Brain tumor classification using deep convolutional neural networks

This study presents a comparative analysis of various convolutional neural network (CNN) models for brain tumor detection on MRI medical images. The primary aim was to assess the effectiveness of different CNN architectures in accurately identifying brain tumors. Multiple models were trained, includ...

Full description

Saved in:
Bibliographic Details
Main Authors: M. Nurtay, M. Kissina, A. Tau, A. Akhmetov, G. Alina, N. Mutovina
Format: Article
Language:English
Published: Samara National Research University 2025-04-01
Series:Компьютерная оптика
Subjects:
Online Access:https://computeroptics.ru/KO/Annot/KO49-2/490210.html
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849232861668835328
author M. Nurtay
M. Kissina
A. Tau
A. Akhmetov
G. Alina
N. Mutovina
author_facet M. Nurtay
M. Kissina
A. Tau
A. Akhmetov
G. Alina
N. Mutovina
author_sort M. Nurtay
collection DOAJ
description This study presents a comparative analysis of various convolutional neural network (CNN) models for brain tumor detection on MRI medical images. The primary aim was to assess the effectiveness of different CNN architectures in accurately identifying brain tumors. Multiple models were trained, including a custom-designed CNN with its specific layer architecture, and models based on Transfer Learning utilizing pre-trained neural networks: ResNet-50, VGG-16, and Xception. Performance evaluation of each model in terms of accuracy metrics such as precision, recall, F1-score, and confusion matrix on a test dataset was carried out. The dataset used in this study was obtained from the openly accessible Kaggle competition "Brain Tumor Detection from MRI." This dataset consisted of four classes: glioma, meningioma, no tumor (healthy), and pituitary, ensuring a balanced representation. Testing four models revealed that the custom CNN architecture, utilizing separable convolutions and batch normalization, achieved an average ROC AUC score of 0.99, outperforming the other models. Moreover, this model demonstrated an accuracy of 0.94, indicating its robust performance in brain tumor classification on MRI images.
format Article
id doaj-art-cffb4d61dd0c4854934fba409bcf29ba
institution Kabale University
issn 0134-2452
2412-6179
language English
publishDate 2025-04-01
publisher Samara National Research University
record_format Article
series Компьютерная оптика
spelling doaj-art-cffb4d61dd0c4854934fba409bcf29ba2025-08-20T17:20:18ZengSamara National Research UniversityКомпьютерная оптика0134-24522412-61792025-04-0149225326210.18287/2412-6179-CO-1476Brain tumor classification using deep convolutional neural networksM. Nurtay0M. Kissina1A. Tau2A. Akhmetov3G. Alina4N. Mutovina5Abylkas Saginov Karagandy Technical UniversityAbylkas Saginov Karagandy Technical UniversityAbylkas Saginov Karagandy Technical UniversityAbylkas Saginov Karagandy Technical UniversityAbylkas Saginov Karagandy Technical UniversityAbylkas Saginov Karagandy Technical UniversityThis study presents a comparative analysis of various convolutional neural network (CNN) models for brain tumor detection on MRI medical images. The primary aim was to assess the effectiveness of different CNN architectures in accurately identifying brain tumors. Multiple models were trained, including a custom-designed CNN with its specific layer architecture, and models based on Transfer Learning utilizing pre-trained neural networks: ResNet-50, VGG-16, and Xception. Performance evaluation of each model in terms of accuracy metrics such as precision, recall, F1-score, and confusion matrix on a test dataset was carried out. The dataset used in this study was obtained from the openly accessible Kaggle competition "Brain Tumor Detection from MRI." This dataset consisted of four classes: glioma, meningioma, no tumor (healthy), and pituitary, ensuring a balanced representation. Testing four models revealed that the custom CNN architecture, utilizing separable convolutions and batch normalization, achieved an average ROC AUC score of 0.99, outperforming the other models. Moreover, this model demonstrated an accuracy of 0.94, indicating its robust performance in brain tumor classification on MRI images.https://computeroptics.ru/KO/Annot/KO49-2/490210.htmlbrain tumorcomputer visionpattern recognitionmachine learningdeep learningconvolutional neural networktransfer learning
spellingShingle M. Nurtay
M. Kissina
A. Tau
A. Akhmetov
G. Alina
N. Mutovina
Brain tumor classification using deep convolutional neural networks
Компьютерная оптика
brain tumor
computer vision
pattern recognition
machine learning
deep learning
convolutional neural network
transfer learning
title Brain tumor classification using deep convolutional neural networks
title_full Brain tumor classification using deep convolutional neural networks
title_fullStr Brain tumor classification using deep convolutional neural networks
title_full_unstemmed Brain tumor classification using deep convolutional neural networks
title_short Brain tumor classification using deep convolutional neural networks
title_sort brain tumor classification using deep convolutional neural networks
topic brain tumor
computer vision
pattern recognition
machine learning
deep learning
convolutional neural network
transfer learning
url https://computeroptics.ru/KO/Annot/KO49-2/490210.html
work_keys_str_mv AT mnurtay braintumorclassificationusingdeepconvolutionalneuralnetworks
AT mkissina braintumorclassificationusingdeepconvolutionalneuralnetworks
AT atau braintumorclassificationusingdeepconvolutionalneuralnetworks
AT aakhmetov braintumorclassificationusingdeepconvolutionalneuralnetworks
AT galina braintumorclassificationusingdeepconvolutionalneuralnetworks
AT nmutovina braintumorclassificationusingdeepconvolutionalneuralnetworks