Scholarlink

Lungs disease is a life threatening disease. Life may be endangered if not acted upon right time and thus early diagnosis of disease is vital. The aim of this research is to create a deep learning model using VGG16 and EfficientNetB0 and analyze outcome based on test data for a few different categories of lungs diseases. In this research, six classes of lung disease chest x-ray images include Atelectasis, Effusion, Pneumothorax, Bacterial Pneumonia, Viral Pneumonia, and Normal. We have implemented image enhancement technique known as CLAHE (Contrast Limited Adaptive Histogram Equalization) to improve the accuracy of the trained model. VGG16 and EfficientNetB0 (baseline model) architecture are used to train model using transfer learning-based approach. VGG16 and EfficientNetB0 yield classfication accuracy of 93.69% and 70.80% respectively.

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

Multiclass Classification of Lungs Disease Based on Chest X-Ray Image Using Transfer Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Chandan Shah,
  • Sanjeeb Prasad Panday,
  • Sharad Kumar Ghimire

摘要

Lungs disease is a life threatening disease. Life may be endangered if not acted upon right time and thus early diagnosis of disease is vital. The aim of this research is to create a deep learning model using VGG16 and EfficientNetB0 and analyze outcome based on test data for a few different categories of lungs diseases. In this research, six classes of lung disease chest x-ray images include Atelectasis, Effusion, Pneumothorax, Bacterial Pneumonia, Viral Pneumonia, and Normal. We have implemented image enhancement technique known as CLAHE (Contrast Limited Adaptive Histogram Equalization) to improve the accuracy of the trained model. VGG16 and EfficientNetB0 (baseline model) architecture are used to train model using transfer learning-based approach. VGG16 and EfficientNetB0 yield classfication accuracy of 93.69% and 70.80% respectively.