N. Yu. Ilyasova1, A.A. Selezneva2, N.S. Demin3, E.N. Surovcev4, A. V. Kapishnikov5

1–3 Samara National Research University n. a. S.P. Korolyov (Samara, Russia)
1,3 Image Processing Systems Institute, NRC «Kurchatov Institute» (Moscow, Russia)
4,5 FSBEI HE «Samara State Medical University MOH Russia» (Samara, Russia)
1 ilyasova.nata@gmail.com, 2 seleznevalisha@gmail.com, 3 volfgunus@gmail.com, 4 evgeniisurovcev@mail.ru, 5 a.v.kapishnikov@samsmu.ru

The development of technologies, in particular artificial intelligence, creates the prerequisites for the intensive implementation of new methods in medicine. They are especially relevant in tasks that require an extraordinary approach. Such a task is to predict the growth of primary extra-axial tumors based on MRI images using deep learning methods. Over the past 5 years, only one study has been conducted on this topic, which concerns only neurinomas and does not consider the influence of tissues around the tumor.

The aim of this work is to develop a technology for predicting the growth of primary extra-axial brain tumors based on radiomic analysis of MRI images, including tumor segmentation, calculation of radiomic features, and subsequent construction of a predictive model.

The use of developed technology for predicting the growth of extra-axial tumors based on radiomic parameters has demonstrated its importance for clinical decision-making. The results confirm the relevance and effectiveness of radiomic approaches in oncology, opening new possibilities for more personalized treatment.

Ilyasova N.Yu., Selezneva A.A., Demin N.S., Surovtsev E.N., Kapishnikov A.V. Application of neural networks to predict the growth of primary extra-axial brain tumors. Biomedicine Radioengineering. 2025. V. 28. № 5. P. 125–128. DOI: https:// doi.org/10.18127/j1560 4136-202505-25 (In Russian)

1. Ostrom Q.T., Price M., Neff C. et al. CBTRUS Statistical Report: Primary Brain and Other Central Nervous System Tumors Diagnosed in the United States in 2015-2019. Neuro Oncol. 2022. V. 24. № 5. P. v1–v95. DOI: 10.1093/neuonc/noac202.
2. Goldbrunner R., Stavrinou P., Jenkinson M.D. et al. EANO guideline on the diagnosis and management of meningiomas. Neuro Oncol. 2021. V. 23. № 11. P. 1821–1834. DOI: 10.1093/neuonc/noab150.
3. Goldbrunner R., Weller M., Regis J. et al. EANO guideline on the diagnosis and treatment of vestibular schwannoma. Neuro Oncol. 2020. Vol. 22. № 1. P. 31–45. DOI: 10.1093/neuonc/noz153.
4. Itoyama T., Nakaura T., Hamasaki T. et al. Whole Tumor Radiomics Analysis for Risk Factors Associated with Rapid Growth of Vestibular Schwannoma in Contrast-Enhanced T1-Weighted Images. World Neurosurg. 2022. V. 166. P. e572–e582. DOI: 10.1016/j.wneu. 2022.07.058.
5. Maggio I., Franceschi E., Tosoni A. et al. Meningioma: not always a benign tumor. A review of advances in the treatment of meningiomas. CNS Oncology. 2021. V. 10. P. CNS72. DOI: 10.2217/cns-2021-0003.
6. Ghosh S., Chaki A., Santosh K. Improved U-Net architecture with VGG-16 for brain tumor segmentation. Physical and Engineering Sciences in Medicine. 2021. V. 44. P. 703–712. DOI: 10.1007/s13246-021-01019-w.
7. Agafonova, Yu.D., Gaidel A.V., Zelter P.M., Kapishnikov A.V. Efficiency of machine learning algorithms and convolutional neural network for detection of pathological changes on magnetic resonance images of the brain. Computer Optics. 2020. V. 44. № 2. P. 266–273. DOI: 10.18287/2412-6179-CO-671.
8. Mittal M., Goyal L.M., Kaur S. et al. Deep learning based enhanced tumor segmentation approach for MR brain images. Applied Soft Computing. 2019. V. 78. P. 346–354. DOI: 10.1016/j.asoc.2019.02.036.
9. Claus E.B., Bondy M. L., Schildkraut J. M. et al. Epidemiology of intracranial meningioma. Neurosurgery. 2005. V. 57. P. 1088–1095. DOI: 10.1227/01.neu.0000188281.91351.b9.
10. Van Timmeren J., Cester D., Tanadini-Lang S. et al. Radiomics in medical imaging. “how-to” guide and critical reflection. Insights into Imaging. 2020. V. 11. № 1. P. 91–107. DOI: 10.1186/s13244-020-00887-2.