WGCAMNet: Wasserstein Generative Adversarial Network Augmented and Custom Attention Mechanism Based Deep Neural Network for Enhanced Brain Tumor Detection and Classification
Brain tumor detection and categorization of its subtypes are essential for early diagnosis and improving patient outcomes. This research presents a cutting-edge approach that employs advanced data augmentation and deep learning methodologies for brain tumor classification. For this work, a dataset o...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-09-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/15/9/560 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850260774774112256 |
|---|---|
| author | Fatema Binte Alam Tahasin Ahmed Fahim Md Asef Md Azad Hossain M. Ali Akber Dewan |
| author_facet | Fatema Binte Alam Tahasin Ahmed Fahim Md Asef Md Azad Hossain M. Ali Akber Dewan |
| author_sort | Fatema Binte Alam |
| collection | DOAJ |
| description | Brain tumor detection and categorization of its subtypes are essential for early diagnosis and improving patient outcomes. This research presents a cutting-edge approach that employs advanced data augmentation and deep learning methodologies for brain tumor classification. For this work, a dataset of 6982 MRI images from the IEEE Data Port was considered, in which a total of 5712 images of four classes (1321 glioma, 1339 meningioma, 1595 no tumor, and 1457 pituitary) were used in the training set and a total of 1270 images of the same four classes were used in the testing set. A Wasserstein Generative Adversarial Network was implemented to generate synthetic images to address class imbalance, resulting in a balanced and consistent dataset. A comparison was conducted between various data augmentation metholodogies demonstrating that Wasserstein Generative Adversarial Network-augmented results perform excellently over traditional augmentation (such as rotation, shift, zoom, etc.) and no augmentation. Additionally, a Gaussian filter and normalization were applied during preprocessing to reduce noise, highlighting its superior accuracy and edge preservation by comparing its performance to Median and Bilateral filters. The classifier model combines parallel feature extraction from modified InceptionV3 and VGG19 followed by custom attention mechanisms for effectively capturing the characteristics of each tumor type. The model was trained for 64 epochs using model checkpoints to save the best-performing model based on validation accuracy and learning rate adjustments. The model achieved a 99.61% accuracy rate on the testing set, with precision, recall, AUC, and loss of 0.9960, 0.9960, 0.0153, and 0.9999, respectively. The proposed architecture’s explainability has been enhanced by t-SNE plots, which show unique tumor clusters, and Grad-CAM representations, which highlight crucial areas in MRI scans. This research showcases an explainable and robust approach for correctly classifying four brain tumor types, combining WGAN-augmented data with advanced deep learning models in feature extraction. The framework effectively manages class imbalance and integrates a custom attention mechanism, outperforming other models, thereby improving diagnostic accuracy and reliability in clinical settings. |
| format | Article |
| id | doaj-art-6d837006a37747cd84bb27d04de278e8 |
| institution | OA Journals |
| issn | 2078-2489 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj-art-6d837006a37747cd84bb27d04de278e82025-08-20T01:55:33ZengMDPI AGInformation2078-24892024-09-0115956010.3390/info15090560WGCAMNet: Wasserstein Generative Adversarial Network Augmented and Custom Attention Mechanism Based Deep Neural Network for Enhanced Brain Tumor Detection and ClassificationFatema Binte Alam0Tahasin Ahmed Fahim1Md Asef2Md Azad Hossain3M. Ali Akber Dewan4Institute of Information and Communication Technology, Bangladesh University of Engineering and Technology, Dhaka 1000, BangladeshDepartment of Electrical and Electronic Engineering, University of Chittagong, Chittagong 4331, BangladeshDepartment of Electrical and Computer Engineering, Auburn University, Auburn, AL 36849, USADepartment of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chittagong 4349, BangladeshSchool of Computing and Information Systems, Faculty of Science and Technology, Athabasca University, Athabasca, AB T9S 3A3, CanadaBrain tumor detection and categorization of its subtypes are essential for early diagnosis and improving patient outcomes. This research presents a cutting-edge approach that employs advanced data augmentation and deep learning methodologies for brain tumor classification. For this work, a dataset of 6982 