(46-4) 13 * << * >> * Russian * English * Content * All Issues

Improving the efficiency of brain MRI image analysis using feature selection
V.V. Konevsky 1, A.V. Blagov 1, A.V. Gaidel 1,2, A.V. Kapishnikov 3, A.V. Kupriyanov 1, E.N. Surovtsev 3, D.G. Asatryan 4,5

Samara National Research University, 443086, Samara, Russia, Moskovskoye Shosse 34;
IPSI RAS – Branch of the FSRC "Crystallography and Photonics" RAS,
443001, Samara, Russia, Molodogvardeyskaya 151;
Federal State Budgetary Educational Institution of Higher Education "Samara State Medical University" of the Minis-try of Health of the Russian Federation,
443099, Russia, Samara, st. Chapaevskaya, 89;
Russian-Armenian University, Armenia, Yerevan;
Institute for Informatics and Automation Problems of National Academy of Sciences of Armenia, Armenia, Yerevan

 PDF, 807 kB

DOI: 10.18287/2412-6179-CO-1040

Pages: 621-627.

Full text of article: Russian language.

This article discusses the possibility of improving the quality of analysis of MRI images of the brain in various scanning modes by using greedy feature selection algorithms. A total of five MRI sequences were reviewed. The texture features were formed using the MaZda software package. Using an algorithm for recursive feature selection, the accuracy of determining the type of tumor can be increased from 69% to 100%. With the help of the combined algorithm for the selection of signs, it was possible to increase the accuracy of determining the need for treatment of a patient from 60% to 75% and from 81% to 88% in the case of using an additional class of data for patients whose accurate result of treatment is unknown. The use of textural features in combination with a feature that is responsible for the type of meningioma made it possible to unambiguously determine the need for patient treatment.

texture analysis, computer optics, image processing, greedy algorithms, MRI diagnostics, meningioma.

Konevsky VV, Blagov AV, Gaidel AV, Kapishnikov AV, Kupriyanov AV, Surovtsev EN, Asatryan DG. Improving the efficiency of brain MRI image analysis using feature selection. Computer Optics 2022; 46(4): 621-627. DOI: 10.18287/2412-6179-CO-1040.

Theoretical studies were carried out with the support of the RFBR grant No. 19-29-01235 MK. The experimental results were obtained with the support of the Russian Foundation for Basic Research and RA Science Committee in the frames of the joint research project RFBR 20-51-05008 Аrm_a and SCS 20RF-144 accordingly.


  1. Ostrom QT, Patil N, Cioffi G, Waite K, Kruchko C, Barn-holtz-Sloan JS. CBTRUS statistical report: Primary brain and other central nervous system tumors diagnosed in the united states in 2013-2017. Neuro Oncol 2020; 22(Suppl 2): iv1-iv96. DOI: 10.1093/neuonc/noaa200.
  2. Kholin AV. Magnetic resonance imaging for diseases and injuries of the central nervous system [In Russian]. Moscow: "MEDpress-inform" Publisher; 2017.
  3. Louis DN, Perry A, Reifenberger G, von Deimling A, Figa-rella-Branger D, Cavenee WK, Ohgaki H, Wiestler OD, Kleihues P, Ellison DW. 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.
  4. Goldbrunner R, Minniti G, Preusser M, et al. EANO guidelines for the diagnosis and treatment of meningiomas. Lancet Oncol 2016; 17(9): e383-e391. DOI: 10.1016/S1470-2045(16)30321-7.
  5. Goldbrunner R, Weller M, Regis J, et al. EANO guideline on the diagnosis and treatment of vestibular schwannoma. Neuro Oncol 2020; 22(1): 31-45. doi: 10.1093/neuonc/noz153.
  6. Shabani S, Kaushal M, Kaufman B, et al. Intracranial ex-traskeletal mesenchymal chondrosarcoma: Case report and review of the literature of reported cases in adults and children. World Neurosurg 2019; 129: 302-310. doi: 10.1016/j.wneu.2019.05.221.
  7. Strasilla C, Sychra V. Bildgebende Diagnostik des Vestibu-larisschwannoms. HNO 2017; 65(5): 373-380. doi: 10.1007/s00106-016-0227-6.
  8. Kim KH, Kang SJ, Choi JW, et al. Clinical and radiological outcomes of proactive Gamma Knife surgery for asympto-maticmeningiomas compared with the natural course without intervention. J Neurosurg 2018; 130(5): 1740-1749. doi: 10.3171/2017.12.JNS171943.
  9. Nasi D, Zunarelli E, Puzzolante A, Moriconi E, Pavesi G. Early life-threating enlargement of a vestibular schwannoma after gamma knife radiosurgery. Acta Neurochir (Wien) 2020; 162(8): 1977-1982. doi: 10.1007/s00701-020-04434-2.
  10. Kim JH, Jung HH, Chang JH, Chang JW, Park YG, Chang WS. Predictive factors of unfavorable events after gamma knife radiosurgery for vestibular schwannoma. World Neurosurg 2017; 107: 175-184. doi: 10.1016/j.wneu.2017.07.139.
  11. Speckter H, Bido J, Hernandez G, Rivera D, Suazo L, Valenzuela S, Miches I, Oviedo J, Gonzalez C, Stoeter P. Pretreatment texture analysis of routine MR images and shape analysis of the diffusion tensor for prediction of volumetric response after radiosurgery for meningioma. J Neurosurg 2018; 129(Suppl 1): 31-37. doi: 10.3171/2018.7.GKS181327.
  12. Lambin P, Leijenaar RTH, Deist TM, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 2017; 14(12): 749-762. doi: 10.1038/nrclinonc.2017.141.
  13. Agafonova YuD, Gaidel AV, Zelter PM, Kapishnikov AV. Efficiency of machine learning algorithms and convolutional neural network for detecting of pathological changes in MR images of the brain. Computer Optics 2020; 44(2): 266-273. DOI: 10.18287/2412-6179-CO-671.
  14. Wen PY, Chang SM, Van den Bent MJ, Vogelbaum MA, Macdonald DR, Lee EQ. Response assessment in neuro-oncology clinical trials. J Clin Oncol 2017; 35(21): 2439-2449. doi: 10.1200/JCO.2017.72.7511.
  15. Szczypinski PM, Strzelecki M, Materka A. MaZda – a software for texture analysis. Int Symposium on Information Technology Convergence 2007: 245-249. DOI: 10.1109/ISITC.2007.15.
  16. Fernández-Delgado M, Cernadas E, Barro S, Amorim D. Do we need hundreds of classifiers to solve real world classification problems? J Mach Learn Res 2014; 15(1): 3133-3181. DOI: 10.5555/2627435.2697065.
  17. Guyon I, Weston J, Barnhill S, Vapnik V. Gene selection for cancer classification using support vector machines. Mach Learn 2002; 46(1-3): 389-422. DOI: 10.1023/A:1012487302797.
  18. Couvreur C, Bresler Y. On the optimality of the back-ward greedy algorithm for the subset selection problem. SIAM J Matrix Anal Appl 2000; 21(3): 797-808. DOI: 10.1137/S0895479898332928.
  19. Goncharova EF, Gaidel AV. Greedy algorithms of feature selection for multiclass image classification. CEUR Workshop Proceedings 2018; 2210: 38-46.
  20. Marcano-Cedeño A, Quintanilla-Domínguez J, Cortina-Januchs MG, Andina D. Feature selection using sequential forward selection and classification applying artificial metaplasticity neural network. IECON 2010 – 36th Annual Conf on IEEE Industrial Electronics 2010: 2845-2850. DOI: 10.1109/IECON.2010.5675075.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20