Scholarlink

Battle against respiratory diseases whose impact on global health is significant, especially pneumonia, tuberculosis, and lung cancer requires timely, accurate, and quick diagnosis. In this paper, deep learning techniques, particularly convolutional neural networks (CNN), are used to automate disease diagnosis and classification from chest X-rays. By utilizing ResNet and DenseNet architectures on the NIH Chest X-ray dataset, which contains more than 10,000 images, we were able to achieve a diagnostic accuracy of up to 91.19%, which is higher than several previous systems. On Inceptionv3, ResNet50, and VGG-16. Scalable deployment within clinical settings is possible with the suggested system, which also enables performance comparable to that of expert radiologists.

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

Advanced Chest X-Ray Analysis for Predicting Pulmonary Diseases Using Deep Learning Techniques

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Vanshraj Singh Rathore,
  • Akshar Kankar,
  • Manoj Kushwaha

摘要

Battle against respiratory diseases whose impact on global health is significant, especially pneumonia, tuberculosis, and lung cancer requires timely, accurate, and quick diagnosis. In this paper, deep learning techniques, particularly convolutional neural networks (CNN), are used to automate disease diagnosis and classification from chest X-rays. By utilizing ResNet and DenseNet architectures on the NIH Chest X-ray dataset, which contains more than 10,000 images, we were able to achieve a diagnostic accuracy of up to 91.19%, which is higher than several previous systems. On Inceptionv3, ResNet50, and VGG-16. Scalable deployment within clinical settings is possible with the suggested system, which also enables performance comparable to that of expert radiologists.