Scholarlink

<p>The emergence of an abnormal cell cluster defines a brain tumor, signifying a highly precarious condition for the brain. Early detection of brain tumors is crucial for ensuring accurate diagnosis and effective treatment formulation. Magnetic Resonance Imaging (MRI) is commonly employed to assess the tumor and holds paramount importance in this regard. This research presents a comprehensive framework for automated brain tumor diagnosis through advanced MRI image analysis. The approach combines the undecimated wavelet transform to extract both frequency and temporal information, followed by feature extraction using a pretrained EfficientNet-B0 model. Principal Component Analysis (PCA) is applied for features selection, enhancing computational efficiency while retaining essential features. The final step involves robust classification using a multi-SVM approach, distinguishing between meningioma, glioma, pituitary, and no tumor classes. The proposed approach achieves an outstanding classification accuracy of 97.5%, underscoring its efficacy in improving the diagnostic capabilities of MRI-based brain tumor classification systems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Advanced Brain Tumor MR Image Classification Using a Combination Undecimated Wavelet Transform, EfficientNet-B0 and PCA via Multi-SVM Analysis

  • 期刊论文

  • 发表日期：

    2025年3月12日

查看全文
  • Oussama Abda,
  • Hilal Naimi

摘要

The emergence of an abnormal cell cluster defines a brain tumor, signifying a highly precarious condition for the brain. Early detection of brain tumors is crucial for ensuring accurate diagnosis and effective treatment formulation. Magnetic Resonance Imaging (MRI) is commonly employed to assess the tumor and holds paramount importance in this regard. This research presents a comprehensive framework for automated brain tumor diagnosis through advanced MRI image analysis. The approach combines the undecimated wavelet transform to extract both frequency and temporal information, followed by feature extraction using a pretrained EfficientNet-B0 model. Principal Component Analysis (PCA) is applied for features selection, enhancing computational efficiency while retaining essential features. The final step involves robust classification using a multi-SVM approach, distinguishing between meningioma, glioma, pituitary, and no tumor classes. The proposed approach achieves an outstanding classification accuracy of 97.5%, underscoring its efficacy in improving the diagnostic capabilities of MRI-based brain tumor classification systems.