ANFIS-Net for automatic detection of COVID-19

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Computational Biology

Background:

• Infectious diseases, including COVID-19, are a leading global cause of mortality.
• The rapid spread of COVID-19 necessitates efficient and automated diagnostic tools.
• Fuzzy logic offers a robust method for handling uncertainty in medical diagnoses.

Purpose of the Study:

• To propose an Adaptive Neuro-Fuzzy Inference System (ANFIS) for automatic COVID-19 detection.
• To utilize texture analysis via Gray Level Co-occurrence Matrix (GLCM) for feature extraction from chest X-ray images.
• To demonstrate the efficacy of ANFIS, particularly on small datasets, in contrast to deep learning methods.

Main Methods:

• Chest X-ray images were analyzed using texture analysis with the Gray Level Co-occurrence Matrix (GLCM) technique.
• An Adaptive Neuro-Fuzzy Inference System (ANFIS) was developed for automated classification.
• The ANFIS model's performance was evaluated and compared against existing state-of-the-art techniques.

Main Results:

• The proposed ANFIS-based method demonstrated promising performance accuracy in detecting COVID-19 from chest X-rays.
• The ANFIS approach achieved performance comparable to complex deep learning architectures.
• A key advantage of the ANFIS method is its ability to function effectively with small datasets.

Conclusions:

• The ANFIS model presents an efficient and accurate solution for automated COVID-19 diagnosis using chest X-ray images.
• This approach offers a viable alternative to deep learning, especially when limited data is available.
• The ANFIS system shows potential for assisting healthcare professionals in rapid patient assessment.