Answers are grounded in this paper and cite their sources.
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.
No takes yet. Share an insight, caveat, or question.
Soloveva et al. (2023) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: