A Lightweight Convolutional Neural Network for Classification of Brain Tumors Using Magnetic Resonance Imaging
The brain, which controls important vital functions such as vision, hearing and movement, negatively affects our lives when it is sick. Of these diseases, the deadliest is undoubtedly the brain tumor, which can occur in all age groups and can be benign or malignant. Therefore, early diagnosis and pr...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sakarya University
2024-12-01
|
| Series: | Sakarya University Journal of Computer and Information Sciences |
| Subjects: | |
| Online Access: | https://dergipark.org.tr/en/download/article-file/4079043 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841556344822300672 |
|---|---|
| author | Mahir Kaya Alper Özatılgan |
| author_facet | Mahir Kaya Alper Özatılgan |
| author_sort | Mahir Kaya |
| collection | DOAJ |
| description | The brain, which controls important vital functions such as vision, hearing and movement, negatively affects our lives when it is sick. Of these diseases, the deadliest is undoubtedly the brain tumor, which can occur in all age groups and can be benign or malignant. Therefore, early diagnosis and prognosis are very important. Magnetic Resonance (MR) images are used for the detection and treatment of brain tumor types. Successful results in the detection of diseases from medical images with Convolutional Neural Networks (CNN) depend on the optimum creation of the number of layers and other hyper-parameters. In this study, we propose a CNN model that will achieve the highest accuracy with the least number of layers. A public data set consisting of 4 different classes (Meningioma, Glioma, Pituitary and Normal) obtained for use in the training of CNN models was trained and tested with 50 different deep learning models designed, and a better result was obtained when compared with the existing studies in the literature with 99.47% accuracy and 99.44% F1 score values. |
| format | Article |
| id | doaj-art-3f316d4c8b3d4ca9ad9d794388d3618e |
| institution | Kabale University |
| issn | 2636-8129 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Sakarya University |
| record_format | Article |
| series | Sakarya University Journal of Computer and Information Sciences |
| spelling | doaj-art-3f316d4c8b3d4ca9ad9d794388d3618e2025-01-07T09:08:01ZengSakarya UniversitySakarya University Journal of Computer and Information Sciences2636-81292024-12-017348249310.35377/saucis...151813928A Lightweight Convolutional Neural Network for Classification of Brain Tumors Using Magnetic Resonance ImagingMahir Kaya0https://orcid.org/0000-0001-9182-271XAlper Özatılgan1https://orcid.org/0009-0003-5344-5142TOKAT GAZİOSMANPAŞA ÜNİVERSİTESİTOKAT GAZIOSMANPASA UNIVERSITY, COMPUTER PROGRAMMING PR.The brain, which controls important vital functions such as vision, hearing and movement, negatively affects our lives when it is sick. Of these diseases, the deadliest is undoubtedly the brain tumor, which can occur in all age groups and can be benign or malignant. Therefore, early diagnosis and prognosis are very important. Magnetic Resonance (MR) images are used for the detection and treatment of brain tumor types. Successful results in the detection of diseases from medical images with Convolutional Neural Networks (CNN) depend on the optimum creation of the number of layers and other hyper-parameters. In this study, we propose a CNN model that will achieve the highest accuracy with the least number of layers. A public data set consisting of 4 different classes (Meningioma, Glioma, Pituitary and Normal) obtained for use in the training of CNN models was trained and tested with 50 different deep learning models designed, and a better result was obtained when compared with the existing studies in the literature with 99.47% accuracy and 99.44% F1 score values.https://dergipark.org.tr/en/download/article-file/4079043lightweight modelbrain tumor classificationconvolutional neural networkdeep learning |
| spellingShingle | Mahir Kaya Alper Özatılgan A Lightweight Convolutional Neural Network for Classification of Brain Tumors Using Magnetic Resonance Imaging Sakarya University Journal of Computer and Information Sciences lightweight model brain tumor classification convolutional neural network deep learning |
| title | A Lightweight Convolutional Neural Network for Classification of Brain Tumors Using Magnetic Resonance Imaging |
| title_full | A Lightweight Convolutional Neural Network for Classification of Brain Tumors Using Magnetic Resonance Imaging |
| title_fullStr | A Lightweight Convolutional Neural Network for Classification of Brain Tumors Using Magnetic Resonance Imaging |
| title_full_unstemmed | A Lightweight Convolutional Neural Network for Classification of Brain Tumors Using Magnetic Resonance Imaging |
| title_short | A Lightweight Convolutional Neural Network for Classification of Brain Tumors Using Magnetic Resonance Imaging |
| title_sort | lightweight convolutional neural network for classification of brain tumors using magnetic resonance imaging |
| topic | lightweight model brain tumor classification convolutional neural network deep learning |
| url | https://dergipark.org.tr/en/download/article-file/4079043 |
| work_keys_str_mv | AT mahirkaya alightweightconvolutionalneuralnetworkforclassificationofbraintumorsusingmagneticresonanceimaging AT alperozatılgan alightweightconvolutionalneuralnetworkforclassificationofbraintumorsusingmagneticresonanceimaging AT mahirkaya lightweightconvolutionalneuralnetworkforclassificationofbraintumorsusingmagneticresonanceimaging AT alperozatılgan lightweightconvolutionalneuralnetworkforclassificationofbraintumorsusingmagneticresonanceimaging |