Scholarlink

This paper presents a comparative analysis of two deep learning architectures, VGG19 and ResNet50, for MRI-based brain tumor detection. The primary objective is to assess the performance of these architectures and determine which yields superior results in terms of accuracy. Utilizing a dataset of MRI brain images, VGG19 and ResNet50 models were trained and evaluated. Experimental results revealed a remarkable accuracy of 99.5% for VGG19 and 93% for ResNet50 in tumor detection. The study includes a comprehensive analysis of the strengths and weaknesses of both architectures, shedding light on their effectiveness in medical image analysis tasks. Ultimately, the findings contribute to the advancement of automated brain tumor detection systems, aiding clinicians in accurate diagnosis and treatment planning.

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

Identifying Brain Tumors from Magnetic Resonance Imaging (MRI) Data Using Deep Learning Algorithms

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Harisudha Kuresan,
  • B. Priyalakshmi,
  • S. Yuvaraj,
  • G. Elavel Visuvanathan

摘要

This paper presents a comparative analysis of two deep learning architectures, VGG19 and ResNet50, for MRI-based brain tumor detection. The primary objective is to assess the performance of these architectures and determine which yields superior results in terms of accuracy. Utilizing a dataset of MRI brain images, VGG19 and ResNet50 models were trained and evaluated. Experimental results revealed a remarkable accuracy of 99.5% for VGG19 and 93% for ResNet50 in tumor detection. The study includes a comprehensive analysis of the strengths and weaknesses of both architectures, shedding light on their effectiveness in medical image analysis tasks. Ultimately, the findings contribute to the advancement of automated brain tumor detection systems, aiding clinicians in accurate diagnosis and treatment planning.