Combining the Transformer and Convolution for Effective Brain Tumor Classification Using MRI Images

被引:32
作者
Aloraini, Mohammed [1 ]
Khan, Asma [2 ]
Aladhadh, Suliman [3 ]
Habib, Shabana [3 ]
Alsharekh, Mohammed F. [1 ]
Islam, Muhammad [4 ]
机构
[1] Qassim Univ, Coll Engn, Dept Elect Engn, Unaizah 56452, Saudi Arabia
[2] Islamia Coll Peshawar, Dept Comp Sci, Peshawar 25120, Pakistan
[3] Qassim Univ, Coll Comp, Dept Informat Technol, Buraydah 51452, Saudi Arabia
[4] Onaizah Coll, Coll Engn & Informat Technol, Dept Elect Engn, Onaizah 56447, Saudi Arabia
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 06期
关键词
brain tumor; classification; convolutional neural network; MRI; SVM; Vision Transformers; NEURAL-NETWORK; SEGMENTATION; FEATURES; CNN;
D O I
10.3390/app13063680
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
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.
引用
收藏
页数:20
相关论文
共 79 条
[1]  
Abbood AA, 2021, Indonesian Journal of Electrical Engineering and Computer Science, V22, P252, DOI [10.11591/ijeecs.v22.i1.pp252-259, 10.11591/ijeecs.v22.i1.pp252-259, DOI 10.11591/IJEECS.V22.I1.PP252-259]
[2]   Differential Deep Convolutional Neural Network Model for Brain Tumor Classification [J].
Abd El Kader, Isselmou ;
Xu, Guizhi ;
Shuai, Zhang ;
Saminu, Sani ;
Javaid, Imran ;
Salim Ahmad, Isah .
BRAIN SCIENCES, 2021, 11 (03)
[3]  
Abir T.A., 2018, Int. J. Sci. Res. Sci. Eng. Technol, V4, P65, DOI DOI 10.32628/IJSRSET184814
[4]   Brain Tumor Classification Using Convolutional Neural Network [J].
Abiwinanda, Nyoman ;
Hanif, Muhammad ;
Hesaputra, S. Tafwida ;
Handayani, Astri ;
Mengko, Tati Rajab .
WORLD CONGRESS ON MEDICAL PHYSICS AND BIOMEDICAL ENGINEERING 2018, VOL 1, 2019, 68 (01) :183-189
[5]   From Handcrafted to Deep-Learning-Based Cancer Radiomics Challenges and opportunities [J].
Afshar, Parnian ;
Mohammadi, Arash ;
Plataniotis, Konstantinos N. ;
Oikonomou, Anastasia ;
Benali, Habib .
IEEE SIGNAL PROCESSING MAGAZINE, 2019, 36 (04) :132-160
[6]   An Efficient Lightweight Hybrid Model with Attention Mechanism for Enhancer Sequence Recognition [J].
Aladhadh, Suliman ;
Almatroodi, Saleh A. ;
Habib, Shabana ;
Alabdulatif, Abdulatif ;
Khattak, Saeed Ullah ;
Islam, Muhammad .
BIOMOLECULES, 2023, 13 (01)
[7]   An Effective Skin Cancer Classification Mechanism via Medical Vision Transformer [J].
Aladhadh, Suliman ;
Alsanea, Majed ;
Aloraini, Mohammed ;
Khan, Taimoor ;
Habib, Shabana ;
Islam, Muhammad .
SENSORS, 2022, 22 (11)
[8]   Hajj Crowd Management Using CNN-Based Approach [J].
Albattah, Waleed ;
Khel, Muhammad Haris Kaka ;
Habib, Shabana ;
Islam, Muhammad ;
Khan, Sheroz ;
Kadir, Kushsairy Abdul .
CMC-COMPUTERS MATERIALS & CONTINUA, 2021, 66 (02) :2183-2197
[9]   To Assist Oncologists: An Efficient Machine Learning-Based Approach for Anti-Cancer Peptides Classification [J].
Alsanea, Majed ;
Dukyil, Abdulsalam S. ;
Afnan ;
Riaz, Bushra ;
Alebeisat, Farhan ;
Islam, Muhammad ;
Habib, Shabana .
SENSORS, 2022, 22 (11)
[10]   Automatic skin lesions detection from images through microscopic hybrid features set and machine learning classifiers [J].
Alyami, Jaber ;
Rehman, Amjad ;
Sadad, Tariq ;
Alruwaythi, Maryam ;
Saba, Tanzila ;
Bahaj, Saeed Ali .
MICROSCOPY RESEARCH AND TECHNIQUE, 2022, 85 (11) :3600-3607