Efficiency of machine learning algorithms and convolutional neural network for detection of pathological changes in MR images of the brain
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...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Samara National Research University
2020-04-01
|
| Series: | Компьютерная оптика |
| Subjects: | |
| Online Access: | http://computeroptics.smr.ru/KO/PDF/KO44-2/440217.pdf |
| _version_ | 1818487312155148288 |
|---|---|
| author | Julia Agafonova Andrey Gaidel Pavel Zelter Aleksandr Kapishnikov |
| author_facet | Julia Agafonova Andrey Gaidel Pavel Zelter Aleksandr Kapishnikov |
| author_sort | Julia Agafonova |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-10T16:36:13Z |
| format | Article |
| id | doaj.art-10ef9b52ace14218827915abb4a7d6cb |
| institution | Directory Open Access Journal |
| issn | 0134-2452 2412-6179 |
| language | English |
| last_indexed | 2024-12-10T16:36:13Z |
| publishDate | 2020-04-01 |
| publisher | Samara National Research University |
| record_format | Article |
| series | Компьютерная оптика |
| spelling | doaj.art-10ef9b52ace14218827915abb4a7d6cb2022-12-22T01:41:24ZengSamara National Research UniversityКомпьютерная оптика0134-24522412-61792020-04-0144226627310.18287/2412-6179-CO-671Efficiency of machine learning algorithms and convolutional neural network for detection of pathological changes in MR images of the brainJulia Agafonova0Andrey Gaidel 1Pavel Zelter2Aleksandr Kapishnikov3Samara National Research University, Moskovskoye shosse 34, 443086, Samara, RussiaSamara National Research University, Moskovskoye shosse 34, 443086, Samara, Russia; IPSI RAS – Branch of the FSRC “Crystallography and Photonics” RAS, Molodogvardeyskaya 151, 443001, Samara, RussiaSamara State Medical University, Chapayevskaya 89, 443099, Samara, RussiaSamara State Medical University, Chapayevskaya 89, 443099, Samara, RussiaWe 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.http://computeroptics.smr.ru/KO/PDF/KO44-2/440217.pdfcomputer visionimage processingmagnetic-resonance imagingclassificationconvolutional neural network |
| spellingShingle | Julia Agafonova Andrey Gaidel Pavel Zelter Aleksandr Kapishnikov Efficiency of machine learning algorithms and convolutional neural network for detection of pathological changes in MR images of the brain Компьютерная оптика computer vision image processing magnetic-resonance imaging classification convolutional neural network |
| title | Efficiency of machine learning algorithms and convolutional neural network for detection of pathological changes in MR images of the brain |
| title_full | Efficiency of machine learning algorithms and convolutional neural network for detection of pathological changes in MR images of the brain |
| title_fullStr | Efficiency of machine learning algorithms and convolutional neural network for detection of pathological changes in MR images of the brain |
| title_full_unstemmed | Efficiency of machine learning algorithms and convolutional neural network for detection of pathological changes in MR images of the brain |
| title_short | Efficiency of machine learning algorithms and convolutional neural network for detection of pathological changes in MR images of the brain |
| title_sort | efficiency of machine learning algorithms and convolutional neural network for detection of pathological changes in mr images of the brain |
| topic | computer vision image processing magnetic-resonance imaging classification convolutional neural network |
| url | http://computeroptics.smr.ru/KO/PDF/KO44-2/440217.pdf |
| work_keys_str_mv | AT juliaagafonova efficiencyofmachinelearningalgorithmsandconvolutionalneuralnetworkfordetectionofpathologicalchangesinmrimagesofthebrain AT andreygaidel efficiencyofmachinelearningalgorithmsandconvolutionalneuralnetworkfordetectionofpathologicalchangesinmrimagesofthebrain AT pavelzelter efficiencyofmachinelearningalgorithmsandconvolutionalneuralnetworkfordetectionofpathologicalchangesinmrimagesofthebrain AT aleksandrkapishnikov efficiencyofmachinelearningalgorithmsandconvolutionalneuralnetworkfordetectionofpathologicalchangesinmrimagesofthebrain |