Related Experiment Video
Updated: May 1, 2026
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
14.1K
FACNN: fuzzy-based adaptive convolution neural network for classifying COVID-19 in noisy CXR images
Suganyadevi S1, Seethalakshmi V2
1Department of ECE, KPR Institute of Engineering and Technology, Coimbatore, 641 407, India. suganya3223@gmail.com.
Medical & Biological Engineering & Computing
|May 6, 2024
Summary
A novel fuzzy-based adaptive convolution neural network (FACNN) improves COVID-19 detection from chest X-rays. This AI model enhances accuracy and reduces false positives, aiding in faster, more precise diagnosis.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Computational Pathology
Background:
- Chest X-rays (CXR) are crucial for early COVID-19 diagnosis.
- Computer and intelligent algorithms enhance CXR-based detection precision.
Purpose of the Study:
- To propose a fuzzy-based adaptive convolution neural network (FACNN) model.
- To improve COVID-19 detection precision and reduce false rates in CXR analysis.
Main Methods:
- Utilized a fuzzy process for feature extraction and pixel classification (labeled vs. unknown).
- Derived membership functions based on high-precision features for detection and false rate suppression.
- Employed recurrent training of the convolution neural network based on feature availability, verified using fuzzy derivatives.
Main Results:
- The FACNN model demonstrated significant improvements: accuracy (+14.36%), precision (+8.74%), and feature extraction (+12.35%).
- Reduced false detection rates by 10.35% and extraction time by 10.66%.
Conclusions:
- The proposed FACNN model offers enhanced accuracy and efficiency for COVID-19 detection using chest X-rays.
- This AI-driven approach effectively suppresses false rates and improves diagnostic precision.
