Related Experiment Video
Updated: Oct 18, 2025
14:27
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
Published on: June 26, 2013
15.9K
Multiple Sclerosis Recognition by Biorthogonal Wavelet Features and Fitness-Scaled Adaptive Genetic Algorithm.
Shui-Hua Wang1, Xianwei Jiang2, Yu-Dong Zhang3
1School of Mathematics and Actuarial Science, University of Leicester, Leicester, United Kingdom.
Frontiers in Neuroscience
|September 30, 2021
Summary
A new method using biorthogonal wavelets and a genetic algorithm (BWF-FAGA) accurately recognizes multiple sclerosis (MS). This approach outperforms existing artificial intelligence and deep learning techniques for MS detection.
Area of Science:
- Biomedical Engineering
- Signal Processing
- Artificial Intelligence
Background:
- Multiple sclerosis (MS) is a debilitating neurological disease affecting the brain and spinal cord.
- Accurate and early recognition of MS is crucial for effective patient management.
Purpose of the Study:
- To propose a novel and highly accurate method for multiple sclerosis recognition.
- To introduce the Biorthogonal Wavelet Feature-Fitness-Scaled Adaptive Genetic Algorithm (BWF-FAGA) method.
Main Methods:
- Extraction of multiscale coefficients using the bior4.4 wavelet.
- Calculation of three types of biorthogonal wavelet features.
- Optimization using a Fitness-Scaled Adaptive Genetic Algorithm (FAGA).
- Application of multiple-way data augmentation with 10-fold cross-validation.
Main Results:
- Achieved high sensitivity (98.00 ± 0.95%), specificity (97.78 ± 0.95%), and accuracy (97.89 ± 0.94%).
- Attained an Area Under the Curve (AUC) of 0.9876.
- Demonstrated superior performance compared to 10 state-of-the-art MS recognition methods.
Conclusions:
- The proposed BWF-FAGA method offers a significant advancement in multiple sclerosis recognition.
- This novel approach surpasses existing artificial intelligence and deep learning techniques.
