A cognitive framework based on deep neural network for classification of coronavirus disease

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Epidemiology

Background:

• The global spread of coronavirus (CorV) since December 2019 poses a significant public health challenge.
• Effective diagnosis and prevention strategies are crucial for managing the pandemic.

Purpose of the Study:

• To develop and validate a deep learning model for the early detection of CorV from chest X-ray images.
• To enable timely implementation of preventive measures.

Main Methods:

• A hybrid deep learning model integrating spatio-temporal analysis was employed.
• The SQueezeNet model was utilized for classifying CorV patients.
• Chest X-ray images were used as input for the diagnostic system.

Main Results:

• The proposed hybrid deep learning model achieved an average accuracy of 97.8% in identifying CorV-suspected individuals.
• The model demonstrated enhanced accuracy for early identification and time-sensitive decision-making.
• Performance was validated through experimental comparison with state-of-the-art models.

Conclusions:

• The developed deep learning approach offers a promising tool for the early and accurate diagnosis of CorV.
• This technology can significantly aid in controlling the spread of the virus through timely interventions.