Scholarlink

The development of artificial intelligence (AI) has altered medicine. Lung cancer is one of the most common and dangerous tumors worldwide, and it is generally detected late in life, when treatment options are limited. Early identification increases the survival rate of lung cancer, however current diagnostic procedures are time-consuming and prone to human error. This study looks at the use of Convolutional Neural Networks (CNNs) in automated lung cancer diagnosis utilizing medical imaging techniques such as X-rays and CT scans. The study investigates several CNN designs, their efficacy in categorizing lung nodules, and how CNNs might improve accuracy and reduce diagnosis time. The paper discusses the benefits and limitations of employing CNNs in clinical practice, with the goal of improving AI-based diagnostic tools for early diagnosis of lung cancer.

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

Improved Lung Cancer Detection Using Transfer Learning and CNN Architecture

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Shweta Kaushik,
  • Harsh Pandey,
  • Harshit Nagar,
  • Kartikey Suman,
  • Raj Biswas

摘要

The development of artificial intelligence (AI) has altered medicine. Lung cancer is one of the most common and dangerous tumors worldwide, and it is generally detected late in life, when treatment options are limited. Early identification increases the survival rate of lung cancer, however current diagnostic procedures are time-consuming and prone to human error. This study looks at the use of Convolutional Neural Networks (CNNs) in automated lung cancer diagnosis utilizing medical imaging techniques such as X-rays and CT scans. The study investigates several CNN designs, their efficacy in categorizing lung nodules, and how CNNs might improve accuracy and reduce diagnosis time. The paper discusses the benefits and limitations of employing CNNs in clinical practice, with the goal of improving AI-based diagnostic tools for early diagnosis of lung cancer.