Scholarlink

Brain tumors are aggressive and potentially fatal, requiring rapid and precise detection. Their varied symptoms complicate diagnosis and treatment. MRI is critical for detecting brain lesions and is widely used by radiologists. This study proposes a CNN-based approach to classify brain tumors using 3,064 T1-weighted contrast-enhanced MRI images from 233 patients. By leveraging deep learning techniques, modified VGG16, an 18-layer CNN model, achieved 93% accuracy, precision, recall, and F1-score, demonstrating its potential to improve diagnostic accuracy in neuro-oncology and support clinical decision-making.

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

Brain Tumor Classification Through Transfer Learning Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Shaghayegh Khalighiyan,
  • Mohammad Hassanzadeh,
  • Esam Abdel-Raheem

摘要

Brain tumors are aggressive and potentially fatal, requiring rapid and precise detection. Their varied symptoms complicate diagnosis and treatment. MRI is critical for detecting brain lesions and is widely used by radiologists. This study proposes a CNN-based approach to classify brain tumors using 3,064 T1-weighted contrast-enhanced MRI images from 233 patients. By leveraging deep learning techniques, modified VGG16, an 18-layer CNN model, achieved 93% accuracy, precision, recall, and F1-score, demonstrating its potential to improve diagnostic accuracy in neuro-oncology and support clinical decision-making.