Differential diagnostic of a recurrent glial tumor from radiation necrosis by signs of radiomics

SUMMARY. An urgent neurosurgical problem is the identification of recurrent brain glioma and radiation necrosis, due to the absence of pathognomonic signs for these pathological processes at an early stage after CRT (up to 6 months). To solve this problem, methods of computer processing of MR images are used, the differentiation of RN and GBT in which is based on the difference in the signs of radiomics, but these methods do not show high accuracy.

PURPOSE OF THE STUDY: development and practical testing of a technique for differential diagnosis of radiation necrosis and recurrent glial tumor on MRI images based on the analysis and selection of a new combination of radiomics signs.

MATERIALS AND METHODS: development of a package of algorithmic, structural and mathematical models of the proposed solution. Practical implementation and testing of the technique in the framework of MR diagnostics of 108 patients with Grade III, IV glial tumors during dynamic follow-up — 1,3,6,9,12 months after surgery and a course of CRT.

RESULTS. As a result of the study, a combination of signs of radiomics underlying the proposed technique was selected; a practical approbation of the technique was performed, according to the results of which a high accuracy of differentiation of relapse and radiation necrosis on MRI images was established (98.1 %).

CONCLUSION. The results of the approbation of the presented technique allow us to assert that it is highly effective in diagnosis, which makes it possible to differentiate the recurrence of GBT and RN at an early stage.

1. Rynda A.Yu., Rostovcev D.M., Olyushin B.E. Fluorescentno-kontroliruemaya rezekciya astrocitarnyh opuholej golovnogo mozga — obzor literatury. Rossijskij nejrohirurgicheskij zhurnal im. professora A. L. Polenova. 2018;10(1):97–110. EDN VGOGCW (In Russ.).

2. Ostrom QT, Cioffi G, Waite K, Kruchko C, Barnholtz-Sloan JS. CBTRU S Statistical Report: Primary Brain and Other Central Nervous System Tumors Diagnosed in the United States in 2014–2018. Neuro Oncol. 2021;23(12 Suppl 2): iii1-iii105. https://doi.org/10.1093/neuonc/noab200

3. Gribanova T.G., Fokin V.A., Martynov B.V., Trufanov G.E., Malakhovsky V. N., Serebryakova S.V. Sopostavlenie razlichnykh metodov neirovizualizatsii v differentsial’noi diagnostike retsidiva zlokachestvennykh opukholei golovnogo mozga i luchevogo nekroza. Vestnik of St Petersburg University. 2016;3:56–53. https://doi.org/10.21638/11701/spbu11.2016.305 EDN: XQRQBB (In Russ.).

4. Gahramanov S, Muldoon LL, Varallyay CG, Li X , Kraemer DF, Fu R , Hamilton BE, Rooney WD , Neuwelt EA. Pseudoprogression of glioblastoma after chemo- and radiation therapy: diagnosis by using dynamic susceptibility-weighted contrast-enhanced perfusion MR imaging with ferumoxytol versus gadoteridol and correlation with survival. Radiology. 2013;266(3):842–852. https://doi.org/10.1148/radiol.12111472

5. Kong DS, Kim ST, Kim EH, Lim DH, Kim WS, Suh YL, Lee JI, Park K, Kim JH, Nam DH. Diagnostic dilemma of pseudoprogression in the treatment of newly diagnosed glioblastomas: the role of assessing relative cerebral blood flow volume and oxygen‑6-methylguanine-DNA methyltransferase promoter methylation status. AJ NR Am J Neuroradiol. 2011;32(2):382–387. https://doi.org/10.3174/ajnr.A2286

6. Ricci PE, Karis JP, Heiserman JE, Fram EK, Bice AN, Drayer BP. Differentiating recurrent tumor from radiation necrosis: time for re-evaluation of positron emission tomography? AJ NR Am J Neuroradiol. 1998;19(3):407–413. https://pubmed.ncbi.nlm.nih.gov/9541290/

7. Hotta M, Minamimoto R, Miwa K. 11C-methionine-PET for differentiating recurrent brain tumor from radiation necrosis: radiomics approach with random forest classifier. the National Center for Global Health and Medicine. 2019;9(1):15666. https://doi.org/10.1038/s41598‑019‑52279‑2

8. Acquitter C, Piram L, Sabatini U, Gilhodes J, Moyal Cohen-Jonathan E, Ken S, Lemasson B. R adiomics-Based Detection of Radionecrosis Using Harmonized Multiparametric MR I. Cancers. 2022;14(2):286. https://doi.org/10.3390/cancers14020286

9. Gao Y, Xiao X, Han B, Li G, Ning X , Wang D, Cai W, Kikinis R, Berkovsky S, Di Ieva A, Zhang L, Ji N, Liu S. Deep Learning Methodology for Differentiating Glioma Recurrence From Radiation Necrosis Using Multimodal Magnetic Resonance Imaging: Algorithm Development and Validation. JM IR Med Inform. 2020;8(11): e19805. https://doi.org/10.2196/19805

10. Soloveva S.N., Urosova V.S. Razrabotka modeli avtomaticheskogo opredeleniya granits gliomy golovnogo mozga, na osnove komplexnogo metoda obrabotki MR T-I CT-izobrazheniya. Sovremennyye naukoyomkiye technologii. 2018;5:83–88. eLIBRARY ID: 35050127 EDN: XPPQKL (In Russ.).

11. Jang K, Russo C, Di Ieva A. Radiomics in gliomas: clinical implications of computational modeling and fractal-based analysis. Neuroradiology. 2020;62(7):771–790. https://doi.org/10.1007/s00234‑020‑02403‑1

12. Pallavi T, Prateek P, Lisa R, Leo W, Chaitra B, Andrew S, Mark C, Anant M. Texture Descriptors to distinguish Radiation Necrosis from Recurrent Brain Tumors on multi-parametric MR I. Proceedings of SPIE — the International Society for Optical Engineering. 2014;9035, 90352B. https://doi.org/10.1117/12.2043969

13. Dohm AE, Nickles TM, Miller CE, Bowers HJ, Miga MI, Attia A, Chan MD, Weis JA . Clinical assessment of a biophysical model for distinguishing tumor progression from radiation necrosis. Med Phys. 2021 Jul;48(7):3852–3859. https://doi.org/10.1002/mp.14999

14. Shur J, Blackledge M, D’Arcy J, Collins DJ, Bali M, O’Leach M, Koh DM. MR I texture feature repeatability and image acquisition factor robustness, a phantom study and in silico study. Eur Radiol Exp. 2021;5(1):2. https://doi.org/10.1186/s41747‑020‑00199‑6