MRI images from the IEEE Data Port was considered, in which a total of 5712 images of four classes (1321 glioma, 1339 meningioma, 1595 no tumor, and 1457 pituitary) were used in the training set and a total of 1270 images of the same four classes were used in the testing set. A Wasserstein Generative Adversarial Network was implemented to generate synthetic images to address class imbalance, resulting in a balanced and consistent dataset. A comparison was conducted between various data augmentation metholodogies demonstrating that Wasserstein Generative Adversarial Network-augmented results perform excellently over traditional augmentation (such as rotation, shift, zoom, etc.) and no augmentation. Additionally, a Gaussian filter and normalization were applied during preprocessing to reduce noise, highlighting its superior accuracy and edge preservation by comparing its performance to Median and Bilateral filters. The classifier model combines parallel feature extraction from modified InceptionV3 and VGG19 followed by custom attention mechanisms for effectively capturing the characteristics of each tumor type. The model was trained for 64 epochs using model checkpoints to save the best-performing model based on validation accuracy and learning rate adjustments. The model achieved a 99.61% accuracy rate on the testing set, with precision, recall, AUC, and loss of 0.9960, 0.9960, 0.0153, and 0.9999, respectively. The proposed architecture’s explainability has been enhanced by t-SNE plots, which show unique tumor clusters, and Grad-CAM representations, which highlight crucial areas in MRI scans. This research showcases an explainable and robust approach for correctly classifying four brain tumor types, combining WGAN-augmented data with advanced deep learning models in feature extraction. The framework effectively manages class imbalance and integrates a custom attention mechanism, outperforming other models, thereby improving diagnostic accuracy and reliability in clinical settings.https://www.mdpi.com/2078-2489/15/9/560attention mechanismbrain tumorconvolutional neural networkdeep neural networkWGAN |
| spellingShingle | Fatema Binte Alam Tahasin Ahmed Fahim Md Asef Md Azad Hossain M. Ali Akber Dewan WGCAMNet: Wasserstein Generative Adversarial Network Augmented and Custom Attention Mechanism Based Deep Neural Network for Enhanced Brain Tumor Detection and Classification Information attention mechanism brain tumor convolutional neural network deep neural network WGAN |
| title | WGCAMNet: Wasserstein Generative Adversarial Network Augmented and Custom Attention Mechanism Based Deep Neural Network for Enhanced Brain Tumor Detection and Classification |
| title_full | WGCAMNet: Wasserstein Generative Adversarial Network Augmented and Custom Attention Mechanism Based Deep Neural Network for Enhanced Brain Tumor Detection and Classification |
| title_fullStr | WGCAMNet: Wasserstein Generative Adversarial Network Augmented and Custom Attention Mechanism Based Deep Neural Network for Enhanced Brain Tumor Detection and Classification |
| title_full_unstemmed | WGCAMNet: Wasserstein Generative Adversarial Network Augmented and Custom Attention Mechanism Based Deep Neural Network for Enhanced Brain Tumor Detection and Classification |
| title_short | WGCAMNet: Wasserstein Generative Adversarial Network Augmented and Custom Attention Mechanism Based Deep Neural Network for Enhanced Brain Tumor Detection and Classification |
| title_sort | wgcamnet wasserstein generative adversarial network augmented and custom attention mechanism based deep neural network for enhanced brain tumor detection and classification |
| topic | attention mechanism brain tumor convolutional neural network deep neural network WGAN |
| url | https://www.mdpi.com/2078-2489/15/9/560 |
| work_keys_str_mv | AT fatemabintealam wgcamnetwassersteingenerativeadversarialnetworkaugmentedandcustomattentionmechanismbaseddeepneuralnetworkforenhancedbraintumordetectionandclassification AT tahasinahmedfahim wgcamnetwassersteingenerativeadversarialnetworkaugmentedandcustomattentionmechanismbaseddeepneuralnetworkforenhancedbraintumordetectionandclassification AT mdasef wgcamnetwassersteingenerativeadversarialnetworkaugmentedandcustomattentionmechanismbaseddeepneuralnetworkforenhancedbraintumordetectionandclassification AT mdazadhossain wgcamnetwassersteingenerativeadversarialnetworkaugmentedandcustomattentionmechanismbaseddeepneuralnetworkforenhancedbraintumordetectionandclassification AT maliakberdewan wgcamnetwassersteingenerativeadversarialnetworkaugmentedandcustomattentionmechanismbaseddeepneuralnetworkforenhancedbraintumordetectionandclassification |