Scholarlink

This study explores the application of deep learning to brain tumor classification through Magnetic Resonance Imaging (MRI). MRI’s high-resolution images and non-invasive procedure make it an ideal tool for tumor identification. We use Convolutional Neural Networks (CNNs), specifically the pre-trained VGG16, InceptionV3, and EfficientNetB0 models, for the classification of brain tumors. Using a dataset of 2669 MRI scans which have enhanced T1-weights on 334 cases, our study classifies tumor types but not tumor grades. Performance metrics reflect differences in accuracy among the models: VGG16 achieved 76.65%, InceptionV3 achieved 80.20%, and EfficientNetB0 achieved 25.38%. These findings demonstrate the potential of deep learning in brain tumor classification, as well as the differences in performance among various CNN architectures.

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

Enhanced Brain Tumor Detection Using CNN-Based Image Classification: A Deep Learning Approach

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Pranav Karwa,
  • Nabhya Sharma,
  • Aniruddha Bolakhe,
  • Abhay Sharma

摘要

This study explores the application of deep learning to brain tumor classification through Magnetic Resonance Imaging (MRI). MRI’s high-resolution images and non-invasive procedure make it an ideal tool for tumor identification. We use Convolutional Neural Networks (CNNs), specifically the pre-trained VGG16, InceptionV3, and EfficientNetB0 models, for the classification of brain tumors. Using a dataset of 2669 MRI scans which have enhanced T1-weights on 334 cases, our study classifies tumor types but not tumor grades. Performance metrics reflect differences in accuracy among the models: VGG16 achieved 76.65%, InceptionV3 achieved 80.20%, and EfficientNetB0 achieved 25.38%. These findings demonstrate the potential of deep learning in brain tumor classification, as well as the differences in performance among various CNN architectures.