4.

47. Abdalla G, Mancini L, Sanverdi SE, et al. Diffusion kurtosis imaging identifies the IDH-mutation status of gliomas. Neuro Oncol. 2018; 20(Suppl 5):v351. DOI: 10.1093/neuonc/noy129.031.

48. Zhao J, Wang YL, Li XB, et al. Comparative analysis of the diffusion kurtosis imaging and diffusion tensor imaging in grading gliomas, predicting tumour cell proliferation and IDH-1 gene mutation status. J Neurooncol. 2019; 141(1):195–203. DOI: 10.1007/s11060-018-03025-7.

49. Zhao J, Huang Y, Song Y, et al. Diagnostic accuracy and potential covariates for machine learning to identify IDH mutations in glioma patients: evidence from a meta-analysis. Eur Radiol. 2020; 30(8):4664–4674. DOI: 10.1007/s00330-020-06717-9

50. Taha B, Boley D, Sun J, et al. State of Radiomics in Glioblastoma. Neurosurgery. 2021; 89(2):177–184. DOI: 10.1093/neuros/nyab124.

51. Li L, Mu W, Wang Y, et al. A Non-invasive Radiomic Method Using 18F-FDG PET Predicts Isocitrate Dehydrogenase Genotype and Prognosis in Patients With Glioma. Front Oncol. 2019; 9:1183. DOI: 10.3389/fonc.2019.01183.

52. Zhao K, Yu P, Xue Z, et al. 11C-Methionine Integrated PET/MRI-Based Texture Analysis Features May Have a Potential Ability to Distinguish Oligodendroglioma (IDH-Mutant and 1p/19q-Codeleted) From Varied Gliomas. Acad Radiol. 2020; 27(7):e159-e167. DOI: 10.1016/j.acra.2019.09.013.

53. Lohmann P, Lerche C, Bauer EK, et al. Predicting IDH genotype in gliomas using FET PET radiomics. Sci Rep. 2018; 8(1):13328. DOI: 10.1038/s41598-018-31806-7.

54. Bø HK, Solheim O, Kvistad KA, et al. Intraoperative 3D ultrasound-guided resection of diffuse low-grade gliomas: radiological and clinical results. J Neurosurg. 2019; 132(2):518–529. DOI: 10.3171/2018.10.JNS181290.

55. Kim Y, Cho HH, Kim ST, et al. Radiomics features to distinguish glioblastoma from primary central nervous system lymphoma on multi-parametric MRI. Neuroradiology. 2018; 60(12):1297–1305. DOI: 10.1007/s00234-018-2091-4.

56. Chen C, Ou X, Wang J, et al. Radiomics-Based Machine Learning in Differentiation Between Glioblastoma and Metastatic Brain Tumors. Front Oncol. 2019; 9:806. DOI: 10.3389/fonc.2019.00806.

57. Tian Q, Yan LF, Zhang X, 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.

58. Cho HH, Lee SH, Kim J, et al. Classification of the glioma grading using radiomics analysis. PeerJ. 2018; 6:e5982. DOI: 10.7717/peerj.5982.

59. Dong F, Zeng Q, Jiang B, et al. Predicting epidermal growth factor receptor gene amplification status in glioblastoma multiforme by quantitative enhancement and necrosis features deriving from conventional magnetic resonance imaging. Medicine (Baltimore). 2018; 97(21):e10833. DOI: 10.1097/MD.0000000000010833.