PCA-Based Incremental Extreme Learning Machine (PCA-IELM) for COVID-19 Patient Diagnosis Using Chest X-Ray Images.

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Machine Learning

Background:

• The COVID-19 pandemic has severely impacted global health and economies.
• Early and accurate detection of COVID-19 is crucial to control its spread.
• Radiological diagnosis using X-ray images is a key tool for identifying COVID-19.

Purpose of the Study:

• To propose a novel method, PCA-IELM, for automated COVID-19 detection from X-ray images.
• To enhance the accuracy and efficiency of COVID-19 diagnosis.
• To support radiologists in identifying positive cases faster.

Main Methods:

• Principal Component Analysis (PCA) for feature extraction and dimension reduction.
• Incremental Extreme Learning Machine (ELM) for efficient classification.
• Testing the PCA-IELM method on a dataset of COVID-19 patient chest X-ray images.

Main Results:

• PCA-IELM demonstrated high performance metrics: 98.11% accuracy, 96.11% precision, 97.50% recall, and 98.50% F1-score.
• The method effectively reduces input dimensions by extracting essential image information.
• PCA-IELM exhibited a faster training speed compared to multi-layer neural networks.

Conclusions:

• The PCA-IELM method offers a promising approach for accurate and rapid COVID-19 detection.
• This technique can significantly aid in the early identification of COVID-19 patients.
• PCA-IELM outperforms existing methods like PCA-SVM and PCA-ELM in diagnostic performance.