Scholarlink

Pulmonary diseases constitute a great threat to global health and therefore, their early detection remains very important for improving survival rates. This paper demonstrates the effectiveness of convolutional neural networks in classifying certain lung diseases from chest X-ray images. We introduced Bayesian optimization in hyperparameter tuning to maximize the performance of the model. The experimental findings reveal that, generally, the performance would experience significant improvement after optimization, with MobileNet-BO achieving an accuracy of 93.53%. These results further confirm the important role played by hyperparameter optimization in improving the performance of CNNs, particularly in critical medical applications adhering to accuracy.

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

Optimizing Convolutional Neural Networks for Lung Disease Classification Using Bayesian Optimization

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Fatima Fatih,
  • Hanae El Fahfouhi,
  • Zakariae En-Naimani,
  • Khalid Haddouch

摘要

Pulmonary diseases constitute a great threat to global health and therefore, their early detection remains very important for improving survival rates. This paper demonstrates the effectiveness of convolutional neural networks in classifying certain lung diseases from chest X-ray images. We introduced Bayesian optimization in hyperparameter tuning to maximize the performance of the model. The experimental findings reveal that, generally, the performance would experience significant improvement after optimization, with MobileNet-BO achieving an accuracy of 93.53%. These results further confirm the important role played by hyperparameter optimization in improving the performance of CNNs, particularly in critical medical applications adhering to accuracy.