An integrated framework for COVID-19 classification based on classical and quantum transfer learning from a chest...

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Quantum Computing

Background:

• COVID-19 has caused a global health crisis with significant economic impact.
• Early detection of COVID-19 is crucial for reducing mortality rates.
• Artificial intelligence (AI) shows promise in early disease detection from medical images.

Purpose of the Study:

• To develop and evaluate an AI-based system for accurate and early detection of COVID-19 using chest radiographs.
• To compare the performance of the proposed AI model against existing methods.

Main Methods:

• A two-phase approach was employed, utilizing deep features (DFs) from pre-trained models (AlexNet, MobileNet) and feature selection (PCA).
• Phase II involved a quantum transfer learning model with a ResNet-18 pre-trained model and a 4-qubit quantum circuit for classification.
• The methodology was validated on two public chest X-ray datasets.

Main Results:

• The proposed AI methodology achieved a high accuracy index of 99.0%.
• The model demonstrated effectiveness in classifying three categories: COVID-19 positive, normal, and pneumonia radiographs.
• Experimental results indicate superior performance compared to other recently published approaches.

Conclusions:

• The developed AI and quantum transfer learning model offers a highly accurate and efficient solution for early COVID-19 detection.
• This approach has the potential to significantly aid in managing the COVID-19 pandemic through rapid and reliable diagnosis.
• The study highlights the growing importance of AI and quantum computing in medical diagnostics.