Sineglazov VictorShevchenko Maksym2026-05-252026-05-252025Sineglazov V. M. Definition and Intelligent Extraction of Texture Features of Vestibular Schwannoma Based on MRI Imaging / V. M. Sineglazov, M. V. Shevchenko // Electronics and Control Systems, No 4(86) – Kyiv: TOV “Al'yant”, 2025. – pp. 72–791990-5548DOI:10.18372/1990-5548.86.20626https://er.kai.edu.ua/handle/KAI/70069[1] G. Cioffi, D. N. Yeboa, M. Kelly, N. Patil, N. Manzoor, K. Greppin, K. Takaoka, K. Waite, C. Kruchko, and J. S. Barnholtz-Sloan, “Epidemiology of vestibular schwannoma in the United States, 2004-2016,” Neuro-Oncology Advances, 2020, (1):vdaa135. https://doi.org/10.1093/noajnl/vdaa135 [2] J. P. Marinelli, C. J. Beeler, M. L. Carlson, P. Caye-Thomasen, S. A. Spear, andI. D. Erbele, “Global Incidence of Sporadic Vestibular Schwannoma: A Systematic Review,” Otolaryngology–Head and Neck Surgery. 2022, 167(2), 209–214. https://doi.org/10.1177/01945998211042006 [3] M. L. Carlson and M. J. Link, “Vestibular Schwannomas,” New England Journal of Medicine, 2021, 384(14), 1335–1348. https://doi.org/10.1056/NEJMra2020394 [4] K. A. Lees, N. M. Tombers, M. J. Link, C. L. W. Driscoll, B. A. Neff, J. J. Van Gompel, and M. L. Carlson, “Natural History of Sporadic Vestibular Schwannoma: A Volumetric Study of Tumor Growth,” Otolaryngology–Head and Neck Surgery, 2018, 159(3), pp. 535–542. https://doi.org/10.1177/0194599818770629 [5] S. K. Warfield, K. H. Zou, and W. M. Wells, “Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation,” IEEE Transactions on Medical Imaging. 2004, 23(7), pp. 903–921. https://doi.org/10.1109/TMI.2004.828354 [6] R. J. Gillies, P. E. Kinahan, and H. Hricak. “Radiomics: Images Are More than Pictures, They Are Data,” Radiology. 2016, 278(2), pp. 563–577. https://doi.org/10.1148/radiol.2015151169 [7] B. Varghese, L. Cai, C. Benz, D. Hwang, S. Cen, X. Lei, B. Desai, V. Duddalwar, and J. Gao, “MRI texture analysis for differentiating solitary fibrous tumor from angiomatous meningioma,” Frontiers in Radiology, 2023, 3, 1240544. https://doi.org/10.3389/fradi.2023.1240544 [8] P. P. J. H. Langenhuizen, S. Zinger, S. Leenstra, H. P. M. Kunst, J. J. S. Mulder, P. E. J. Hanssens, P. H. N. de With, and J. B. Verheul, “Radiomics-Based Prediction of Long-term Treatment Response of Vestibular Schwannomas Following Stereotactic Radiosurgery,” Otology & Neurotology, 2020, 41(10), e1321–e1327. https://doi.org/10.1097/MAO.0000000000002886 [9] C. Yang, D. Alvarado, P. K. Ravindran, M. E. Keizer, K. Hovinga, M. P. G. Broen, H. P. M. Kunst, and Y. Temel, “Untreated Vestibular Schwannoma: Analysis of the Determinants of Growth,” Cancers. 2024, 16(21), 3718. https://doi.org/10.3390/cancers16213718 [10] I. Bossi Zanetti, F. Pagni, E. De Bernardi, and R. Liserre, “Radiomic Features and Predictive Models for Tumor Aggressivity in Medical Imaging: A Systematic Review and Meta-Analysis,” Journal of Personalized Medicine, 2023, 13(5), 808. https://doi.org/10.3390/jpm13050808 [11] D. Song, C. Li, Y. Fang, J. Huang, Y. Qu, N. Jiang, and Y. Wang, “Prediction of Tumor Blood Supply in Vestibular Schwannoma Using Radiomics Machine Learning Classifiers,” Scientific Reports, 2021, 11:18872. https://doi.org/10.1038/s41598-021-97865-5 [12] T, Gill, D. W. Hamilton, and A. D. Rajgor, “The Application of Radiomics in Vestibular Schwannomas,” J Laryngol Otol., 139(8), pp. 647–654, 2025. https://doi.org/10.1017/S0022215125000258 [13] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic Minority Over-sampling Technique,” Journal of Artificial Intelligence Research, 2002, 16, pp. 321–357. https://doi.org/10.1613/jair.953 [14] J. Bergstra and Y. Bengio, “Random Search for Hyper-Parameter Optimization,” Journal of Machine Learning Research, 2012, 13, pp. 281–305. https://doi.org/10.5555/2503308.2188395 [15] T. G. Dietterich, “Ensemble Methods in Machine Learning,” Multiple Classifier Systems. Lecture Notes in Computer Science, 2000, 1857, pp. 1–15. https://doi.org/10.1007/3-540-45014-9_1 [16] J. J. M. van Griethuysen, A. Fedorov, C. Parmar, A. Hosny, N. Aucoin, and V. Narayan, R. G. H. Beets-Tan, J. C. Fillion-Robin, S. Pieper, and H. J. W. L. Aerts, “Computational Radiomics System to Decode the Radiographic Phenotype,” Cancer Research, 2017, 77(21), e104–e107. https://doi.org/10.1158/0008-5472.CAN-17-0339 [17] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, 12, pp. 2825–2830, 2011. https://doi.org/10.5555/1953048.2078195. [18] J. C. Reinhold, B. E. Dewey, A. Carass, and J. L. Prince, “Evaluating the Impact of Intensity Normalization on MR Image Synthesis,” Medical Imaging 2019: Image Processing. SPIE. 2019, 10949:109493H. https://doi.org/10.1117/12.2513089 [19] J. Shapey, A. Kujawa, R. Dorent, G. Wang, S. Bisdas, A. Dimitriadis, D. Grishchuk, I. Paddick, N. Kitchen, R. Bradford, S. R. Saeed, S. Ourselin, and T. Vercauteren, “Segmentation of vestibular schwannoma from MRI, an open annotated dataset and baseline algorithm,” Scientific Data, 2021, 8:286. https://doi.org/10.1038/s41597-021-01064-w [20] N. A. George-Jones, R. Chkheidze, S. Moore, J. Wang, J. B. Hunter, “MRI Texture Features are Associated with Vestibular Schwannoma Histology,” Laryngoscope, 2021, 131(6), E2000–E2006. https://doi.org/10.1002/lary.29309The scientific work is devoted to the development of a method for intelligent extraction of textural features of vestibular schwannomas based on magnetic resonance imaging images for predicting tumor growth. The VS-MC-RC2 dataset was analyzed (421 timepoints, 189 patients, 1990–1999). The ML dataset consists of 211 samples (74 growing, 137 stable, imbalance 1.85:1). Gray Level Co-occurrence Matrix and Gray Level Size Zone Matrix matrices, shape features, wavelet transform, and the PyRadiomics v3.0.1 library were used to extract features from T1C images (priority) and T1 images (fallback) with the following parameters: bins = 32, δ = 1 voxel, 13 3D directions. Model v2 (107 original features) achieved an AUC of 0.618. Model v3 (851 features + 8 wavelet decompositions) achieved an AUC of 0.712 (+15.2%). Validation was performed using 10-fold cross-validation with an 80/20 train/test split. Among the top 15 features, 73% were wavelet features (LHH, LLH, HLH). The best feature, original_glszm_ZoneEntropy (F = 12.67, threshold = 4.51), correlates with the Antoni A/B tissue ratio and the proliferative activity of the tumor. Роботу присвячено розробці метода інтелектуального вилучення текстурних ознак вестибулярних шванном на основі МРТ-зображень для прогнозування росту пухлини. Проаналізовано датасет VS-MC-RC2 (421 timepoint, 189 пацієнтів, 1990-1999). ML датасет: 211 зразків (74 зростаючі, 137 стабільні, дисбаланс 1.85:1). Використано матрицю співзустрічальності рівнів сірого, матрицю зон рівнів сірого, Shape Features, Wavelet Transform, бібліотеку PyRadiomics v3.0.1 для вилучення ознак з T1C-зображень (пріоритет) та T1 (резерв) з параметрами: bins = 32, δ = 1 voxel, 13 3D напрямків. Model v2 (107 оригінальних ознак): AUC 0.618. Model v3 (851 ознак + 8 вейвлет-декомпозицій): AUC 0.712 (+15.2%). Валідація: 10-fold CV, навчальна/тестова 80/20. Топ-15 ознак: 73% wavelet features (LHH, LLH, HLH). Найкраща: original_glszm_ZoneEntropy (F = 12.67, threshold = 4.51), що корелює з співвідношенням Antoni A/B тканин і проліферативною активністю пухлини.envestibular schwannomamagnetic resonance imagingradiomicsgray level co-occurrence matrixgray level size zone matrixwaveletRandom ForestPyRadiomicsвестибулярна шванномамагнітно-резонансна томографіяradiomicsматриця співзустрічальності рівнів сірогоматриця зон рівнів сіроговейвлетRandom ForestPyRadiomicsArticle004.855.5(045)