Classification of Brain MRI Tumor Images Based on Deep Learning PGGAN Augmentation
The wide prevalence of brain tumors in all age groups necessitates having the ability to make an early and accurate identification of the tumor type and thus select the most appropriate treatment plans. The application of convolutional neural networks (CNNs) has helped radiologists to more accuratel...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/12/2343 |
| _version_ | 1797505436959637504 |
|---|---|
| author | Ahmed M. Gab Allah Amany M. Sarhan Nada M. Elshennawy |
| author_facet | Ahmed M. Gab Allah Amany M. Sarhan Nada M. Elshennawy |
| author_sort | Ahmed M. Gab Allah |
| collection | DOAJ |
| description | The wide prevalence of brain tumors in all age groups necessitates having the ability to make an early and accurate identification of the tumor type and thus select the most appropriate treatment plans. The application of convolutional neural networks (CNNs) has helped radiologists to more accurately classify the type of brain tumor from magnetic resonance images (MRIs). The learning of CNN suffers from overfitting if a suboptimal number of MRIs are introduced to the system. Recognized as the current best solution to this problem, the augmentation method allows for the optimization of the learning stage and thus maximizes the overall efficiency. The main objective of this study is to examine the efficacy of a new approach to the classification of brain tumor MRIs through the use of a VGG19 features extractor coupled with one of three types of classifiers. A progressive growing generative adversarial network (PGGAN) augmentation model is used to produce ‘realistic’ MRIs of brain tumors and help overcome the shortage of images needed for deep learning. Results indicated the ability of our framework to classify gliomas, meningiomas, and pituitary tumors more accurately than in previous studies with an accuracy of 98.54%. Other performance metrics were also examined. |
| first_indexed | 2024-03-10T04:18:34Z |
| format | Article |
| id | doaj.art-01baa7cb9783443087167e5a0c50dc1c |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T04:18:34Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-01baa7cb9783443087167e5a0c50dc1c2023-11-23T07:54:45ZengMDPI AGDiagnostics2075-44182021-12-011112234310.3390/diagnostics11122343Classification of Brain MRI Tumor Images Based on Deep Learning PGGAN AugmentationAhmed M. Gab Allah0Amany M. Sarhan1Nada M. Elshennawy2Department of Computers and Control Engineering, Faculty of Engineering, Tanta University, Tanta 31733, EgyptDepartment of Computers and Control Engineering, Faculty of Engineering, Tanta University, Tanta 31733, EgyptDepartment of Computers and Control Engineering, Faculty of Engineering, Tanta University, Tanta 31733, EgyptThe wide prevalence of brain tumors in all age groups necessitates having the ability to make an early and accurate identification of the tumor type and thus select the most appropriate treatment plans. The application of convolutional neural networks (CNNs) has helped radiologists to more accurately classify the type of brain tumor from magnetic resonance images (MRIs). The learning of CNN suffers from overfitting if a suboptimal number of MRIs are introduced to the system. Recognized as the current best solution to this problem, the augmentation method allows for the optimization of the learning stage and thus maximizes the overall efficiency. The main objective of this study is to examine the efficacy of a new approach to the classification of brain tumor MRIs through the use of a VGG19 features extractor coupled with one of three types of classifiers. A progressive growing generative adversarial network (PGGAN) augmentation model is used to produce ‘realistic’ MRIs of brain tumors and help overcome the shortage of images needed for deep learning. Results indicated the ability of our framework to classify gliomas, meningiomas, and pituitary tumors more accurately than in previous studies with an accuracy of 98.54%. Other performance metrics were also examined.https://www.mdpi.com/2075-4418/11/12/2343brain tumormagnetic resonance imagingdeep learninggenerative adversarial networkconvolutional neural network |
| spellingShingle | Ahmed M. Gab Allah Amany M. Sarhan Nada M. Elshennawy Classification of Brain MRI Tumor Images Based on Deep Learning PGGAN Augmentation Diagnostics brain tumor magnetic resonance imaging deep learning generative adversarial network convolutional neural network |
| title | Classification of Brain MRI Tumor Images Based on Deep Learning PGGAN Augmentation |
| title_full | Classification of Brain MRI Tumor Images Based on Deep Learning PGGAN Augmentation |
| title_fullStr | Classification of Brain MRI Tumor Images Based on Deep Learning PGGAN Augmentation |
| title_full_unstemmed | Classification of Brain MRI Tumor Images Based on Deep Learning PGGAN Augmentation |
| title_short | Classification of Brain MRI Tumor Images Based on Deep Learning PGGAN Augmentation |
| title_sort | classification of brain mri tumor images based on deep learning pggan augmentation |
| topic | brain tumor magnetic resonance imaging deep learning generative adversarial network convolutional neural network |
| url | https://www.mdpi.com/2075-4418/11/12/2343 |
| work_keys_str_mv | AT ahmedmgaballah classificationofbrainmritumorimagesbasedondeeplearningpgganaugmentation AT amanymsarhan classificationofbrainmritumorimagesbasedondeeplearningpgganaugmentation AT nadamelshennawy classificationofbrainmritumorimagesbasedondeeplearningpgganaugmentation |