A Hybrid Deep Learning-Based Approach for Brain Tumor Classification

Keyphrases

• Brain Tumor 100%
• Deep Learning Methods 100%
• Brain Tumor Detection 100%
• Hybrid Deep Learning 100%
• GoogLeNet 75%
• Traditional Machine Learning 50%
• Classification Basis 25%
• ResNet50 25%
• F1 Score 25%
• Machine Learning Learning 25%
• Deep Machine Learning 25%
• Feature Map 25%
• Leaky ReLU 25%
• Meningioma Subtype 25%
• MRI Images 25%
• Deep Learning 25%
• Convolutional Neural Network Model 25%
• Feature Extraction 25%
• Art Classification 25%
• Glioma Tumor 25%
• AlexNet 25%
• Handcrafted Features 25%
• Detection Accuracy 25%
• Machine Learning Classifiers 25%
• SqueezeNet 25%
• Pituitary Tumor 25%
• Publicly Available 25%
• Evaluation Purposes 25%
• ResNet101 25%
• ShuffleNet 25%
• Convolutional Neural Network Architecture 25%
• Accurate Classification 25%
• Research Datasets 25%
• Expressiveness 25%
• ReLU Activation Function 25%
• DarkNet-53 25%
• New Layers 25%
• Proposed Methodology 25%
• Classification Results 25%
• MobileNetV2 25%

Computer Science

• Deep Learning Method 100%
• Machine Learning 66%
• Learning System 66%
• Convolutional Neural Network 66%
• Feature Map 33%
• Deep Learning Model 33%
• Feature Extraction 33%
• MobileNetV2 33%
• Neural Network Model 33%
• ResNet50 33%
• Activation Function 33%
• Tumor Detection 33%
• classification result 33%
• Neural Network Architecture 33%

Neuroscience

• Intracranial Tumor 100%
• Neural Network 28%
• Magnetic Resonance Imaging 14%
• Meningioma 14%
• Pituitary Tumour 14%