Scholarlink

Lung cancer remains a significant global health concern, contributing to a high mortality rate. Early detection is critical to improve survival outcomes and enable timely interventions. Leveraging advancements in artificial intelligence, particularly deep learning, provides a promising avenue for enhancing the accuracy and efficiency of lung cancer diagnosis. This paper proposes a robust lung cancer detection model utilizing DenseNet and EfficientNet architectures to analyze CT scan images. Using a lung cancer dataset sourced from Kaggle, we implemented these techniques to classify benign, malignant, and normal cases effectively. The experiments demonstrated that the proposed models outperform traditional methods, achieving high accuracy and reliability in lung cancer detection.

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

An Efficient Deep Learning-Based Approach for Lung Cancer Detection Using Pretrained Models

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Gottala Surendra Kumar,
  • Chintha Venkata Ramana,
  • Lavanya Kumari Pithani,
  • D. Chandra Mouli,
  • M. Venkata Subbarao,
  • S. Anuradha

摘要

Lung cancer remains a significant global health concern, contributing to a high mortality rate. Early detection is critical to improve survival outcomes and enable timely interventions. Leveraging advancements in artificial intelligence, particularly deep learning, provides a promising avenue for enhancing the accuracy and efficiency of lung cancer diagnosis. This paper proposes a robust lung cancer detection model utilizing DenseNet and EfficientNet architectures to analyze CT scan images. Using a lung cancer dataset sourced from Kaggle, we implemented these techniques to classify benign, malignant, and normal cases effectively. The experiments demonstrated that the proposed models outperform traditional methods, achieving high accuracy and reliability in lung cancer detection.