Variability Regularized Feature Selection (VaRFS) for optimal identification of robust and discriminable features from medical imaging

Key Points

• Optimal identification of robust and discriminable features enhances medical imaging performance.
• Evaluated against standard methods, the new algorithm achieved a 15% increase in feature accuracy.
• Analysis using variability regularized feature selection across various imaging datasets demonstrates effectiveness.
• Highlights the need for advanced features to improve diagnostic outcomes in clinical settings.