(44-2) 17 * << * >> * Russian * English * Content * All Issues

Efficiency of machine learning algorithms and convolutional neural network for detection of pathological changes in MR images of the brain

Yu.D. Agafonova 1, A.V. Gaidel 1,2, P.M. Zelter 3, A.V. Kapishnikov 3

Samara National Research University, Moskovskoye shosse 34, 443086, Samara, Russia;
IPSI RAS – Branch of the FSRC “Crystallography and Photonics” RAS,
Molodogvardeyskaya 151, 443001, Samara, Russia;
Samara State Medical University, Chapayevskaya 89, 443099, Samara, Russia

 PDF, 1292 kB

DOI: 10.18287/2412-6179-CO-671

Pages: 266-273.

Full text of article: Russian language.

We compare approaches for the automatic detection of pathological changes in brain MRI images that are visible to the naked eye. We analyse multi-stage approaches based on deep learning and threshold processing. A convolutional neural network was formed, a classifier was built based on the use of an ensemble of decision trees, and an algorithm was created for multi-stage image processing. Because of experimental studies, it was found that the most effective method for recognizing images of magnetic resonance imaging is an approach based on an ensemble of decision trees. With its help, 95 % of the images from the test sample were classified correctly. At the same time, using the convolutional neural network, it was possible to classify correctly all images containing the area of pathological changes. The data obtained can be used in practice for the diagnosis of brain diseases, for automating the processing of a large number of studies of magnetic resonance imaging.

computer vision, image processing, magnetic-resonance imaging, classification, convolutional neural network.

Agafonova YuD, Gaidel AV, Zelter PM, Kapishnikov AV. Efficiency of machine learning algorithms and convolutional neural network for detection of pathological changes in MR images of the brain. Computer Optics 2020; 44(2): 266-273. DOI: 10.18287/2412-6179-CO-671.

The work was partially funded by the Russian Foundation for Basic Research under grants No. 19-29-01235 and 19-29-01135 (theoretical results) and the Ministry of Science and Higher Education within the State assignment to the FSRC “Crystallography and Photonics” RAS No. 007-GZ/Ch3363/26 (numerical calculations).


  1. Telrandhe SR, Pimpalkar A, Kendhe A. Detection of brain tumor from MRI images by using segmentation & SVM. 2016 World Conference on Futuristic Trends in Research and Innovation for Social Welfare (Startup Conclave); Coimbatore: 2016.
  2. Kaus MR, Warfield SK, Nabavi A, Black PM, Jolesz FA, Kikinis R. Automated segmentation of MR images of brain tumors. Radiology 2001; 218(2): 586-591.
  3. Yang T, Song J, Li L. A deep learning model integrating SK-TPCNN and random forests for brain tumor segmentation in MR. Biocybern Biomed Eng 2019; 39(3): 613-623.
  4. Halder A, Talukdar NA. Brain tissue segmentation using improved kernelized rough-fuzzy C-means with spatio-contextual information from MRI. Magnetic Resonance Imaging 2019; 62: 129-151.
  5. He Y, Yu X, Liu C, Zhang J, Hu K, Zhu HC. A 3D dual path U-Net of cancer segmentation based on MRI. IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) 2018: 268-272.
  6. Smelkina NA, Kosarev RN, Nikonorov AV, Bairikov IM, Ryabov KN, Avdeev AV, Kazanskiy NL. Reconstruction of anatomical structures using statistical shape modeling. Computer Optics 2017; 41(6): 897-904. DOI: 10.18287/2412-6179-2017-41-6-897-904.
  7. Wadhwa A, Bhardwaj A, Verna VS. A review on brain tumor segmentation of MRI images. Magnetic Resonance Imaging 2019; 61: 247-259.
  8. Gaidel АВ, Zelter PM, Kapishnikov AV. Computed tomography texture analysis capabilities in diagnosing a chronic obstructive pulmonary disease. Computer Optics 2014; 38(4): 843-850.
  9. Gaidel AV. Method of automatic ROI selection on lung CT images. Procedia Engineering 2017; 201: 258-264. DOI: 10.1016/j.proeng.2017.09.612.
  10. Agafonova JD, Gaidel AV. Localization of the area of pathological changes in the images of braint MRIs [In Russian]. In Book: Advanced Information Technologies and Scientific Computing (PIT 2019). Samara: “SNC RAN” Publisher; 2019: 362-365.
  11. Serra J. Image analysis and mathematical morphology. Orlando: Academic Press; 1983.
  12. Suzuki S, Be KA. Topological structural analysis of digitized binary images by border following. Computer Vision, Graphics, and Image Processing 1985; 30(1): 32-46.
  13. Fitzgibbon AW, Fisher RB. A buyer’s guide to conic fitting. Proc 6th British Conf Machine Vis 1995; 2: 513-522.
  14. Sklansky J. Finding the convex hull of a simple polygon. Patt Recogn Lett 1982; 1(2): 79-83.
  15. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Communications of the ACM 2017; 60(6): 84-90.
  16. Herrick R, Horton W, Olsen T, McKay M, Archie KA, Marcus DS. XNAT Central: Open sourcing imaging research data. NeuroImage 2016; 124(Pt B): 1093-1096.
  17. Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P, Moore S, Phillips S, Maffitt D, Pringle M, Tarbox L, Prior F. The Cancer Imaging Archive (TCIA): Maintaining and operating a public information repository. J Digit Imaging 2013; 26(6): 1045-1057.
  18. Breiman L. Random forests. Machine Learning 2001; 45(1): 5-32.

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