COVID-19 Diagnosis Using Capsule Network and Fuzzy C-Means and Mayfly Optimization Algorithm

Area of Science:

• Medical Imaging and Artificial Intelligence
• Computational Pathology
• Infectious Disease Diagnostics

Background:

• Early and accurate diagnosis of COVID-19 is critical for effective treatment and control.
• Computer-aided diagnostic tools can enhance the accuracy and efficiency of disease detection.
• Chest X-ray imaging is a widely accessible modality for assessing pulmonary conditions, including COVID-19.

Purpose of the Study:

• To propose an optimal computer-aided method for the accurate diagnosis of COVID-19 using chest X-ray images.
• To develop an enhanced capsule network (ECN) integrated with fuzzy C-ordered means (FCOM) and optimized by the mayfly optimization (MFO) algorithm.
• To evaluate the performance of the proposed method against existing state-of-the-art techniques.

Main Methods:

• Implementation of a hybrid approach combining fuzzy C-ordered means (FCOM) and an enhanced capsule network (ECN).
• Optimization of the enhanced capsule network (ECN) using the mayfly optimization (MFO) algorithm.
• Validation of the proposed method on publicly available chest X-ray datasets for COVID-19 diagnosis.

Main Results:

• The proposed FCOM-MFO-ECN method achieved a high accuracy of 97.08% and precision of 97.29%.
• The method demonstrated superior performance compared to established methods like FOMPA, MID, and 4S-DT.
• Sensitivity reached 97.1%, and the F1-score was 97.47%, indicating excellent diagnostic capability.

Conclusions:

• The developed fuzzy C-ordered means (FCOM) and mayfly optimization (MFO)-enhanced capsule network (ECN) offers a highly accurate and reliable approach for COVID-19 diagnosis from chest X-rays.
• This computer-aided method shows significant potential for improving diagnostic accuracy in clinical settings.
• The study highlights the effectiveness of integrating advanced optimization algorithms with deep learning models for medical image analysis.