|
This article is cited in 25 scientific papers (total in 25 papers)
IMAGE PROCESSING, PATTERN RECOGNITION
Efficiency of machine learning algorithms and convolutional neural network for detection of pathological changes in MR images of the brain
J. D. Agafonovaa, A. V. Gaidelab, P. M. Zelterc, A. V. Kapishnikovc a Samara National Research University, Moskovskoye shosse 34, 443086, Samara, Russia
b IPSI RAS – Branch of the FSRC “Crystallography and Photonics” RAS,
Molodogvardeyskaya 151, 443001, Samara, Russia
c Samara State Medical University, Chapayevskaya 89, 443099, Samara, Russia
Abstract:
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.
Keywords:
computer vision, image processing, magnetic-resonance imaging, classification, convolutional neural network.
Received: 18.11.2019 Accepted: 20.03.2020
Citation:
J. D. Agafonova, A. V. Gaidel, P. M. Zelter, A. V. Kapishnikov, “Efficiency of machine learning algorithms and convolutional neural network for detection of pathological changes in MR images of the brain”, Computer Optics, 44:2 (2020), 266–273
Linking options:
https://www.mathnet.ru/eng/co789 https://www.mathnet.ru/eng/co/v44/i2/p266
|
Statistics & downloads: |
Abstract page: | 414 | Full-text PDF : | 108 | References: | 32 |
|