Automatic lung disease classification from the chest X-ray images using hybrid deep learning algorithm.

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Computer-Aided Diagnosis

Background:

• Chest X-rays are crucial for diagnosing lung conditions.
• Existing methods for lung disease classification have limitations in accuracy and efficiency.
• Deep learning offers potential for automated and improved diagnostic accuracy.

Purpose of the Study:

• To develop and evaluate a novel Hybrid Deep Learning Algorithm (HDLA) for automatic lung disease classification from chest X-ray images.
• To enhance the accuracy and reduce the computational complexity of lung disease detection.
• To investigate the effectiveness of combining pre-processing, feature extraction, and machine learning classifiers.

Main Methods:

• Pre-processing of chest X-ray images using optimal filtering to enhance quality.
• Automatic feature extraction using a pre-trained 2D Convolutional Neural Network (CNN) model.
• Optimization of extracted features using min-max scaling.
• Classification of features using AdaBoost, Support Vector Machine (SVM), Random Forest (RM), Backpropagation Neural Network (BNN), and Deep Neural Network (DNN).

Main Results:

• The proposed HDLA framework demonstrated improved performance in lung disease classification.
• The model achieved a 3.1% increase in overall accuracy compared to state-of-the-art methods.
• A reduction in computational complexity by 16.91% was observed.

Conclusions:

• The Hybrid Deep Learning Algorithm (HDLA) presents a robust and efficient approach for lung disease classification from chest X-rays.
• The proposed method offers significant improvements in diagnostic accuracy and computational efficiency.
• This framework has the potential to enhance computer-aided diagnosis systems for pulmonary diseases.