Chest X-Ray Disease Classification

  • Unique Paper ID: 179969
  • Volume: 11
  • Issue: 12
  • PageNo: 8255-8266
  • Abstract:
  • This research presents an automated, hybrid machine learning and deep learning system for chest X-ray disease classification, aiming to improve diagnostic accuracy and streamline clinical workflows. The system addresses fracture detection, pneumonia prediction, and multi-disease classification using a combination of traditional machine learning and deep learning techniques. For fracture detection, Histogram of Oriented Gradients (HOG) features are used with an SVM classifier. Pneumonia prediction employs a Convolutional Neural Network (CNN), while multi-disease classification combines SVM, Random Forest (RF), and an ensemble model to classify conditions like pneumonia, fibrosis, and cardiomegaly. Data preprocessing techniques, such as image normalization and augmentation, enhance model performance. The system is integrated into a Flask-based web application, allowing healthcare professionals to upload chest X-rays and receive real-time predictions. This hybrid model, combining the strengths of HOG+SVM and CNN, balances accuracy and computational efficiency, reducing radiologists' workload, improving diagnostic accuracy, and enabling early detection of critical conditions. The research suggests future potential in expanding to other medical imaging domains and integrating with healthcare infrastructure

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 12
  • PageNo: 8255-8266

Chest X-Ray Disease Classification

Related Articles