Combining the Transformer and Convolution for Effective Brain Tumor Classification Using MRI Images
In the world, brain tumor (BT) is considered the major cause of death related to cancer, which requires early and accurate detection for patient survival. In the early detection of BT, computer-aided diagnosis (CAD) plays a significant role, the medical experts receive a second opinion through CAD d...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/6/3680 |
| _version_ | 1797613665847869440 |
|---|---|
| author | Mohammed Aloraini Asma Khan Suliman Aladhadh Shabana Habib Mohammed F. Alsharekh Muhammad Islam |
| author_facet | Mohammed Aloraini Asma Khan Suliman Aladhadh Shabana Habib Mohammed F. Alsharekh Muhammad Islam |
| author_sort | Mohammed Aloraini |
| collection | DOAJ |
| description | In the world, brain tumor (BT) is considered the major cause of death related to cancer, which requires early and accurate detection for patient survival. In the early detection of BT, computer-aided diagnosis (CAD) plays a significant role, the medical experts receive a second opinion through CAD during image examination. Several researchers proposed different methods based on traditional machine learning (TML) and deep learning (DL). The TML requires hand-crafted features engineering, which is a time-consuming process to select an optimal features extractor and requires domain experts to have enough knowledge of optimal features selection. The DL methods outperform the TML due to the end-to-end automatic, high-level, and robust feature extraction mechanism. In BT classification, the deep learning methods have a great potential to capture local features by convolution operation, but the ability of global features extraction to keep Long-range dependencies is relatively weak. A self-attention mechanism in Vision Transformer (ViT) has the ability to model long-range dependencies which is very important for precise BT classification. Therefore, we employ a hybrid transformer-enhanced convolutional neural network (TECNN)-based model for BT classification, where the CNN is used for local feature extraction and the transformer employs an attention mechanism to extract global features. Experiments are performed on two public datasets that are BraTS 2018 and Figshare. The experimental results of our model using BraTS 2018 and Figshare datasets achieves an average accuracy of 96.75% and 99.10%, respectively. In the experiments, the proposed model outperforms several state-of-the-art methods using BraTS 2018 and Figshare datasets by achieving 3.06% and 1.06% accuracy, respectively. |
| first_indexed | 2024-03-11T06:59:02Z |
| format | Article |
| id | doaj.art-e71c73bec3ba4f908382ce19317b6b81 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T06:59:02Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e71c73bec3ba4f908382ce19317b6b812023-11-17T09:25:15ZengMDPI AGApplied Sciences2076-34172023-03-01136368010.3390/app13063680Combining the Transformer and Convolution for Effective Brain Tumor Classification Using MRI ImagesMohammed Aloraini0Asma Khan1Suliman Aladhadh2Shabana Habib3Mohammed F. Alsharekh4Muhammad Islam5Department of Electrical Engineering, College of Engineering, Qassim University, Unaizah 56452, Saudi ArabiaDepartment of Computer Science, Islamia College Peshawar, Peshawar 25120, PakistanDepartment of Information Technology, College of Computer, Qassim University, Buraydah 51452, Saudi ArabiaDepartment of Information Technology, College of Computer, Qassim University, Buraydah 51452, Saudi ArabiaDepartment of Electrical Engineering, College of Engineering, Qassim University, Unaizah 56452, Saudi ArabiaDepartment of Electrical Engineering, College of Engineering and Information Technology, Onaizah Colleges, Onaizah 56447, Saudi ArabiaIn the world, brain tumor (BT) is considered the major cause of death related to cancer, which requires early and accurate detection for patient survival. In the early detection of BT, computer-aided diagnosis (CAD) plays a significant role, the medical experts receive a second opinion through CAD during image examination. Several researchers proposed different methods based on traditional machine learning (TML) and deep learning (DL). The TML requires hand-crafted features engineering, which is a time-consuming process to select an optimal features extractor and requires domain experts to have enough knowledge of optimal features selection. The DL methods outperform the TML due to the end-to-end automatic, high-level, and robust feature extraction mechanism. In BT classification, the deep learning methods have a great potential to capture local features by convolution operation, but the ability of global features extraction to keep Long-range dependencies is relatively weak. A self-attention mechanism in Vision Transformer (ViT) has the ability to model long-range dependencies which is very important for precise BT classification. Therefore, we employ a hybrid transformer-enhanced convolutional neural network (TECNN)-based model for BT classification, where the CNN is used for local feature extraction and the transformer employs an attention mechanism to extract global features. Experiments are performed on two public datasets that are BraTS 2018 and Figshare. The experimental results of our model using BraTS 2018 and Figshare datasets achieves an average accuracy of 96.75% and 99.10%, respectively. In the experiments, the proposed model outperforms several state-of-the-art methods using BraTS 2018 and Figshare datasets by achieving 3.06% and 1.06% accuracy, respectively.https://www.mdpi.com/2076-3417/13/6/3680brain tumorclassificationconvolutional neural networkMRISVMVision Transformers |
| spellingShingle | Mohammed Aloraini Asma Khan Suliman Aladhadh Shabana Habib Mohammed F. Alsharekh Muhammad Islam Combining the Transformer and Convolution for Effective Brain Tumor Classification Using MRI Images Applied Sciences brain tumor classification convolutional neural network MRI SVM Vision Transformers |
| title | Combining the Transformer and Convolution for Effective Brain Tumor Classification Using MRI Images |
| title_full | Combining the Transformer and Convolution for Effective Brain Tumor Classification Using MRI Images |
| title_fullStr | Combining the Transformer and Convolution for Effective Brain Tumor Classification Using MRI Images |
| title_full_unstemmed | Combining the Transformer and Convolution for Effective Brain Tumor Classification Using MRI Images |
| title_short | Combining the Transformer and Convolution for Effective Brain Tumor Classification Using MRI Images |
| title_sort | combining the transformer and convolution for effective brain tumor classification using mri images |
| topic | brain tumor classification convolutional neural network MRI SVM Vision Transformers |
| url | https://www.mdpi.com/2076-3417/13/6/3680 |
| work_keys_str_mv | AT mohammedaloraini combiningthetransformerandconvolutionforeffectivebraintumorclassificationusingmriimages AT asmakhan combiningthetransformerandconvolutionforeffectivebraintumorclassificationusingmriimages AT sulimanaladhadh combiningthetransformerandconvolutionforeffectivebraintumorclassificationusingmriimages AT shabanahabib combiningthetransformerandconvolutionforeffectivebraintumorclassificationusingmriimages AT mohammedfalsharekh combiningthetransformerandconvolutionforeffectivebraintumorclassificationusingmriimages AT muhammadislam combiningthetransformerandconvolutionforeffectivebraintumorclassificationusingmriimages |